MF研究者総覧

Researcher Database

Advance
Hidenori Kawamura
Faculty of Information Science and Technology　Computer Science and Information Technology　Synergetic Information Engineering
Professor
Researchers' Page on researchmap
Last Updated :2024/05/14

Researcher Profile and Settings

Affiliation

  • Faculty of Information Science and Technology　Computer Science and Information Technology　Synergetic Information Engineering

Job Title

  • Professor

URL

J-Global ID

Research Interests

  • 人工知能   ニューラルネットワーク   ディープラーニング   機械学習   進化システム   マルチエージェントシステム   データマイニング   ロボティクス   観光情報学   複雑系工学   Multiagent Systems   Tourism Infomatics   Complex Systems Engineering   

Research Areas

  • Informatics / Intelligent robotics
  • Informatics / Perceptual information processing
  • Informatics / Intelligent informatics
  • Informatics / Information theory

Educational Organization

Academic & Professional Experience

  • 2016/01 - Today Laboratory of Harmonious Systems Engineering, Research Group of Synergetic Information Engineering, Division of Computer Science and Information Technology, Faculty of Information Science and Technology Professor
  • 2007/04 - 2015/12 情報科学研究科 複合情報学専攻 複雑系工学講座 調和系工学研究室 准教授
  • 2006/10 - 2007/03 情報科学研究科 複合情報学専攻 複雑系工学講座 調和系工学研究室 助教授
  • 2006 - 2007 Associate Professor
  • 2004/04 - 2006/09 情報科学研究科 複合情報学専攻 複雑系工学講座 調和系工学研究室 助手
  • 2004 - 2006 Research Associate
  • 2000/04 - 2004/03 工学研究科 システム情報工学専攻 複雑系工学講座 調和系工学分野 助手
  • 2000 - 2004 Research Associate
  • 1999 - 2000 工学研究科 システム情報工学専攻 複雑系工学講座 調和系工学分野 日本学術振興会特別研究員
  • 1999 - 2000 Postdoctoral Fellowships of Japan Society for the Promotion of Science

Education

  • 1998/04 - 2000/03  北海道大学
  • 1996/04 - 1998/03  Hokkaido University
  • 1992/04 - 1996/03  Hokkaido University  Graduate School, Division of Engineering

Association Memberships

  • 電子情報通信学会   ソフトウェア科学会   電気学会   人工知能学会   情報処理学会   観光情報学会   さっぽろ観光情報学研究会   日本オペレーションズ・リサーチ学会   JSAIIPSJORSJSociety for Tourism Informatics   

Research Activities

Published Papers

  • 吉田拓海, 横山想一郎, 山下倫央, 川村秀憲
    電子情報通信学会論文誌 D(Web) J105-D (1) 60 - 74 1881-0225 2022/01 [Refereed]
  • Kohei Hatamoto, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura
    Transactions of the Japanese Society for Artificial Intelligence 一般社団法人 人工知能学会 36 (5) AG21 - C_1 1346-0714 2021/09/01 [Refereed]
     

    Auctions have long been used to trade goods that do not have a fixed price. In recent years, with the spread of internet auctions, the number of goods that can be handled at a single auction has increased. The time required to make a bidding decision per product remains the same even when a large number of goods are traded, such as in wholesale. For this reason, a large time is required to determine the valuation in proportion to the number of goods. This causes problems for the auctioneer and the participants. It is difficult for the auctioneer to set the reserve price and for the participants to decide the amount and target of their bids. It is necessary to understand the value of a product and estimate the end price. Since there is no fixed price for a product sold in an auction, we estimate the distribution of end prices instead of point estimation. We focus on B2B luxury brand goods auctions, where the number of goods is large and the bidding decision cost per product is high. We estimate the distribution of successful bids on actual auction data of wristwatches, which have large transaction volumes in the auction. The performance of the proposed method was measured by MAE, RMSE, and MAPE, and was close to that of experts. The proposed method was able to capture the data distribution. Finally, we show that the end price distribution estimation can be used to support both auctioneers and participants in brand-name auctions with a large number of goods.

  • Kohei Hatamoto, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura
    WI/IAT 658 - 663 2021 [Refereed]
  • Impression Estimation of Clothing Images by Semi-Supervised Learning Using CNN
    Mizuki Kambe, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura
    Proceedings of the 26th International Symposium on Artificial Life and Robotics 2021 [Refereed]
  • Yuto Mori, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Norio Kato, Masato Mori
    Artificial Life and Robotics 1433-5298 2021 [Refereed]
     
    Owing to technological advancements in medicine and nursing, an aging population has emerged in Japan. Consequently, the elderly need extra care and support from their caregivers. This study develops an autonomous forearm-supported walker for users who can handle the walker without any support. The three main functions of the proposed walker include moving with the weight support of the user, assisting the user in walking, and autonomous driving. These functions are expected to assist the patient in walking, hence reducing the burden on the nursing staff. In this study, we experimented on the degree of support in straight-line walking using the walking support function of the proposed walker. The effect of the walking support function was confirmed by measuring the muscle activity of five muscles of the subject’s lower limbs. In addition, we confirmed the accuracy of the autonomous driving function by checking the results of the self-position estimation during 90 turns and forward movement. Additionally, we conducted a route driving experiment that confirmed the possibility of driving without a significant deviation from the set route.
  • Development of a forearm-supported walker with walking support and autonomous driving functions
    Yuto Mori, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Masato Mori, Norio Kato
    Proceedings of the 26th International Symposium on Artificial Life and Robotics 2021 [Refereed]
  • Detection of fish species in sonar images using CNN
    Yudai Hirama, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Keiji Suzuki, Masaaki Wada
    Proceedings of the 26th International Symposium on Artificial Life and Robotics 2021 [Refereed]
  • Deep Reinforcement Learning for Smooth Traffic Flow at An Intersection
    Tomoya Oda, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Takayuki Warabino, Tomohiko Ogishi, Hideaki Tanaka
    Proceedings of the 26th International Symposium on Artificial Life and Robotics 2021 [Refereed]
  • Development of a Traffic-Simulation Environment Using RC Cars
    Tomoya Oda, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Takayuki Warabino, Tomohiko Ogishi, Hideaki Tanaka
    The 1st International Workshop on Frontiers of Multi-Agent Systems 2020 [Refereed]
  • 横山 想一郎, 山下 倫央, 川村 秀憲
    Journal of the Japanese Society for Artificial Intelligence 一般社団法人 人工知能学会 (34) 467 - 474 2188-2266 2019/07/01
  • ZHENG Yeqin, YOKOYAMA Soichiro, YAMASHITA Tomohisa, KAWAMURA Hidenori
    JSAI Technical Report, Type 2 SIG 一般社団法人 人工知能学会 2019 (SAI-034) 05  2019/03/07 
    The evaluation function for an imperfect information game is always hard to define but has a significant impact on the playing strength of a program. Deep learning has made great achievements in several recent years, and already exceeded the level of top human players in perfect information games such as AlphaGo. Predicting opponents moves and hidden states is important in imperfect information games. This paper describes a model on building a Mahjong artificial intelligence with deep learning method and supervised learning theory. Four deep neural network for discarding and predicting opponents' waiting, waiting tiles and point changes are combined into one model and performs good during games. With improved feature engineering, our accuracies on validation data of these networks reach higher than Dr. Mizukami and Professor Tsuruoka's network.
  • Determining the Number of Tourist Arrivals from Travel Reviews: A Bivariate Correlation Analysis
    Shuang Song, Tomohisha Yamashita, Hidenori Kawamura, Junichi Uchida, Hajime Saito
    Proceedings of the 20th Asia Pacific Industrial Engineering and Management System Conference 244 - 248 2019 [Refereed]
  • Tomohisha Yamashita, Ichitaro Ogawa, Soichiro Yokoyama, Hidenori Kawamura, Akira Sakatoku, Tadashi Yanagihara, Tomohiko Ogishi, Hideaki Tanaka
    Intelligent Transport Systems for Everyone’s Mobility 357 - 375 2019 [Refereed]
  • Mizuki Kambe, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura
    Proceedings of the 23rd Asia Pacific Symposium on Intelligent and Evolutionary Systems(IES) 67 - 78 2019 [Refereed]
  • Song Shuang, Kawamura Hidenori, Uchida Junichi, Saito Hajime
    Information Technology & Tourism 21 (3) 337 - 36 1098-3058 2019 [Refereed]
  • 吉田拓海, 横山想一郎, 山下倫央, 川村秀憲
    情報処理学会論文誌ジャーナル(Web) 60 (10) 1882-7764 2019 [Refereed]
  • 幡本昂平, 横山想一郎, 山下倫央, 川村秀憲
    情報処理学会論文誌ジャーナル(Web) 60 (10) 1882-7764 2019 [Refereed]
  • Hiroya Nagata, Stefan Walke, Soichiro Yokoyama, Tomohisa Yamashita, Hiroyuki Iizuka, Masahito Yamamoto, Keiji Suzuki, Hidenori Kawamura
    Artificial Life and Robotics 23 (2) 192 - 199 1433-5298 2018/06/01 [Refereed][Not invited]
     
    This project revolves around the combination of different state-of-the-art concepts to create balloon robots which can be used for entertainment purposes. The goal is having multiple robots perform a choreographed flight on preset paths to make use of the “dead space” over the crowd of an event, either as part of the show or displaying information and advertisements. As the balloon is flying on a defined trajectory, a tracking system for its position is needed. For this purpose, several infrared cameras monitor the position of a marker attached to the balloon. The main challenge is overcoming the instabilities of the system to ensure a smooth and precise flight, resulting from the balloons structure: the balloon is filled with helium to counteract the forces of gravity and, therefore, minimize the work needed to keep its momentum. Finding a way to achieve this optimization and the precision mentioned beforehand is the task that we will present and solve in this paper.
  • YONEDA Koki, YOKOYAMA Soichiro, YAMASHITA Tomohisa, KAWAMURA Hidenori
    JSAI Technical Report, Type 2 SIG 一般社団法人 人工知能学会 2018 (SAI-031) 03  2018/03/01 
    近年, 深層学習を使用した芸術の作成に注目が集まっている. また, 日本で古くから親しまれている芸術として俳句がある. そこで, 俳句を作成する方法として一般的な「モチーフから俳句を作る」ということを深層学習を使用して行うことで, 芸術作成としての深層学習の有用性を示す.そのための方法として, 小林一茶をはじめとする俳人たちの俳句を大量に用意してLSTMに入力して学習し, 文字列を生成する. その後, 得られた文字列から俳句としての条件を満たすものをとりだし, モチーフ画像に適合するかどうかの評価値を算出する. 評価が高ければそのモチーフ画像にあった俳句として生成できたものとしている. その過程で,LSTMが俳句としてのルールを学習できているかを確認するための実験を行った.
  • HIRAMA Yudai, YOKOYAMA Soichiro, YAMASHITA Tomohisa, KAWAMURA Hidenori, SUZUKI Keiji, WADA Masaaki
    JSAI Technical Report, Type 2 SIG 一般社団法人 人工知能学会 2018 (SAI-031) 04  2018/03/01 
    近年、漁業の乱獲などによって水産資源の枯渇が問題となっており、魚種ごとの資源管理が課題とされている。しかし、受動的漁法である定置網漁法において、漁獲量を調整することが難しい。そこで、本研究は定置網漁場に設置された魚群探知機によって得られる音響画像を用いて、Deep Learningによる定置網内の魚種・漁獲量推定のアプローチを行い、推定モデルの有効性を検証する。
  • YOSHIDA Takumi, YOKOYAMA Soichiro, YAMASHITA Tomohisa, KAWAMURA Hidenori
    JSAI Technical Report, Type 2 SIG 一般社団法人 人工知能学会 2018 (SAI-031) 02  2018/03/01 
    競輪の1日当たりのレース数を考えると予想記事の作成にかかるコストは大きい．よって本研究では，競輪の予想記事を自動生成することを目的とする．また，新規ユーザーの獲得という競輪業界の課題や既存記事が新規ユーザーには理解が困難であることを踏まえ，本研究では，新規ユーザー向けの予想記事の自動生成を行う．本研究では，機械学習による着順予測の生成と，生成された着順予測を解説する予想記事の生成を行った．着順予測については，予測のための入出力設定の比較，機械学習手法の比較，入力特徴量の比較を実施し，本研究での最良の着順予測を生成した．記事生成については，既存記事を参考に，生成する記事の満たすべき条件を設定し，その条件を満たす記事生成手法としてテンプレートによる記事生成を提案した．
  • SONG Shuang, KAWAMURA Hidenori, UCHIDA Junichi, SAITO Hajime
    Proceedings of the Annual Conference of JSAI 一般社団法人 人工知能学会 JSAI2018 1B1OS11a03 - 1B1OS11a03 2018 
    Many travel surveys have been carried out in many tourist destinations to investigate tourist's needs. However, traditional survey methods can be time and money consuming. Meanwhile, the analysis of the massive and up-to-date travel reviews may be able to provide a low-cost and real-time substitute. There are many tasks before we can develop a method to perform the investigation automatically. This paper will explain the progresses we have made through manual analysis and show the remaining tasks for developing an automated method.
  • Towards a New Investigation Method for Tourists’ Needs: from Travel Survey to the Analysis of Travel Reviews
    Shuang Song, Hidenori Kawamura, Junichi Uchida, Hajime Saito
    Proceedings of The First International Conference on Digital Practice for Science 11 - 16 2018 [Refereed]
  • Identification of Fish Species in a Set-Net with Convolutional Neural Network
    Yudai Hirama, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Keiji Suzuki, Masaaki Wada
    The 1st International Conference on Digital Practice for Science, Technology, Education, and Management 84 - 87 2018 [Refereed]
  • A PID Controlled Balloon Robot with Multiple Camera Positioning
    Hiroya Nagata, Soichiro Yokoyama, Tomohisa Yamashita, Hiroyuki Iizuka, Masahito Yamamoto, Keiji Suzuki, Hidenori Kawamura
    The 1st International Conference on Digital Practice for Science, Technology, Education, and Management 78 - 83 2018 [Refereed]
  • Implementation of Mutual Concessions of Autonomous Cars Using Deep Q-Network
    Ichitaro Ogawa, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Akira Sakatoku, Tadashi Yanagihara, Tomohiko Ogishi, Hideaki Tanaka
    2018 [Refereed]
  • The Substitute Worker Selection Method Using Agent-based Simulation
    Kohei Hatamoto, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura
    The 22nd Asia Pacific Symposium on Intelligent and Evolutionary Systems 134 - 141 2018 [Refereed]
  • Prediction of Race Results and Generation of Predicted Articles in Keirin
    Takumi Yoshida, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura
    The 22nd Asia Pacific Symposium on Intelligent and Evolutionary Systems 99 - 105 2018 [Refereed]
  • Shuang Song 0004, Hajime Saito, Hidenori Kawamura
    Information and Communication Technologies in Tourism 2018(ENTER) 93 - 105 2018 [Refereed]
  • Hiroya Nagata, Soichiro Yokoyama, Tomohisa Yamashita, Hiroyuki Iizuka, Masahito Yamamoto, Keiji Suzuki, Hidenori Kawamura
    J. Robotics Mechatronics 30 (3) 390 - 396 2018 [Refereed]
  • Yudai Hirama, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Keiji Suzuki, Masaaki Wada
    Proceedings - 2017 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems, IES 2017 2017-January 112 - 115 2017/12/21 [Refereed]
     
    Currently, the prediction of fish species and catches is based on the experience of fishermen. Echo sounders can support fisheries; however, they cannot identify fish species. A system for the identification of fish species with machines has not been established. The purpose of this research is to propose a new method for the identification of fish species using echo sounders attached to a set-net. From the results of an experiment, five fish species (yellowtail, salmon, sardine, squid, and juvenile tuna) were identified with an accuracy of 95%.
  • Nozomi Koyama, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Kiyotaka Takeda, Makoto Yokogawa
    Proceedings - 2017 21st Asia Pacific Symposium on Intelligent and Evolutionary Systems, IES 2017 2017-January 122 - 126 2017/12/21 [Refereed]
     
    The conventional control method for road-heating systems, which is controlled mainly by snowfall, is the feedforward control. Therefore, the road-heating systems often operate in spite of no snow on the parking lots. In this paper, we introduce the method of feedback control for road-heating systems that detects snow condition on the parking lots, and turns road-heating systems on and off properly. To recognize the snow condition, we adopt images for recognition using convolutional neural networks.
  • Development of Real Time 3D Positioning System for Indoor Entertainment Balloon Robots
    Hiroya Nagata, Soichiro Yokoyama, Tomohisa Yamashita, Hiroyuki Iizuka, Masahito Yamamoto, Keiji Suzuki, Hidenori Kawamura
    Eighth International Conference on Indoor Positioning and Indoor Navigation 2017 [Refereed]
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    INTELLIGENT AUTONOMOUS SYSTEMS 13 302 1213 - 1225 2194-5357 2016 [Refereed][Not invited]
     
    The main feature that keeps states and structures stable can be seen in living organisms. This adjusting and adaptive features are called homeostasis. This integrated adaptive feature is achieved by the cooperation of organs in living organisms. Living organisms in nature act dynamically due to this feature. Highly adaptive behavior caused by this feature is also observed in simple living organisms that have no neural circuits such as amoebas. Based on these facts, a method of control to generate homeostasis in robotic systems is proposed by assuming a robot system is an aggregation of oscillators and each parameter in a robot system is allocated to an oscillator. Especially, interaction between two independent robots as oscillator aggregation is focused in this paper.
  • 川村 秀憲, 山本, 雅人, 鈴木, 恵二, 松原 仁
    サービソロジー 1 (4) 36 - 41 2188-5362 2015/10 [Refereed][Not invited]
  • 山下 晃弘, 上村 卓史, 川村 秀憲, 鈴木 恵二
    デジタルプラクティス 6 (2) 150 - 158 2188-4390 2015/04/15 [Not refereed][Not invited]
     
    特集「プライバシーフレンドリーシステム」投稿論文（Vol.6 No.2掲載分）家族や友人のみならず，就職活動やビジネスにおいてもSNSの利用が一般化している．一方で，炎上やネットストーカーに代表されるプライバシーリスクも顕在化してきた．スマホのアプリやサービスの選択肢が増える一方で，それらの情報源から第三者が個人情報を容易に推測可能な環境が整いつつある．特定のSNS上では安全でも，それらが結びつくことで生じるリスクは目視や手作業での把握や管理が難しい．筆者らは，多様化するSNSにおいて，利用者がプライバシーリスクを正確に把握し，適切な管理下で安全に利用可能な環境作りについて検討してきた．また独自にソーシャルモニタリングツールを開発して運用し，SNSに内在するさまざまなリスクについて知見を得てきた．本稿ではその取り組みを紹介し，今後さらに多様化が予想されるSNS利用形態とプライバシーリスク管理の課題について検討する．
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    ELECTRONICS AND COMMUNICATIONS IN JAPAN 98 (4) 44 - 51 1942-9533 2015/04 [Refereed][Not invited]
     
    Flocking algorithms for a multiagent system are distributed algorithms that only have simple rules for each agent but generate complex formational movement. These algorithms are known as swarm intelligence and are robust and disaster tolerant for most cases. We consider that flocking algorithms that have these characteristics are the way to generate homeostasis in a system. We expect that by making use of this algorithm the system can tune its self-parameters and thus maintain a high performance. First, to apply a flocking algorithm to a system, we extended the flocking algorithm to form an arbitrary lattice for further flexibility. We then applied the extended flocking algorithm to position tracking camera system as an example. (C) 2015 Wiley Periodicals, Inc.
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    Transactions of the Japanese Society for Artificial Intelligence 30 (1) 1 - 11 1346-8030 2015/01/06 [Refereed][Not invited]
     
    The main feature that keeps states and structures stable can be seen in living organisms. This adjusting and adaptive feature is called homeostasis. This integrated adaptive feature is achieved by the cooperation of organs in living organisms. Living organisms in nature act dynamically due to this feature. Highly adaptive behavior caused by this feature is also observed in simple living organisms that have no neural circuits such as amoebas. In amoeba case, each cell acts as an oscillator and such behavior is explicable as synchronization phenomena of oscillators. Based on these facts, a method of control to generate homeostasis in robotic systems is proposed by assuming a robot system is an aggregation of oscillators in this paper. When a robot system is assumed as an aggregation of oscillators, a robot system tries to keep the value of the specific function that indicate its uncomfortable level small the whole time. To keep such function value small, a robot system stabilize the relationship between oscillators when its value is small and reconstruct the relationship between oscillators when its value is large. This behavior is also explicable as synchronization phenomena of oscillators. A redundant robot arm is made to confirm the effect of this control method to generate homeostatic behaviors in robotic systems.
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    2015 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) 1438 - 1443 2015 [Refereed][Not invited]
     
    The main feature that keeps states and structures stable can be seen in living organisms. This adjusting and adaptive feature is called homeostasis. This integrated adaptive feature is achieved by the cooperation of organs in living organisms. Living organisms in nature act dynamically due to this feature. Highly adaptive behavior caused by this feature is also observed in simple living organisms that have no neural circuits such as amoebas. In amoeba case, each cell acts as an oscillator and such behavior is explicable as synchronization phenomena of oscillators. Based on these facts, a method of control to generate homeostasis in robotic systems is proposed by assuming a robot system is an aggregation of oscillators in this paper. When a robot system is assumed as an aggregation of oscillators, a robot system tries to keep the value of the specific function that indicate its uncomfortable level small the whole time. To keep such function value small, a robot system stabilize the relationship between oscillators when its value is small and reconstruct the relationship between oscillators when its value is large. This behavior is also explicable as synchronization phenomena of oscillators. Wheeled robot with camera is applied this control method in this paper to confirm the effect of the method. Adaptive behavior is observed in the robot through the task to find the better position between the object.
  • 小野 良太, 山下 晃弘, 川村 秀憲, 鈴木 恵二
    観光と情報 : 観光情報学会誌 観光情報学会 11 (1) 23 - 34 1349-919X 2015 [Not refereed][Not invited]
  • 伊藤千輝, 篠田孝祐, 諏訪博彦, 小野良太, 平田圭, 川村秀憲, 栗原聡
    社会情報システム学シンポジウム学術講演論文集 21 21st 55 - 58 1882-9473 2015/01 [Not refereed][Not invited]
  • Shinsaku Segawa, Shofuku Kin, Hidenori Kawamura, Keiji Suzuki
    WMSCI 2014 - 18th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings 1 262 - 266 2014 [Refereed]
     
    Agent Based Model (ABM) is efficient for analysis of various social mechanisms. Recently, there are many studies on massive agent model to explain more complex social phenomena. Then, we aim for implementation of large scale simulation model using Repast HPC toolkit, a platform for massive agent model. In this article, we build "Schelling Segregation Model" for spatial model using geospatial data provided OpenStreetMap, an open source project creating a free editable map. In this model, agents are located continuous space, not grid in original. When an agent is "unhappy" and migrates to new location, it costs agents some simulation time depending on distance between old location and new one. This article reports simulation results using Japanese cities and verification result about execution time.
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    Advances in Intelligent Systems and Computing 274 59 - 69 2194-5357 2014 [Refereed][Not invited]
     
    The main feature that keeps states and structures stable can be seen in living organisms. This adjusting and adaptive feature is called homeostasis. This integrated adaptive feature is achieved by the cooperation of organs in living organisms. Living organisms in nature act dynamically due to this feature. Highly adaptive behavior caused by this feature is also observed in simple living organisms that have no neural circuits such as amoebas. Based on these facts, a method of control to generate homeostasis in robotic systems is proposed by assuming a robot system is an aggregation of oscillators in this paper and each parameter in a robot system is allocated to an oscillator. Such oscillators interact so that the whole system can adapt to the environment. Also, a redundant robot arm is made to confirm the effect of this control method to generate homeostatic behaviors in robotic systems.
  • Hidenori Kawamura, Ryota Ono, Keiji Suzuki
    Journal of Information Processing 22 (2) 270 - 278 1882-6652 2014 [Refereed][Not invited]
     
    In this paper, we focus on allocating of social service facilities which are operated under the first-comefirst- serve rule. In such facilities, users cannot make a reservation in advance. To reduce congestion, it is desirable to adjust a schedule by communication devices. We propose the user-in-the-loop forecasting with the statement-based cost estimate, and apply to two types of facility allocation models, i.e., the theme park scenario and the highway scenario. The computer experiments show that the proposed estimate caused better results in both scenarios to reduce congestion. In particular, the users in the highway scenario could achieve a near user equilibrium situation without any advance experience of the system. © 2014 Information Processing Society of Japan.
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    DISTRIBUTED AUTONOMOUS ROBOTIC SYSTEMS 104 247 - 258 1610-7438 2014 [Refereed][Not invited]
     
    Flocking algorithms for a multi-agent system are distributed algorithms that only have simple rules for each agent but generate complex formational movement. These algorithms are known as swarm intelligence and are robust and disaster tolerant for most cases. We consider that flocking algorithms that have these characteristics are the way to generate homeostasis in a system. We expect that by making use of this algorithm the system can tune its self parameters and thus maintain a high performance. First, to apply a flocking algorithm to a system, we extended the flocking algorithm to form an arbitrary lattice for further flexibility. We then applied the extended flocking algorithm to a position tracking camera system as an example.
  • MATSUBARA Hitoshi, YAMAMOTO Masahito, KAWAMURA Hidenori, SUZUKI Keiji
    Systems, control and information システム制御情報学会 57 (8) 316 - 322 0916-1600 2013/08/15 [Not refereed][Not invited]
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    Journal of Advanced Computational Intelligence and Intelligent Informatics 17 (5) 715 - 720 1883-8014 2013 [Refereed][Not invited]
     
    Flocking algorithms for multi-agent systems are distributed algorithms that generate complex formational movement despite having simple rules for each agent. These algorithms, known as swarmintelligence, are flexible and robust. However, to exploit these features to generate flexible behavior in an autonomous system, greater flexibility is needed. To achieve this, these algorithms are extended to enable arbitrary lattice formation. In addition, extended flocking algorithms can be assumed to be the aggregation of oscillators and observed the behavior of synchronization. It is difficult to explain the behavior of extended flocking algorithms as a consensus problem but, by assuming the flock as the set of oscillators, it can be explained as a synchronization phenomenon.
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    IEEJ Transactions on Electronics, Information and Systems 133 (6) 1195 - 1201 1348-8155 2013 [Refereed][Not invited]
     
    Flocking algorithms for a multi-agent system are distributed algorithms that only have simple rules for each agent but generate complex formational movement. These algorithms are known as swarm intelligence and are robust and disaster tolerant for most cases. We consider that flocking algorithms that have these characteristics are the way to generate homeostasis in a system. We expect that by making use of this algorithm the system can tune its self parameters and thus maintain a high performance. First, to apply a flocking algorithm to a system, we extended the flocking algorithm to form an arbitrary lattice for further flexibility. We then applied extended flocking algorithm to position tracking camera system as an example. © 2013 The Institute of Electrical Engineers of Japan.
  • Seishi Yamagata, Hidenori Kawamura, Keiji Suzuki
    Proceedings of the 2013 IEEE/SICE International Symposium on System Integration(SII) 370 - 375 2013
  • Ayumi Kanehira, Hidenori Kawamura, Keiji Suzuki
    2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics(AIM) 212 - 216 2013
  • Takeshi Ikeda, Mitsuru Kawamoto, Akio Sashima, Junpei Tsuji, Hidenori Kawamura, Keiji Suzuki, Koichi Kurumatani
    Serviceology for Services(ICServ) 191 - 201 2013
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    Advances in Intelligent Systems and Computing 194 (2) 835 - 842 2194-5357 2013 [Refereed][Not invited]
     
    Flocking algorithm of multi agent system is robust and disaster tolerant even though agents face obstacles or destructed. In this paper, we focus on applying these mechanism to single humanoid robot by assuming that the robot is the set of agents. We extend flocking algorithm to be capable of using in single robot and apply it to humanoid robot to maintain standing posture. © 2013 Springer-Verlag.
  • Shogo Sugawara, Hidenori Kawamura, Keiji Suzuki
    2013 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM): MECHATRONICS FOR HUMAN WELLBEING 1591 - 1596 2159-6255 2013 [Refereed][Not invited]
     
    Not only skill but also determination of strategy (choosing a club and a target) is important to improve golf scores. This study aims to optimize a strategy to help golfer's improve their scores. To optimize a strategy, first, we develop a simulation model that determines the drop position of a golf ball probabilistically. The size of a gap between a target and a position at which the ball actually falls changes depending on the skill parameters. Next, expected values of the score are calculated at every spot among the golf course by the Q-learning [9] using the simulation model. Finally, we check the capability to acquire a strategy through simulation that directs action to a golfer agent using optimized Q-tables. Results of the optimization show that when the shot distance of each club is the same but the shot accuracy is not, a club that has a shorter shot distance is more suitable for a golfer with low shot accuracy than a golfer with high shot accuracy. The strategy is optimized in consideration of course layout and golfer's skills.
  • Kayoko H. Murakami, Hidenori Kawamura, Keiji Suzuki
    International Journal of Advancements in Computing Technology 4 (22) 239 - 247 2005-8039 2012/12 [Refereed][Not invited]
     
    An intensive earthquake off the Pacific coast of Tohoku struck the greater east Japan area on March 11, 2011. The earthquake and resulting tsunami directly affected the international inbound tourism, and the number of foreign visitors to Japan suffered a great decline compared to the previous year. One important method by which we can explore how the crisis affected the international inbound tourism is the analysis of word-of-mouth information by foreign visitors. This paper examined text data collected from a major travel blog website from April 2010 to February 2012 and investigated if there were any tendencies that could be found in the tourists' activities before and after the March 11 earthquake. It found that the number of appearances of the term "earthquake" in the blogs was related to the seismic intensity of each earthquake and aftershock. Also, there were differences in the content of nouns in the blogs posted right after the March 11 earthquake. Earthquake-related words appeared with a high TF-IDF value. However, in the blogs of the following months, Japan travel related terms appeared as topic terms in the same manner as in the blogs before the earthquake. This paper suggests that effective and prompt actions need to be taken immediately following a disaster for the reconstruction of the tourism industry.
  • Hidenori KAWAMURA, Keiji SUZUKI
    IPSJ Magazine 一般社団法人情報処理学会 53 (11) 1146 - 1152 0447-8053 2012/10/15 [Not refereed][Not invited]
     
    観光情報学の実践フィールドとして,北海道大学周辺の約120の飲食店を舞台に二次元バーコードによる電子スタンプラリー「北大グルメエキスポ」を開催し,ログデータの解析を行った.本稿では,なぜイベント開催をフィールドとして研究を展開することに至ったのか,そしてイベント開催と観光情報学の研究を通して何を目指すのかについて述べる.
  • 川村秀憲
    情報処理学会デジタルプラクティス 一般社団法人情報処理学会 3 (4) 272 - 280 1884-5541 2012/10/15 [Not refereed][Not invited]
     
    北海道の基幹産業の一つは観光である.観光分野は独立した大小様々な事業者の集合体として観光客にサービスを提供しているため,個々の事業の範囲でマーケティング等はなされているものの,北海道全体としてITを利用した戦略的な観光情報の収集と発信はこれまでとられてこなかった.そこで,(社)北海道観光振興機構内に設置された情報システムWGでは,SNS上で北海道観光に関する標準タグを利用することを提案し,そのタグを利用した観光情報アグリゲーションの仕組みと情報提供のためのサイト「キュンちゃんねる」を開設することでインターネット上の北海道観光情報を組織化する取り組みを行っている.本論文では,この取り組みを通して得た情報流通の活性化に向けた知見や課題について述べる.
  • K. H. Murakami, H. Kawamura, K. Suzuki
    WIT Transactions on Ecology and the Environment 161 43 - 53 1743-3541 2012 [Refereed][Not invited]
     
    Since the 2011 off the Pacific coast of Tohoku Earthquake damaged the major area of eastern Japan on March 11, 2011, the number of foreign visitors has drastically decreased. Japanese government tried to take urgent countermeasures against the loss. They spread the true information that Japan is safe by using media and Word-of-Mouth (WOM) such as influential bloggers. In this study, we investigate what WOM can be found regarding the earthquake through the blogs posted after the disaster. The blogs including earthquake-related words were collected and analyzed. Extracting the target data from the large number of data allows us to qualitatively examine the data. The text mining approach we used in this study includes morphological analysis and topic words analysis with term frequency-inverse document frequency weight. After that, the topic words and the words with high document frequency were used to find collocation of those topic words. As a result, the topic words "safe" and "normal" were found in the March 2011 blogs while they contained many other topic words about earthquake, tsunami, and nuclear crises. Moreover, gradually the number of earthquake-related words disappeared in the blogs and travel-related words appeared as time went by. In addition, we used concordance software to see the context where the topic words are used and found that the blogs written by the foreign visitors could convey true information about the disaster. © 2012 WIT Press.
  • Yusuke Kobayashi, Hidenori Kawamura, Keiji Suzuki
    6TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND INTELLIGENT SYSTEMS, AND THE 13TH INTERNATIONAL SYMPOSIUM ON ADVANCED INTELLIGENT SYSTEMS 1821 - 1826 2012 [Refereed][Not invited]
     
    Multi-agent systems have attracted a lot of attention recently. RoboCup Soccer Simulation is treated here as a testbed of such systems. This study aims to facilitate the analysis of team behavior and to clarify the role of different types of team possession in the game results of RoboCup Soccer Simulation. We construct a method of detecting counter attacks, which are one type of team possession, by analyzing the log files of games. To detecting the counter attacks, anisotropy feature and others are introduced. Based on these features, a support vector machine (SVM) based detector was able to achieve a 77% detection rate. The detecting method will be expected to reduce the burden of visually checking log data.
  • Sho Yamauchi, Hidenori Kawamura, Keiji Suzuki
    2012 IEEE/SICE INTERNATIONAL SYMPOSIUM ON SYSTEM INTEGRATION (SII) 452 - 457 2012 [Refereed][Not invited]
     
    Flocking algorithms for a multi-agent system are distributed algorithms that only have simple rules for each agent but generate complex formational movement. These algorithms are known as swarm intelligence and are robust and disaster tolerant for most cases. On the other hand, most of organizations are constructed from smaller groups, we call it subgroup here. It means activities of organization should be determined by its subgroups but flocking algorithm itself does not have such feature. To express this feature, we extend flocking algorithm to be able to contain subgroups of agents. Also we add flocking algorithm the term that indicates the relationship with other subgroups. By this extension, flocking algorithm is be able to form specific shape more flexibly.
  • 村上嘉代子, 川村秀憲
    人工知能学会誌 人工知能学会 26 (3) 286 - 293 0912-8085 2011/05/01 [Not refereed][Not invited]
  • Akihiro Yamashita, Hidenori Kawamura, Keiji Suzuki
    ADVANCES IN COMPLEX SYSTEMS 14 (2) 133 - 149 0219-5259 2011/04 [Refereed][Not invited]
     
    In many e-commerce sites, recommender systems, which provide personalized recommendations from among a large number of items, have recently been introduced. Collaborative filtering is one of the most successful algorithms which provide recommendations using ratings of users on items. There are two approaches: user-based and item-based collaborative filtering. Additionally a unifying method for user-based and item-based collaborative filtering was proposed to improve the recommendation accuracy. The unifying approach uses a constant value as a weight parameter to unify both algorithms. However, because the optimal weight for unifying is actually different depending on the situation, the algorithm should estimate an appropriate weight dynamically, and should use it. In this research, we first investigate the relationship between recommendation accuracy and the weight parameter. The results show that the optimal weight is different depending on the situation. Second, we propose an approach for estimation of the appropriate weight value based on collected ratings. Then, we discuss the effectiveness of the proposed approach based on both multi-agent simulation and the MovieLens dataset. The results show that the proposed approach can estimate the weight value within an error rate of 0.5% for the optimal weight.
  • KAWAMURA Hidenori, SUZUKI Keiji, YAMAMOTO Masahito, MATSUBARA Hitoshi
    IPSJ Magazine 一般社団法人情報処理学会 51 (6) 642 - 648 0447-8053 2010/06/15 [Not refereed][Not invited]
  • An IndoorPositioning System Based on Probabilistic Model with ZigBee Sensor Networks
    Junpei Tsuji, Hidenori Kawamura, Keiji Suzuki, Takeshi Ikeda, Akio Sashima, Koichi Kurumatani
    Journal of Advanced Computational Intelligence and Inteligent Informatics 14 (6) 669 - 676 2010 [Refereed][Not invited]
  • Similarity Computation Method for Collaborative Filtering Based on Optimization
    Akihiro Yamashita, Hidenori Kawamura, Keiji Suzuki
    Journal of Advanced Computational Intelligence and Inteligent Informatics 14 (6) 654 - 660 2010 [Refereed][Not invited]
  • Comparison Support Method for Analytic Hierarchy Process
    Tadano Yumi, Kawamura Hidenori, Suzuki Keiji, Ohuchi Azuma
    ASOR Bulletin 29 (4) 48 - 59 2010 [Refereed][Not invited]
  • Hidenori Kawamura, Keiji Suzuki
    Multi-Agent Applications with Evolutionary Computation and Biologically Inspired Technologies: Intelligent Techniques for Ubiquity and Optimization 294 - 307 2010 [Refereed][Not invited]
     
    Pheromones are the important chemical substances for social insects to realize cooperative collective behavior. The most famous example of pheromone-based behavior is foraging. Real ants use pheromone trail to inform each other where food source exists and they effectively reach and forage the food. This sophisticated but simple communication method is useful to design artificial multiagent systems. In this chapter, the evolutionary pheromone communication is proposed on a competitive ant environment model, and we show two patterns of pheromone communication emerged through co-evolutionary process by genetic algorithm. In addition, such communication patterns are investigated with Shannon's entropy. © 2011, IGI Global.
  • YAMASHITA Akihiro, KAWAMURA Hidenori, SUZUKI Keiji, OHUCHI Azuma
    The IEICE transactions on information and systems 電子情報通信学会 92 (11) 1902 - 1910 1880-4535 2009/11/01 [Refereed][Not invited]
     
    ショッピングサイトなどでは,個人の興味や嗜好に適応して積極的にアイテムを提示する推薦システムが実用化されている.協調フィルタリングは,近年最もよく用いられている推薦手法の一つで,アイテムに対する格付けをユーザ全体から収集し,それをもとに個人の興味や嗜好に適合したアイテムを推走して推薦を行う.一般的に,多くの格付けを収集すれば適合アイテムの推定精度が向上し,システム全体の有効性が向上する.そこで実運用においては,メールなどで格付けを促すほか,特典やポイントなどのコストをかけて格付け行為にインセンティブをもたせる試みがなされている.しかし,収集したすべての格付けが均一に推定に寄与するとは限らず,また同じ格付けを収集する場合を考えても,推定精度の向上に必要な格付けをより早い段階で重点的に収集した方が効率的である.本研究では,各々の格付けが推定に寄与する度合(格付け寄与度)を定義し,それを利用した効率的な推定精度の向上方法についてシミュレーションや実データに基づいて議論した.その結果,格付け寄与度が高い格付けを重点的に収集することで,より効率的に推定精度が向上することを示した.
  • Akihiro Yamashita, Hidenori Kawamura, Hiroyuki Iizuka, Azuma Ohuchi
    情報処理学会論文誌. 数理モデル化と応用 一般社団法人情報処理学会 2 (2) 47 - 57 0387-5806 2009/03/27 [Refereed][Not invited]
     
    The problem of information overload spreading across the Internet has been causing serious inefficiency in browsing and searching for information. As a way to overcome the problem, the recommender systems are recently used in many E-commerce sites. Many algorithms have been proposed to improve the accuracy of recommendation based on user ratings. The relation between recommender systems and users is rather interactive in the sense that recommendations decides which items are recommended to users and the results of ratings by users will affect the next recommendations. However, conventional ...
  • Hidenori Kawamura, Hiroyuki Iizuka, Toshihiko Takaya, Azuma Ohuchi
    Artificial Life and Robotics 13 (2) 504 - 507 1433-5298 2009 [Not refereed][Not invited]
     
    We report on the cooperative control of multiple neural networks for an indoor blimp robot. In our research group, the indoor blimp robot has been studied to achieve various flying robot applications. The objective of this article is to propose a robust controller that can adapt to mechanical accidents such as the breakdown of propellers. In our proposed method, each propeller thrust is independently calculated by a small neural network. We confirm the advantage of the proposed method against the control by a single large neural network. © International Symposium on Artificial Life and Robotics (ISAROB). 2009.
  • Toshihiko Takaya, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    IEEJ Transactions on Electronics, Information and Systems 電気学会 129 (1) 24 - 188 1348-8155 2009 [Refereed][Not invited]
     
    We report on cooperative control of multiple neural networks for indoor balloon robot. In our laboratory, the indoor balloon has been studied to achieve various applications. Our objective of this paper is to propose a robust controller that can adapt to mechanical accidents such as breakdown of propellers. In our proposal method, each propeller thrust is independently calculated by each small network. We confirm effectiveness of the proposed method compared to the method of calculating thrusts by a single neural network on the simulator. © 2009 The Institute of Electrical Engineers of Japan.
  • Toshihiko Takaya, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    ELECTRONICS AND COMMUNICATIONS IN JAPAN 91 (2) 1 - 13 1942-9533 2008/02 [Refereed][Not invited]
     
    Blimp robots are an attractive form of small flight robot. because they are maintained aloft by buoyancy, are safe, require little energy and have relatively long flight times. The development of a general-purpose blimp robot research platform allowing modular installation of a variety of hardware and software components will lower the barrier to the creation of new research projects and increase project efficiency. This paper describes the development of such a general-purpose platform and the testing of its suitability for research use. Experiments performed on the platform included: (I) testing of position maintenance capabilities, and changeover from a PID control software module to a learning control module; (2) testing of the ease and effectiveness of exchanging one hardware module (a microphone) for another (a camera); (3) installation of a new hardware module (a microphone) along with an existing module (a camera); (4) testing of addition of functions and performance of a topologic map generation experiment with addition of an ultrasonic sensor. The effectiveness of information fusion combined with a layered software structure was demonstrated in the experiments, indicating that the newly developed platform will be effective in promoting research on blimp robots. (C) 2008 Wiley Periodicals, Inc. Electron Comm Jpn, 91(2): 1-13 2008; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecj.10025
  • Tourism Information Recommender System Using Multiple Recommendation Algorithms based on Collaborative Filtering
    Akihiro Yamashita, Hidenori Kawamura, Azuma Ohuchi
    Intelligent Engineering Systems through Artificial Neural Networks (18) 719 - 725 2008 [Refereed][Not invited]
  • 利用者主導による主観と客観を考慮した個人向け観光情報推薦システム
    山下 晃弘, 川村 秀憲, 大内 東
    観光情報学会誌「観光と情報」 4 (1) 44 - 56 2008 [Not refereed][Not invited]
  • 丸山 加奈, 川村 秀憲, 大内 東
    観光と情報 観光情報学会 4 (1) 35 - 43 1349-919X 2008 [Not refereed][Not invited]
  • Toshihiko Takaya, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    IEEJ Transactions on Electronics, Information and Systems 電気学会 128 (9) 8 - 1461 1348-8155 2008 [Refereed][Not invited]
     
    Recent studies have been mainly engaged with movements by 2 or more autonomous robots. Especially, the development of autonomous robots utilized by the industrial manufacture has been advancing. However, the extent of these researches was limited to robots moving in 3 dimensional autonomous robots, such as airplanes or helicopters. On the other hand, regarding studies on small size indoor 3 dimensional blimp robots, characteristics of entertainment robots, indoor surveillance robots, object searching robots in disaster building have been subject to investigation. However, previous studies drew the attention to the difficulties arising when the cooperative behavior of 2 or more autonomous blimp robots is strongly presented depending on changes in the experimental environment, denoting the weak points of these systems. In this paper, 2 small size autonomous blimp robots were used, and basic experiments with time constraints of behavior control were conducted, examining possible coordinated movements of 2 small size autonomous blimp robots, for the purpose of high application achievement of utility. © 2008 The Institute of Electrical Engineers of Japan.
  • 川村秀憲, 大内東, 川村秀憲, 大内東
    電子情報通信学会論文誌 D J90-D (9) 2432 - 2443 1880-4535 2007/09/01 [Refereed][Not invited]
  • Toshihiko Takaya, Hidenori Kawamura, Yoshihiro Minagawa, Masahito Yamamoto, Azuma Ohuchi
    Artificial Life and Robotics 11 (2) 227  1433-5298 2007/07 [Refereed][Not invited]
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, OHUCHI AZUMA
    IPSJ Journal 一般社団法人情報処理学会 48 (6) 2097 - 2105 0387-5806 2007/06/15 [Refereed][Not invited]
     
    The high-quality service provided by the large-scale tele-communication network constructed in the Internet such as the Gnutella is thought to be achieved by a certain feature network structure. Moreover, a feature structure is assumed to be generated with a certain simple generation rule in another research. This shows that there is a possibility that an effective design approach of the large scale network can be established if the design of the generation rule that generates the optimal structure becomes possible. Authors tried to archive a structural generation rule to make the communica...
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, OUCHI AZUMA
    コンピュータソフトウェア 24 (1) 40 - 49 0289-6540 2007/01/26 [Not refereed][Not invited]
     
    When composing networks for a particular purpose, we previously designed optimal topology for that purpose. Many researches so far have focused on designing optimal topology under various conditions given statically. However, in more than a few cases, the network is used during its growing process because it is difficult to construct a whole network at a. burst when considering the construction of an actual network. In this paper, we investigate the feasibility of building an optimal network from the aspects of the optimality and growth elements of topologies, We lead the optimal growing rules for some conditions and take up network models mentioned in the research of complex networks. Experimental results verify that optimal growing rules vary depending on the purposes and conditions of the building of networks and show that the selection of the growing rules makes it possible to build networks optimally.
  • 大柳 幸彦, 川村 秀憲, 山本 雅人
    観光と情報 観光情報学会 3 (1) 29 - 35 1349-919X 2007 [Not refereed][Not invited]
  • Toshihiko Takaya, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    IEEJ Transactions on Electronics, Information and Systems 電気学会 127 (9) 18 - 1429 1348-8155 2007 [Refereed][Not invited]
     
    A blimp robot is attractive as an small flight robot and can float in the air by buoyancy and realize safe to the crash small flight with low energy and can movement for a long time compared with other flight robots with low energy and can movement for a long time compared with other flight robots. However, control of an airplane robot is difficult for the nonlinear characteristic exposed to inertia by the air flow in response to influence. Therefore, the applied research which carried out the maximum use of such in recent years a blimp robot's feature is prosperous. In this paper, we realized development of blimp robot for research which can be used general-purpose by carrying out clue division of the blimp robot body at a unit, and constituting and building for research of blimp robot, and application development. On the other hand, by developing a general-purpose blimp robot research platform, improvement in the research efficiency of many researchers can be attained, and further, research start of blimp robot becomes easy and contributes to development of research. We performed the experiments for the above-mentioned proof. 1. Checked basic keeping position performance and that various orbital operation was possible. And the unit exchange ease of software unit was checked by the experiment which exchanges the control layer of software for learning control from PID control, and carries out comparison of operation. 2. In order to check the exchange ease of hardware unit, the sensor was exchanged for the microphon from the camera, and control of operation was checked. 3. For the unit addition ease, the microphon which carries out sound detection with the picture detection with a camera was added, and control of operation was verified. 4. The unit exchange was carried out for the check of a function addition and the topological map generation experiment by addition of an ultrasonic sensor was conducted. Developed blimp robot for research mounted the exchange ease and the additional ease of a unit in hardware using an analog and digital I/F fomenting realized in the combination of the software module of a layered structure in software was performed. Consequently, an addition and exchange of a function were able to become easy and were able to realize the research platform of blimp robot.
  • Optimizing of Growing Queuing Network with Slight Reconstruction
    Yusuke Matsumura, Hidenori Kawamura, Azuma Ohuchi
    International Transactions on Systems Science and Applications 3 (1) 27 - 34 2007 [Refereed]
  • Yusuke Matsumura, Hidenori Kawamura, Koichi Kurumatani, Azuma Ohuchi
    EMERGENT INTELLIGENCE OF NETWORKED AGENTS 56 115 - + 1860-949X 2007 [Refereed][Not invited]
     
    In the network field, various researches have tackled optimizing flow in networks. As shown from previous researches, flow optimality is dependent on the link structure and the routing algorithm that controls the flow. Therefore, a research frame is desirable that optimizes each of them independently but still simultaneously handles both. This study proposes a new scheme called Optimal Flow Network Design Problem (OFNDP) and applies it to a queueing network system; flow optimization is also performed. In the experiment, the number of traffics and each service rate were given to nodes and between each node respectively, and then the flow of each traffic was decided to minimize waiting time by a flow control algorithm based on the dijxtra method. Link structure was also optimized by a genetic algorithm under the constraint of a limited number of links. As a result, sub-optimal flow was obtained with short average waiting time for each traffic.
  • KAWAMURA HIDENORI, ONODERA MASAKI, OHUCHI AZUMA
    IPSJ Journal 一般社団法人情報処理学会 47 (7) 2202 - 2211 0387-5806 2006/07/15 [Not refereed][Not invited]
     
    We focus on a method to calculate the estimated value for a probabilistic model in which each event is defined as a combination of several other independent events. The partially exhaustive investigation Monte Carlo method has been proposed by the authors for such model, and it can show higher performance than simple weighted sampling Monte Carlo method on the condition that the used sample number for estimating is limited. This method divides the event into two parts by a threshold parameter; one is composed by high-probability events, and another is by remaining events. To make this metho...
  • H Kawamura, K Kurumatani, A Ohuchi
    ELECTRICAL ENGINEERING IN JAPAN 156 (2) 61 - 74 0424-7760 2006/07 [Refereed][Not invited]
     
    In this paper, in order to investigate the effect of scenarios in which cogeneration spreads in an electricity market we constructed a multi-agent model of an electricity trading market with power distribution and power generation agents. In this model, we analyzed the effect of reducing power generation surplus facilities on market price formation and stability through computer experiments. As a result of the experimental simulations, the market price was decreased by the increase of sell bids according to the demand reduction by the spread of cogeneration, and by the increase of commercial use of cogeneration facilities, the market price was more economical and stable because such agents supplied more electricity generated by surplus cogeneration. However, if power generation agents reduced the number of power generating facilities when the number of power distribution agents' cogeneration facilities was not significant, the fluctuation of market price grew larger. We confirmed that the spread of cogeneration played an important role in stabilizing market price formation. (C) 2006 Wiley Periodicals, Inc.
  • Cellular Automaton Model of a Tumor Tissue Consisting of Tumor Cells, Cytotoxic T Lymphocytes (CTLs), and Cytokine Produced by CTLs
    Toshiaki Takayanagi, Hidenori Kawamura, Azuma Ohuchi
    IPSJ Transactions on Mathematical Modeling and Its Applications 47 (SIG1) 61 - 67 2006 [Refereed][Not invited]
  • Takayanagi Toshiaki, Kawamura Hidenori, Ohuchi Azuma
    ipsjdc Information Processing Society of Japan 2 138 - 144 1349-7456 2006 
    We propose a cellular automaton model of a tumor tissue consisting of a square lattice, tumor cells, cytotoxic T lymphocytes (CTLs) and cytokine. Considering that CTLs circulate in vivo and migrate into a tumor tissue, the square is open and CTLs move through the square. By calculating the cellular automaton model, we obtained these results: the growth of a mass of tumor cells surrounded by CTLs; the rejection of tumor cells by CTLs; and an approximate equilibrium between tumor cells and CTLs. Analysis of the results indicates that the attachment between tumor cells and CTLs is important for the rejection of tumor cells by CTLs.
  • Takayanagi Toshiaki, Kawamura Hidenori, Ohuchi Azuma
    IMT Information and Media Technologies Editorial Board 1 (2) 780 - 786 1881-0896 2006 
    We propose a cellular automaton model of a tumor tissue consisting of a square lattice, tumor cells, cytotoxic T lymphocytes (CTLs) and cytokine. Considering that CTLs circulate in vivo and migrate into a tumor tissue, the square is open and CTLs move through the square. By calculating the cellular automaton model, we obtained these results: the growth of a mass of tumor cells surrounded by CTLs; the rejection of tumor cells by CTLs; and an approximate equilibrium between tumor cells and CTLs. Analysis of the results indicates that the attachment between tumor cells and CTLs is important for the rejection of tumor cells by CTLs.
  • Mitsuyoshi Nagao, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    Information and Communication Technologies in Tourism, ENTER 2006, Proceedings of the International Conference in Lausanne, Switzerland, 2006 Springer 87 - 98 2006 [Refereed][Not invited]
  • KAWAMURA HIDENORI, ONODERA MASAKI, OUCHI AZUMA
    情報処理学会論文誌 46 (12) 3218 - 3227 0387-5806 2005/12/15 [Not refereed][Not invited]
  • Kawamura Hidenori, Ohuchi Azuma
    Transactions of the Operations Research Society of Japan 社団法人日本オペレーションズ・リサーチ学会 48 (0) 48 - 65 0453-4514 2005/12 [Refereed][Not invited]
     
    In this paper, we design a multiagent product market model with network externality, and evaluate the effectiveness of present strategy, which is one of sales promotion like that a sales corporation chooses customers in a market and gives him/her a product without compensation. The proposed multiagent model can explicitly involve customers' interaction network, and we can clarify the relationship between the effectiveness of network externality and the structure of customers interaction network. The customers interaction networks we prepared contain 4 types; random, regular, small world, an...
  • KAWAMURA Hidenori, KADOTA Hisao, YAMAMOTO Masahito, TAKAYA Toshihiko, OHUCHI Azuma
    Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 日本知能情報ファジィ学会 17 (2) 203 - 211 1347-7986 2005/04/15 [Refereed][Not invited]
     
    In this paper, we report the development of the entertainment blimp robot which can make several reactive behaviors for user's appeal. The blimp robot has a wireless CCD camera and wireless microphone at the bottom of body, and rotates or goes upward/downward by trigger of user's handclap. To make variety reactions of the blimp robot, a sequence of robot behavior is generated based on the nondeterministic finite state machine. In addition, the stable flying behavior is achieved by the proposed hovering control based on grounded red circle landmarks. Throughout an experiment, we confirm that...
  • K Kurumatani, H Kawamura, A Ohuchi
    INFORMATION SCIENCES 170 (1) 65 - 74 0020-0255 2005/02 [Refereed][Not invited]
     
    We are developing an agent and server library referred to as X-Economy, by which we can execute multiagent simulations and network games for financial and economic systems. To this end, we analyzed the characteristics of network games in a financial context and compared them with traditional ones. X-Economy has also provided a new research direction in market micro-structure analysis. We executed several kinds of multiagent simulations for technical traders (indices) and obtained non-trivial suggestions regarding the relationship between the market randomness and the effectiveness of technical indices. For instance, the performance of complex technical indices seemed to deeply depend on the characteristics and nature of a market when a market became complex, i.e. it moved far from the Wiener process. (C) 2003 Elsevier Inc. All rights reserved.
  • Hidenori Kawamura, Hisao Kadota, Masahito Yamamoto, Toshihiko Takaya, Azuma Ohuchi
    J. Robotics Mechatronics 17 (5) 500 - 508 2005 [Refereed][Not invited]
  • T Kataoka, H Kawamura, K Kurumatani, A Ohuchi
    SOFT COMPUTING AS TRANSDISCIPLINARY SCIENCE AND TECHNOLOGY 245 - 254 1615-3871 2005 [Not refereed][Not invited]
     
    In this paper, we verified the effect of the Distributed Visitors Coordination System in the theme park problem. The system solves the problem caused by time delay between decision-making and emergence of its effect. Its problem can happen generally in the area of congestion information system and causes the oscillation of the queue length in each service facility. In our system, some users register their next destination into a system server, the server estimates future state based on that information. Moreover, we made the exclusive queue for the agents registering next destination in each service facility to stimulate users' registration. According to the computer simulation, even if there were many agents registering excessively, the whole waiting time reduced greatly and the oscillation of queue length in each attraction moderated.
  • ホバリング制御に基づくエンタテインメントバルーンロボットの開発
    川村 秀憲, 角田 久雄, 山本 雅人, 高谷 敏彦, 大内 東
    知能・情報・ファジイ学会論文誌 Vol. 17 (No. 2) 29 - 37 2005 [Not refereed][Not invited]
  • T Kataoka, H Kawamura, K Kurumatani, A Ohuchi
    MASSIVELY MULTI-AGENT SYSTEMS I 3446 335 - 348 0302-9743 2005 [Refereed][Not invited]
     
    A distributed visitors coordination system is proposed as an application of a massively multi-agent system. In the system, some agents register their next destination using an information device such as a cellular phone, and this information is used to reduce the effect of the time delay between decision-making and effect-emergence. This delay causes queue lengths to oscillate. However, it is troublesome for agents to continuously register their next destination. To compensate them, exclusive queues are made available to agents registering their next destination. Computer simulation of the theme park problem, showed that when all agents avoid the congestion by registering their next destination, the total waiting time is minimized and queue length oscillation is reduced.
  • 長尾 光悦, 川村 秀憲, 山本 雅人 他
    観光情報学会誌 観光情報学会 Vol. 1 (No. 1) 38 - 46 1349-919X 2005 [Not refereed][Not invited]
  • 佐藤 博信, 村上 仁, 川村 秀憲
    観光情報学会誌 観光情報学会 Vol. 1 (No. 1) 64 - 70 1349-919X 2005 [Refereed][Not invited]
  • Hidenori Kawamura, Yasushi Okada, Azuma Ohuchi, Koichi Kurumatani
    New Generation Computing 23 (1) 23 - 32 0288-3635 2005 [Refereed][Not invited]
     
    In an artificial market approach with multi-agent systems, the static equilibrium concept is often used in market systems to approximate continuous market auctions. However, differences between the static equilibrium concept and continuous auctions have not been discussed in the context of an artificial market study. In this paper, we construct an artificial market model with both of them, namely, the Itayose and Zaraba method, and show simple characteristic differences between these methods based on computer simulations. The result indicates the further need to model the market system by studying artificial markets. © Ohmsha, Ltd. 2005.
  • Tomohisa Yamashita, Koichi Kurumatani, Yuichi Sasaki, Hidenori Kawamura, Azuma Ohuchi
    New Generation Computing 23 (1) 13 - 22 0288-3635 2005 [Refereed][Not invited]
     
    In this research, we tackled the emergence and stability of key currency when economic strength countries was equal. We propose an artificial international market model with currency credibility as the standard selected for payment. We constructed multiple markets based on the X-Economy System. Through simulations, we found the possibility that key currency could emerge in a symmetric situation, and market and the specialization of production could be stabilized by foreign exchange trade. © Ohmsha, Ltd. 2005.
  • Hidenori Kawamura, Azuma Ohuchi, Koichi Kurumatani
    IEEJ Transactions on Electronics, Information and Systems 電気学会 125 (6) 956 - 966 1348-8155 2005 [Refereed][Not invited]
     
    In this paper, in order to investigate the effect of cogeneration spread senario in electricity market we constructed a multiagent model of an electricity trade market with distributor and power generator agents. In this model, we analyzed the effect of reducing generators' surplus facilities to market price formation and stability through some computer experiments. As a result of the experimental simulations, the market price was decreased by the increase of sell bids according to the demand reduction by congeneration spread, and by the increase of commercial use of cogeneration facilities, the market price was more economical and stable because such agents supplied more electricity generated by surplus cogenerations. However, if power generators diminished power generating facilities in the situation that distributors' cogeneration facilities were not major the fluctuation of market price took large. We confirmed that cogeneration spread played the important role for stabilizing market price formation. © 2005, The Institute of Electrical Engineers of Japan. All rights reserved.
  • KADOTA HISAO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, TAKAYA TOSHIHIKO, OHUCHI AZUMA
    IPSJ Journal 一般社団法人情報処理学会 45 (6) 1715 - 1724 0387-5806 2004/06/15 [Refereed][Not invited]
     
    Balloon robots have attracted attention as new type indoor robots for various applications, e.g., observation, guidance, and amusement flying. A balloon robot can float and move long time in 3-dimensional space by low energy. However, it is difficult to control positioning of a balloon robot because it has great inertia and is easily effected by a little air stream of a conditioner. Positioning control under usual indoor environment is key technology to realize an autonomous balloon robot. In this paper, we develop the indoor-type balloon robot system with a light wireless vision camera. Th...
  • 大内東, 栗原正仁, 三田村保, 川村秀憲, 宮腰昭男, 中川俊男, 宮本慎一, 山本直也, 柳内統
    医療情報学 vol. 23 (no. 4) 293 - 302 0289-8055 2004 [Refereed][Not invited]
  • Masahito Yamamoto, Koichiro Takagi, Masashi Nakatsugawa, Hidenori Kawamura, Azuma Ohuchi
    Information and Communication Technologies in Tourism(ENTER) 317 - 325 2004 [Refereed][Not invited]
  • Keiko Motoyama, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    IEEJ Transactions on Electronics, Information and Systems 124 (10) 1930 - 1937 1348-8155 2004 [Refereed][Not invited]
     
    The final goal of this study is to achieve an autonomous indoor blimp robot. While blimp robots are attractive entities moving safely in three dimensional space, they are hard to control autonomously as they are subjected to strong inertial forces and air resistance, and have many nonlinear characteristics. As blimp robots are used not only in vast halls but also in complex buildings with obstacles such as pillars and walls, they need to plan suitable motion for avoiding them. Furthermore, robots need to conserve energy with restricted power supply because they are unable to carry heavy batteries. We have to design an action-value function for planning motion in a blimp robot, considering constraints imposed by these characteristics of an actual robot. In this paper, we designed an action-value function for motion planning based on the potential field method, and evaluated its effectiveness in a simulated environment. © 2004, The Institute of Electrical Engineers of Japan. All rights reserved.
  • Hidenori Kawamura, Takashi Kataoka, Azuma Ohuchi, Koichi Kurumatani
    IEEJ Transactions on Electronics, Information and Systems 124 (10) 1922 - 1929 1348-8155 2004 [Refereed][Not invited]
     
    We focus on the simple theme park problem, where there are two attractions and visitor agents which select their destination attraction based on congestion disregarding behavior and congestion avoiding behavior. According to the computer simulation, the result shows that the growth of individual congestion avoiding behavior is not always effective for improving global performance, and this phenomenon is caused by the oscillation of successive selection switching of the same destination by many congestion avoiding agents. Although the model and setting of this paper is simpler than other related works, we consider each phenomenon in those works has the same characteristic based on the ineffectiveness caused by the homogeneity of congestion avoiding behavior and information sharing. © 2004, The Institute of Electrical Engineers of Japan. All rights reserved.
  • Modeling of Theme Park Problem with Multiagent for Mass User Support
    Hidenori Kawamura, Koichi Kurumatani, Azuma Ohuchi
    Multiagent for Mass User Support 3012 48 - 69 2004 [Refereed]
  • Oouchi Azuma, Kawamura Hidenori
    Journal of Japanese Society for Artificial Intelligence 社団法人人工知能学会 18 (6) 697 - 703 0912-8085 2003/11/01 [Not refereed][Not invited]
  • Keiko Motoyama, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    IFIP Advances in Information and Communication Technology 112 191 - 198 2003 [Refereed]
  • 川村秀憲, 大内東
    システム/制御/情報 システム制御情報学会 46 (9) 555 - 560 0916-1600 2002/09/15 [Not refereed][Not invited]
  • KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA
    シミュレーション 日本シミュレーション学会 21 (2) 143 - 153 0285-9947 2002/06/15 [Not refereed][Not invited]
     
    Recently, the agent-based simulation approaches have been remarkable to study social, economic, and financial complex systems. In these approaches, a designed agent often has many parameters which characterize itself, and these parameters are dynamically changed according to the ability of learning, evolution, and adaptation. Thus, it is necessary to confirm the methodologies to design, represent, and evaluate agents and interaction ovjectively. To overcome these issues, we found X-Economy Project in which we try to investigate the economic complex systems based on agent-based simulation approaches and propose the methodology for such research style. Namely, we have constructed the simulation platform, called X-Economy System, for artificial economy and artificial market. X-Economy System is expected to become the simulation system like Linux for such type researches. Especially, we have developed some research programs using X-Economy System for gradual investigation of complex economic systems. In this paper, the concept of X-Economy Project, the outline of X-Economy System, some research programs based on X-Economy System, and the aim of researches have been reported.
  • H Kawamura, A Ohuchi, K Kurumatani
    AGENT-BASED APPROACHES IN ECONOMIC AND SOCIAL COMPLEX SYSTEMS 72 188 - 197 0922-6389 2002 [Refereed][Not invited]
     
    X-Economy project aims to confirm the forum of agent-based economics in order to clarify the principle of complex economic behavior. Especially, this project tries to provide the agent-based economic simulation platform, standard economic models, and research topics. Owing to share the common simulation platform, we can clearly exchange research paradigms and results with each other. We hope these efforts promote the advance of elucidation of economic complex systems. In this paper, we report the archtecture of prototype X-Economy system and two cases of research based on the system.
  • Design of Adaptive Self Navigated Airship in Simulated Environment
    Keiko Motoyama, Keiji Suzuki, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    Operations Research/Management Science at Work, the International Series in Operations Research & Management Science 43 205 - 213 2002 [Refereed][Not invited]
  • Exogenous Information and Endogenous Market Behavior with Artificial Learning Traders
    Hidenori Kawamura, Daisuke Kanehira, Koichi Kurumatani, Azuma Ohuchi
    Papers from the AAAI Workshop, Multi-Agent Modeling and Simulation of Economic Systems, Technical Report WS-02-10 40 - 45 2002 [Refereed][Not invited]
  • Emergence of Key Currency by Interaction among International and Domestic Markets
    Tomohisa Yamashita, Yuichi Sasaki, Hidenori Kawamura, Koichi Kurumatani, Azuma Ohuchi
    Papers from the AAAI Workshop, Multi-Agent Modeling and Simulation of Economic Systems, Technical Report WS-02-10 16 - 21 2002 [Refereed][Not invited]
  • Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    "Operations Research/Management Science at Work" in the International Series in Operations Research & Management Science 43 41 - 52 2002 [Refereed]
  • 川村 秀憲, 大内 東, 車谷 浩一
    オペレーションズ・リサーチ : 経営の科学 社団法人日本オペレーションズ・リサーチ学会 46 (10) 537 - 543 0030-3674 2001/10/01 [Not refereed][Not invited]
  • KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma
    計測自動制御学会論文集 計測自動制御学会 37 (5) 455 - 464 0453-4654 2001/05/31 [Refereed][Not invited]
  • Tomohisa Yamashita, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    Proceedings of JSAI 2001 Internal Workshop on Agent-based Approaches in Economic and Social Complex Systems (AESCS 2001) 174 - 183 2001 [Refereed][Not invited]
  • H Kawamura, M Yamamoto, K Suzuki, A Ohuchi
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES E83A (2) 371 - 379 0916-8508 2000/02 [Refereed][Not invited]
     
    Recently, researchers in various fields have shown interest in the behavior of creatures from the viewpoint of adaptiveness and flexibility. Ants, known as social insects, exhibit collective behavior in performing tasks that can not be carried out by an individual ant. In ant colonies. chemical substances, called pheromones, are used as a way to communicate important information on global behavior. For example. ants looking for food lay the way back to their nest with a specific type of pheromone. Other ants can follow the pheromone trail and find their way to baits efficiently. In 1991, Colorni et al. proposed the ant algorithm for Traveling Salesman Problems (TSPs) by using the analogy of such foraging behavior and pheromone communication. In the ant algorithm, there is a colony consisting of many simple ant agents that continuously visit TSP cities with opinions to prefer subtours connecting near cities and they lay strong pheromones. The ants completing their tours lay pheromones of various intensities with passed subtours according to distances. Namely, subtours in TSP tourns that have the possibility of being better tend to have strong pheromones, so the ant agents specify good regions in the search space by using this positive feedback mechanism. In this paper, we propose a multiple ant colonies algorithm that has been extended from the ant algorithm. This algorithm as several ant colonies for solving a TSP, while the original has only a single ant colony. Moreover, two kinds of pheromone effects, positive and negative pheromone effects, are introduced as the colony-level interactions. As a result of colony-level interactions, the colonies can exchange good schemata for solving a problem and can maintain their own variation in the search process. The proposed algorithm shows better performance than the original algorithm with almost the same agent strategy used in both algorithms except for the introduction of colony-level interactions.
  • A Study on Evolutionary Emergence of Pheromone Communication on Ants War
    Hidenori Kawamura, Masahito Yamamoto, Keiji Suzuki, Azuma Ohuchi
    INTELLIGENT AUTONOMOUS SYSTEMS 6 527 - 534 2000 [Refereed]
  • T Yamashita, H Kawamura, A Ohuchi
    IECON 2000: 26TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4 2873 - 2878 1553-572X 2000 [Refereed][Not invited]
     
    This paper deals with the extended social dilemma model "Distributed Social Dilemma". In order to emerge mutually cooperative behavior among non-altruistic individuals, we propose the solution based on the centralized organization, "meta-player". By comparison with some cases, we confirm the effect of competitive metaplayers.
  • H Kawamura, A Ohuchi
    IECON 2000: 26TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4 2831 - 2836 1553-572X 2000 [Refereed][Not invited]
     
    This paper is concerned with the evolutionary emergence of collective intelligence and agents communication of artificial pheromone. As the stage of evolution, we introduce the ants war environment in which two colinies of ants compete in order to aquire more number of food items. Throughout simulation of evolution, we confirmed the emergence of sense of artificial pheromone and collective intelligence of artificial ants.
  • Hiroyuki Iizuka, Masatoshi Hiramoto, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi
    RoboCup 2000: Robot Soccer World Cup IV Springer 449 - 452 2000 [Refereed][Not invited]
  • Hidenori Kawamura, Masahito Yamamoto, Keiji Suzuki, Azuma Ohuchi
    Advances in Artificial Life, 5th European Conference, ECAL'99, Lausanne, Switzerland, September 13-17, 1999, Proceedings Springer 639 - 643 1999 [Refereed][Not invited]
  • H Kawamura, M Yamamoto, T Mitamura, K Suzuki, A Ohuchi
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES E81A (6) 1089 - 1096 0916-8508 1998/06 [Refereed][Not invited]
     
    In this paper, we propose a new cooperative search algorithm based on pheromone communication for solving the Vehicle Routing Problems. In this algorithm, multi-agents can partition the problem cooperatively and search partial solutions independently using pheromone communication, which mimics the communication method of real ants. Through some computer experiments the cooperative search of multi-agents is confirmed.
  • H Kawamura, M Yamamoto, K Suzuki, A Ohuchi
    INTELLIGENT AUTONOMOUS SYSTEMS 587 - 594 1998 [Refereed][Not invited]
     
    In this paper, we propose the collective search algorithm based on pheromone communication for Vehicle Routing Problems. This algorithm is designed using multi-agent system, in which agents autonomously and independently search the partial solution of given problem to decrease their searching load. Pheromone communication imitated from social insects, i.e., real ants and bee, is used as the communication method between agents to emerge the cooperative behavior. Throughout computer experiments, we confirm the effectiveness of proposed algorithm for view point of cooperative behavior.

Books etc

Conference Activities & Talks

  • ChatGPTを使い倒そう
    川村秀憲
    国立大学図書館協会北海道地区協会 令和5年度企画事業  2024/02
  • ChatGPTの先に待っている世界
    川村秀憲
    株式会社東急エージェンシー社内講演  2024/01
  • 人工知能の未来 ChatGPTを超えて
    川村秀憲
    北海道ミライづくりフォーラム2023  2023/11
  • 人工知能の未来 ChatGPTの先に待っている世界
    川村秀憲
    第416回札幌日経懇話会定例会  2023/10
  • 人工知能の未来 ChatGPTを超えて
    川村秀憲
    東レ株式会社「2023 東レ経営研究所 第35回特別講演会」  2023/10
  • 人工知能の未来 ChatGPTを超えて
    川村秀憲
    日本創造学会 第45回研究大会  2023/09
  • ヒトとデジタル（AI）が共存する未来
    川村秀憲
    公益社団法人日本包装技術協会・北海道支部総会「特別講演」  2023/07
  • 人工知能の未来ChatGPTを超えて
    川村秀憲
    札幌商工会議所 政策委員会 主催セミナー  2023/07
  • 「ヒトとデジタルが共存するミライ」
    川村秀憲, 三浦世子
    「NoMaps Conference 2022」  2022/10
  • 「札幌AIラボ のこれまでとこれから。 ～次なる成長に向けた地域エコシステムの発展を目指して～」
    川村秀憲
    「札幌AI道場」開設式  2022/08
  • AI俳句から目指す、人とAIが調和して発展する動的システムとは
    川村 秀憲
    ビジネス＋IT Webセミナー「AI・業務自動化・RPA 2022春」  2022/05
  • DXによる社会構造の変革について
    川村 秀憲
    令和3年度北海道水素イノベーション推進協議会  2022/02
  • デジタルの力で課題『解決』先進地域へ
    川村 秀憲, 三浦 世子, 舩越 裕勝, 丸山 哲太郎, 瓜生 淳史
    第2回Sapporo mirAI nITe  2021/12
  • テクノロジーと人との調和-人工知能最前線-
    川村 秀憲
    第45回日本血液事業学会総会  2021/11
  • ポストコロナ社会に向けて-人工知能最前線と応用事例-
    川村 秀憲
    日本学術会議北海道地区会議学術講演会  2021/11
  • AIがもたらす“わくわくする未来” ～人工知能が俳句を詠む AI一茶くんの挑戦～
    川村 秀憲
    クレスコフェア2021
  • 未来を描く人工知能〜AI俳句から語る人と機械の調和〜
    川村 秀憲
    さっぽろみらいカンファレンス  2021/10
  • 人工知能が俳句を詠む日～機械が知能を獲得するために～
    川村 秀憲
    一般社団法人情報処理学会「第5回 AI，創造性，SF，その先に(１)」  2021/09
  • AIの産業実装の現状と将来展望
    川村 秀憲
    AI実装によるDX推進（中小企業のAI技術活用セミナー）  2021/07
  • 人工知能が俳句を詠む：AI一茶くんの挑戦
    川村 秀憲
    第5回情報法制シンポジウム  2021/07
  • 人工知能が俳句を詠む日～機械が知能を獲得するために
    川村 秀憲
    NVIDIA GTC 2021  2021/04
  • テクノロジーと人との調和 人工知能最前線
    川村 秀憲
    札幌日経懇話会  2021/04
  • テクノロジーと人との調和 － 人工知能最前線 －
    川村 秀憲
    北海道総合通信局主催「ICTによる地域課題の解決×スタートアップ創出セミナー」  2021/03
  • テクノロジーと人との調和 人工知能最前線
    川村 秀憲
    ネットワンシステムズ株式会社、ソフトバンク株式会社共催Webセミナー「DXにおけるデータサイエンスの必要性」  2021/01
  • ポストコロナ時代、AI、テクノロジーをどう活かすべきか
    川村 秀憲
    日経BPデジタルイノベーション2020  2020/12
  • Withコロナ時代に求められる暮らしに溶け込むサービスデザインとは？
    川村 秀憲
    LIVING TECHカンファレンス2020  2020/10
  • テクノロジーと人との調和 人工知能最前線と応用事例
    川村 秀憲
    令和2年度食肉生産技術システム研究会  2020/10
  • AI活用から新しい価値観をSOUZOUする～予測不能な経済社会環境をスマートに生きるために～
    川村 秀憲
    北海道テレコム懇談会第77回ICTサロン  2020/08
  • ポストコロナ時代、AI、テクノロジーをどう活かすべきか
    川村 秀憲
    STARTUP CITY SAPPORO・経済産業省北海道経済産業局主催「SCSウェビナーシリーズ 北海道発 >> ポストコロナ時代に挑むスタートアップ特集 第1回 ITスタートアップ編」  2020/07
  • withコロナを生き抜く～リテールストアチェーンはAIでどう変わるのか？
    川村 秀憲
    フュージョン株式会社主催特別セミナー  2020/05
  • AI が紡ぎ出した札幌のスタートアップ企業群
    川村 秀憲
    さっぽろ産業振興財団主催「Sapporo mirAI ｎITe」  2020/02
  • 人工知能の最前線と応用事例
    川村 秀憲
    第33回数値流体力学シンポジウム  2019/11
  • Harmony between AI and Humans
    Hidenori Kawamura
    経済産業省北海道経済産業局・一般社団法人ロシアNIS貿易会主催「シベリア・イノベーション分野交流セミナー」  2019/11
  • Harmony between AI and Humans
    Hidenori Kawamura
    The 22nd SNU-HU Joint Symposium  2019/11
  • 人工知能の最新研究事例とその可能性
    川村 秀憲
    株式会社イー・ステート・オンライン主催「ESOテクノロジーサミット2019 in TOKYO」  2019/11
  • 多様なAI技術の活用～AI俳句
    川村 秀憲
    本田技研工業株式会社主催「集中経営フォーラム」  2019/11
  • イスラエルはなぜスタートアップネイションと呼ばれるのか
    川村 秀憲
    NoMaps2019  2019/10
  • Proposal of Mutual Concession Cars using Deep Q-Network
    Ichitaro Ogawa, Yoshiki Hosokawa, Soichiro Yokoyama, Tomohisa Yamashita, Hidenori Kawamura, Takayuki Warabino, Akira Sakatoku, Tadashi Yanagihara, Tomohiko Ogishi, Hideaki Tanaka
    エヌビディア合同会社主催「GTC Japan 2018」  2019/09
  • AI俳句
    川村 秀憲
    奥の細道サミットin金沢実行委員会  2019/07
  • AIの最前線と未来～研究からビジネス応用へ、捉えるべき視点
    川村 秀憲
    アクセンチュア株式会社主催「AI For Business Success 2019 in Osaka」  2019/05
  • 人工知能がもたらすもの －生産性の向上への大革命－
    川村 秀憲
    一般社団法人札幌建設業協会2019年度総会特別講演会  2019/05
  • 人工知能の最前線とその応用
    川村 秀憲
    株式会社北海道二十一世紀総合研究所2019年「北洋ビジネスクラブ新春講演会」  2019/01
  • テクノロジーと人との調和 人工知能最前線
    川村 秀憲
    公益社団法人自動車技術会第5回CFD技術部門委員会  2019/01
  • AIがもたらす近未来の社会変化
    川村 秀憲
    岩見沢商工会議所新春特別講演会  2019/01
  • 社会に調和するAI
    川村 秀憲
    JSAI合同研究会2018  2018/11
  • 人工知能の最新研究と応用
    川村 秀憲
    財団法人沿岸技術研究センター コースタルテクノロジー2018  2018/11
  • AIがもたらす近未来の社会変化～経営者が知っておくべき最近のAI事情～
    川村 秀憲
    札幌商工会議所特別講演会  2018/11
  • AI・ITの進化第4次産業革命
    川村 秀憲
    上士幌町かみしほろ塾2018  2018/10
  • ファッションAIで服の印象を理解する
    神戸瑞樹, 横山想一郎, 山下倫央, 川村秀憲
    エヌビディア合同会社主催「GTC Japan 2018」  2018/09
  • 人工知能が俳句を詠む「AI一茶くん」
    米田航紀, 横山想一郎, 山下倫央, 川村秀憲
    エヌビディア合同会社主催「GTC Japan 2018」  2018/09
  • 人工知能の応用と地域課題
    川村 秀憲
    北海道総合ICT水産業フォーラム交流会  2018/01
  • 人工知能の最新研究と応用
    川村 秀憲
    港湾空港技術地域特別講演会  2017/12
  • ディープラーニングの発展とビジネス応用
    川村 秀憲
    JISTA北海道支部・ITC札幌共催公開セミナー2017  2017/09
  • AIの適用について
    川村 秀憲
    国立研究開発法人海上・港湾・航空技術研究所講演会  2017/07
  • 人工知能の先端と応用
    川村 秀憲
    JR北海道駅ビル協議会講演会  2017/07
  • ディープラーニングの研究事例と産業応用の可能性
    川村 秀憲
    電子情報通信学会リコンフィギャラブルシステム研究会  2017/06
  • 人工知能の先端と応用
    川村 秀憲
    北海道税理士会札幌中支部第38回定期総会  2017/06
  • Sapporo AI Labが描く未来 ～ AI社会実装を先導する都市「さっぽろ」を目指して ～
    川村 秀憲
    札幌AIラボキックオフイベント基調講演  2017/06
  • AIによるイノベーションは社会をどう変えるのか
    川村 秀憲
    NPO法人コンベンション札幌ネットワーク総会記念講演会  2017/05
  • 人工知能の先端と応用
    川村 秀憲
    日立ITユーザ会北海道支部第44回支部総会  2017/05
  • 人工知能の現状とビジネスへの応用
    川村 秀憲
    札幌青年会議所第１回理事長例会講演会  2017/03
  • 人工知能の現状とビジネスへの応用
    川村 秀憲
    北海道NEC C&Cシステムユーザー会  2017/03
  • 人工知能の現状とその応用
    川村 秀憲
    フュージョン株式会社上場記念講演会  2017/03
  • 人工知能のインパクトとこれからの未来
    川村 秀憲
    千歳市市民教養セミナー  2017/03
  • 人工知能のインパクトとこれからの未来
    川村 秀憲
    産学官金連携フォーラム, 中小企業家同友会  2017/03
  • AIの活用と地方創生
    川村 秀憲
    サツドラホールディングス主催「はとの会新春セミナー」  2017/01
  • 人工知能を取り巻く現状と観光分野への展望
    川村 秀憲
    産学官CIM・GIS研究会 観光ICT地域活性化戦略セミナー  2016/11
  • 人工知能のインパクトとこれからの未来
    川村 秀憲
    情報産業エルム会セミナー  2016/09
  • 人工知能のインパクトとこれからの未来
    川村 秀憲
    エスピーアイ × albedo Japan × AI TOKYO LAB & Co. 共催セミナー  2016/07
  • リアルタイム興味解析に基づく地域情報最適化フレームワークの提案
    川村 秀憲
    ICTイノベーションフォーラム2017  2015/09
  • 視覚障がい者における読書支援環境 Light Studyの開発
    川村 秀憲
    文部科学省委託事業「支援機器等教材を活用した指導方法充実事業」 第2回校内研修会  2015/08
  • 北海道大学大学院情報科学研究科調和系工学研究室
    川村 秀憲
    共同研究発掘フェア in 北洋銀行ものづくりテクノフェア2015  2015/07
  • フェイスブック・ツイッターを活用した情報発信方法を学ぶ
    川村 秀憲
    観光情報の効果的受発信に向けたＩＴ活用塾  2014/10
  • 観光地に求められる情報発信のあり方を理解する
    川村 秀憲
    観光情報の効果的受発信に向けたＩＴ活用塾  2014/10
  • リアルタイム興味解析に基づく地域情報最適化フレームワークの提案
    川村 秀憲
    戦略的情報通信研究開発推進事業（SCOPE） 成果発表会  2014/07
  • 観光情報学の実践的取り組み
    川村 秀憲
    北海道ITS推進フォーラム  2014/02
  • 北大発ベンチャーによるO2Oサービスの開発と運用
    川村 秀憲
    第2回ビッグデータと統計学研究集会  2013/02
  • 社会サービスのプラグイン研究とスマートシティ
    川村 秀憲
    ソフトウェア科学会全国大会  2012/08
  • 地域情報サイト あなた情報マガジンびも～る の野望
    川村 秀憲
    GISフォーラム  2011/10
  • 興味解析と流通調整に基づく受信者主導型情報配信システム
    川村 秀憲
    ITベンダグループスタディ  2010/12

MISC

  • 衣服画像ペアの関係を表現する説明文の生成
    阿部 晃平, 横山 想一郎, 山下 倫央, 川村 秀憲  画像ラボ 2023年10月号  2023/10
  • 細川万維, 横山想一郎, 山下倫央, 川村秀憲, 関屋英理子  情報処理学会研究報告(Web)  2022-  (ICS-206)  2022
  • 阿部涼介, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2022-  (ICS-206)  2022
  • 花野愛里咲, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2022-  (ICS-206)  2022
  • 森雄斗, 横山想一郎, 山下倫央, 川村秀憲, 森正人  情報処理学会研究報告(Web)  2022-  (ICS-206)  2022
  • 大江弘峻, 横山想一郎, 山下倫央, 川村秀憲, 多田満朗  情報処理学会研究報告(Web)  2022-  (ICS-206)  2022
  • 西浦翼, 横山想一郎, 山下倫央, 川村秀憲  人工知能学会知識ベースシステム研究会資料  125th-  2022
  • 清水雅之, 横山想一郎, 山下倫央, 川村秀憲, 萩谷俊幸, 大岸智彦  人工知能学会知識ベースシステム研究会資料  125th-  2022
  • 大倉博貴, 横山想一郎, 山下倫央, 川村秀憲, 白井直樹, 長川大介, 宮脇雅史  人工知能学会知識ベースシステム研究会資料  125th-  2022
  • 織田智矢, 山下倫央, 横山想一郎, 川村秀憲, 萩谷俊幸, 大岸智彦  電子情報通信学会技術研究報告(Web)  121-  (439(AI2021 26-36))  2022
  • 着衣人物画像に対する印象推定を用いた衣服推薦システムの開発
    柳 公人, 川村 秀憲, 山下 倫央, 横山 想一郎  社会システムと情報技術研究ウィーク(RST2021)  2021
  • メトリックラーニングを用いたOD推定システムの開発
    久保田 遼裕, 横山 想一郎, 山下 倫央, 川村 秀憲, 弓崎 潔, 佐藤 好美  社会システムと情報技術研究ウィーク(RST2021)  2021
  • 屋内エンターテイメント用バルーンロボットの自律制御システムの開発
    永田 紘也, 横山 想一郎, 山下 倫央, 川村 秀憲  第20回複雑系マイクロシンポジウム  2021
  • 平田航大, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2021-  (IFAT-143)  2021
  • 幡本昂平, 横山想一郎, 山下倫央, 川村秀憲  人工知能学会論文誌(Web)  36-  (5)  2021
  • 川村秀憲  血液事業  44-  (2)  2021
  • 栗原聡, 川村秀憲, 津田一郎, 大倉和博  人工知能  36-  (5)  2021
  • 今原智広, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2021-  (ICS-201)  2021
  • 椿康平, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2021-  (ICS-201)  2021
  • 小林直也, 横山想一郎, 山下倫央, 川村秀憲, 関屋英理子, 杉浦仁志  情報処理学会研究報告(Web)  2021-  (ICS-201)  2021
  • 西佑希, 横山想一郎, 山下倫央, 川村秀憲, 蕨野貴之, 大岸智彦, 田中英明  情報処理学会研究報告(Web)  2021-  (ICS-201)  2021
  • 平田航大, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2021-  (ICS-201)  2021
  • 平間友大, 横山想一郎, 山下倫央, 川村秀憲  画像ラボ  31-  (5)  1  -7  2020/05
  • 川村 秀憲, 大知 正直, 清 雄一, 福田 直樹, 横山 想一郎  情報処理  61-  (5)  482  -483  2020/04/15  
    1991年の特集「30年度の情報処理」に掲載された人工知能研究の将来予測の記事を要約・検証し，それをもとに2050年に向けて人工知能研究の将来を予想する．1991年の記事は仮説推論システムをもとに人工知能による「発想」や「ひらめき」の実現しようというものである．その中で課題とされている知識獲得のボトルネックや処理の高速化と，現在の深層学習をはじめとした機械学習の隆盛とのかかわりを述べる．また，現在は30年前と比べ人工知能技術を利用したシステムが実用に供される場面が増えており，社会のなかで人工知能が果たす役割が重要となりつつある．複数の人間が集まって社会を構成するという人間の知的機能を人工知能が実現するための方法を考察する．
  • 神戸 瑞樹, 横山 想一郎, 山下 倫央, 川村 秀憲  行動変容と社会システム vol.06  (2020)  2020/03/07
  • 幡本 昂平, 横山 想一郎, 山下 倫央, 川村 秀憲  行動変容と社会システム vol.06  (2020)  2020/03/07
  • 吉田拓海, 阿部涼介, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2020-  (2020)  2020/03/07
  • 吉田拓海, 横山想一郎, 山下倫央, 川村秀憲  人工知能学会知識ベースシステム研究会資料  119-  17  -22  2020/03/07
  • B2Bブランド品オークションにおける落札価格分布の推定
    幡本 昂平, 横山 想一郎, 山下 倫央, 川村 秀憲  第18回データ指向構成マイニングとシミュレーション研究会  2020
  • 自動運転車両の交通流量増加に向けた動的パスプランニングの実装
    西 佑希, 横山 想一郎, 山下 倫央, 川村 秀憲, 蕨野 貴之, 大岸 智彦, 田中 英明  情報処理北海道シンポジウム2020  2020
  • 単語の分散表現を用いた俳句における取り合わせの評価手法の検討
    平田 航大, 横山 想一郎, 山下 倫央, 川村 秀憲  情報処理北海道シンポジウム2020  2020
  • 灯油配送の効率化に向けた状態空間モデルを用いた灯油残量の推定
    椿 康平, 横山 想一郎, 山下 倫央, 川村 秀憲  情報処理北海道シンポジウム2020  2020
  • 料理レシピの構造化とスケジューリング
    小林 直也, 横山 想一郎, 山下 倫央, 川村 秀憲, 関屋 英理子, 畠山 潤, 杉浦 仁志  情報処理北海道シンポジウム2020  2020
  • バス車内画像を用いた深層学習に基づく混雑状況推定モデルの検証
    西浦 翼, 横山 想一郎, 山下 倫央, 川村 秀憲  情報処理北海道シンポジウム2020  2020
  • 医療時系列データにおける Attention を用いたイベント予測モデルの検証
    大江 弘峻, 横山 想一郎, 山下 倫央, 川村 秀憲  情報処理北海道シンポジウム2020  2020
  • 服飾画像に対する印象推定を用いたファッション評価システムの開発
    柳 公人, 横山 想一郎, 山下 倫央, 川村 秀憲  情報処理北海道シンポジウム2020  2020
  • バス乗客ODデータの収集に向けた同一人物判定手法の検証
    久保田 遼裕, 横山 想一郎, 山下 倫央, 川村 秀憲, 弓崎 潔, 佐藤 好美  情報処理北海道シンポジウム2020  2020
  • ECサイト掲載商品の紹介文作成支援システムにおける複数文組合せ機能の開発
    阿部 涼介, 横山 想一郎, 山下 倫央, 川村 秀憲  情報処理北海道シンポジウム2020  2020
  • 前腕支持型四輪歩行器の歩行支援機能の開発
    森 雄斗, 横山 想一郎, 山下 倫央, 川村 秀憲, 森 正人, 加藤 士雄  情報処理北海道シンポジウム2020  2020
  • 屋内エンターテイメント用バルーンロボットの自律制御システムの開発
    永田 紘也, 横山 想一郎, 山下 倫央, 川村 秀憲  情報処理北海道シンポジウム2020  2020
  • 川村秀憲  ながれ  39-  (2)  2020
  • JIE Min, YOKOYAMA Soichiro, YAMASHITA Tomohisa, KAWAMURA Hidenori  電子情報通信学会技術研究報告  119-  (469(AI2019 54-64)(Web))  2020
  • 横山想一郎, 高橋遼, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2020-  (ICS-198)  2020
  • 平間友大, 横山想一郎, 山下倫央, 川村秀憲  画像ラボ  31-  (5)  2020
  • 木戸口稜, 横山想一郎, 山下倫央, 川村秀憲  電子情報通信学会技術研究報告  119-  (469(AI2019 54-64)(Web))  2020
  • 吉田拓海, 阿部涼介, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2020-  (DCC-25)  2020
  • 横山 想一郎, 山下 倫央, 川村 秀憲, 武田 清賢  画像ラボ  30-  (6)  27  -33  2019/06
  • 松原仁, 川村秀憲  電子情報通信学会誌  102-  (3)  2019
  • 川村秀憲  水産工学  56-  (1)  2019
  • CHEN Ce, YOKOYAMA Soichiro, YAMASHITA Tomohisa, KAWAMURA Hidenori  情報処理学会研究報告(Web)  2019-  (ICS-194)  2019
  • 平間友大, 横山想一郎, 山下倫央, 川村秀憲, 鈴木恵二, 和田雅昭  電子情報通信学会技術研究報告  118-  (492(AI2018 53-59)(Web))  2019
  • 米田航紀, 横山想一郎, 山下倫央, 川村秀憲  電子情報通信学会技術研究報告  118-  (492(AI2018 53-59)(Web))  2019
  • 小川一太郎, 横山想一郎, 山下倫央, 川村秀憲, 酒徳哲, 柳原正, 蕨野貴之, 大岸智彦, 田中英明  電子情報通信学会技術研究報告  118-  (492(AI2018 53-59)(Web))  2019
  • 工藤郁弥, 横山想一郎, 山下倫央, 川村秀憲  電子情報通信学会技術研究報告  118-  (492(AI2018 53-59)(Web))  2019
  • 桶智輝, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2019-  (ICS-194)  2019
  • 横山想一郎, 米田航紀, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2019-  (ICS-196)  2019
  • 横山想一郎, 山下倫央, 川村秀憲  人工知能  34-  (4)  2019
  • 横山想一郎, 山下倫央, 川村秀憲, 武田清賢  画像ラボ  30-  (6)  2019
  • 吉田拓海, 横山想一郎, 山下倫央, 川村秀憲  情報科学技術フォーラム講演論文集  18th-  2019
  • 平間友大, 横山想一朗, 山下倫央, 川村秀憲, 鈴木恵二, 和田雅昭  情報科学技術フォーラム講演論文集  18th-  2019
  • 神戸瑞樹, 横山想一郎, 山下倫央, 川村秀憲  情報科学技術フォーラム講演論文集  18th-  2019
  • 幡本昂平, 横山想一郎, 山下倫央, 川村秀憲  情報科学技術フォーラム講演論文集  18th-  2019
  • 平間 友大, 横山 想一郎, 山下 倫央, 川村 秀憲  情報処理  59-  (11)  974  -977  2018/10/15  
    本稿に示すディープラーニング活用事例は「FISH（Fisheries Intelligence System Hokkaido）」と呼ばれる，産学連携のプロジェクトの一部である．北海道の定置網漁でマグロをはじめとする漁獲量が制限枠を超過する問題を対象として，制限超過の回避策を講じるための情報提供を目的としている．現状では定置網内の魚種の把握にニーズがあるため，魚群探知機から得られる音響画像に畳み込みニューラルネットワーク（CNN）を適用した魚種推定モデルの開発を進めている．本稿では，マグロの有無に特化した魚種推定モデルを構築する際に利用している開発環境，教師データ，CNNの設定を解説する．さらに，感度マップを用いた誤判別結果の分析を行い，今後の改善を提案する．
  • 山下 倫央, 小川 一太郎, 横山 想一郎, 川村 秀憲, 蕨野 貴之, 大岸 智彦, 田中 英明  シミュレーション = Journal of the Japan Society for Simulation Technology  37-  (3)  153  -159  2018/09
  • 山下 倫央, 小川 一太郎, 横山 想一郎, 川村 秀憲, 蕨野 貴之, 大岸 智彦, 田中 英明  車載テクノロジー = Automotive technology  5-  (6)  42  -46  2018/08
  • 山下 倫央, 小川 一太郎, 横山 想一郎, 川村 秀憲, 酒徳 哲, 柳原 正, 蕨野 貴之, 大岸 智彦, 田中 英明  自動車技術 = Journal of Society of Automotive Engineers of Japan  72-  (5)  53  -58  2018/05
  • 松林 圭, 山下 晃弘, 中村 拓哉, 吉田 優之, 川村 秀憲  第80回全国大会講演論文集  2018-  (1)  277  -278  2018/03/13  [Not refereed][Not invited]
     
    掲示板やSNSが普及してくるにつれ,日報やディスカッションなどの企業業務のナレッジマネジメントに応用をする動きが活発になっている.しかし掲示板やSNSはその特性上どの投稿がその話題の中でもっとも重要な情報であるかをユーザが把握しづらく,埋もれてしまう情報も少なくない.そのため,社内に蓄積された様々な情報を可視化する研究も多く,それらを応用した様々なサービスも存在する.本研究ではそのような大量のテキストデータから重要な情報を自動要約し,社内のナレッジとして有効活用することを目的としている.最終的に社内で活用されるシステムを目指し,複数のテキスト要約手法の比較や実データによる評価を行う.
  • 神戸 瑞樹, 横山 想一郎, 山下 倫央, 川村 秀憲  電子情報通信学会技術研究報告 = IEICE technical report : 信学技報  117-  (468)  1  -7  2018/03/02
  • 今野陽子, 中村拓哉, 吉田優之, 川村秀憲  人工知能学会全国大会論文集(CD-ROM)  32nd-  2018
  • 川村秀憲  日本水産工学会シンポジウム要旨集  2018-  2018
  • 幡本昂平, 横山想一朗, 横山想一朗, 山下倫央, 山下倫央, 川村秀憲, 川村秀憲  情報処理学会研究報告(Web)  2018-  (ICS-190)  2018
  • 山下倫央, 小川一太郎, 横山想一郎, 川村秀憲, 酒徳哲, 柳原正, 蕨野貴之, 大岸智彦, 田中英明  自動車技術  72-  (5)  2018
  • 米田航紀, 横山想一郎, 山下倫央, 川村秀憲  人工知能学会全国大会論文集(CD-ROM)  32nd-  2018
  • 横山想一郎, 山下倫央, 川村秀憲, 武田清賢, 横川誠  人工知能学会全国大会論文集(CD-ROM)  32nd-  2018
  • 小川一太郎, 横山想一郎, 山下倫央, 川村秀憲, 酒徳哲, 柳原正, 大岸智彦, 田中英明  人工知能学会全国大会論文集(CD-ROM)  32nd-  2018
  • 幡本昂平, 横山想一郎, 山下倫央, 川村秀憲  人工知能学会全国大会論文集(CD-ROM)  32nd-  2018
  • 吉田拓海, 横山想一郎, 山下倫央, 川村秀憲  人工知能学会全国大会論文集(CD-ROM)  32nd-  2018
  • 米田航紀, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2018-  (ICS-192)  2018
  • 吉田拓海, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2018-  (ICS-192)  2018
  • 平間友大, 横山想一郎, 山下倫央, 川村秀憲  情報処理  59-  (11)  2018
  • 神戸瑞樹, 横山想一郎, 山下倫央, 川村秀憲  電子情報通信学会技術研究報告  118-  (116(AI2018 1-12)(Web))  2018
  • 木戸口稜, 横山総一郎, 山下倫央, 川村秀憲  電子情報通信学会技術研究報告  118-  (116(AI2018 1-12)(Web))  2018
  • 山下倫央, 小川一太郎, 横山想一郎, 川村秀憲, 蕨野貴之, 大岸智彦, 田中英明  シミュレーション  37-  (3)  2018
  • 山下倫央, 小川一太郎, 横山想一郎, 川村秀憲, 蕨野貴之, 大岸智彦, 田中英明  月刊車載テクノロジー  5-  (6)  2018
  • HIRAMA Yudai, YOKOYAMA Soichiro, YAMASHITA Tomohisa, KAWAMURA Hidenori, SUZUKI Keiji, WADA Masaaki  Proceedings of the Annual Conference of JSAI  2018-  1B2OS11b02  -1B2OS11b02  2018  [Not refereed]
     

    The overfishing and depletion of marine resources including tuna have become problems in Japan. Managing to marine resource is necessary to increase catch amount. However, set-net is difficult to separate fish speceis. Therefore, this research used a sonar image obtained by an echo sounder installed in a set-net. We verify of fish species estimation model based on echo sounder image.

  • 今野陽子, 山下晃弘, 松林圭, 松原良和, 西谷雅史, 鈴木恵二, 川村秀憲, 井上祐寛  情報処理学会研究報告(Web)  2017-  (ICS-186)  2017
  • 川村秀憲  電子情報通信学会技術研究報告  117-  (46(RECONF2017 1-21))  2017
  • 今野陽子, 山下晃弘, 松林圭, 松原良和, 鈴木恵二, 川村秀憲, 井上祐寛  人工知能学会全国大会論文集(CD-ROM)  31st-  2017
  • 小山望海, 武田清賢, 横川誠, 川村秀憲  人工知能学会知識ベースシステム研究会資料  110th-  2017
  • 細川皓平, 川村秀憲  人工知能学会知識ベースシステム研究会資料  110th-  2017
  • 細川皓平, 横山想一郎, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2017-  (MUS-116)  2017
  • 和田雅昭, 松原仁, 鈴木恵二, 長崎健, 安井重哉, 高博昭, 川村秀憲, 山下倫央, 横山想一郎, 塩谷浩之, 岸上順一, 吉野正則, 半澤悟, 長部太郎  日本水産学会北海道支部大会講演要旨集  2017-  2017
  • 平間友大, 横山想一郎, 山下倫央, 川村秀憲, 鈴木恵二, 和田雅昭  日本水産学会北海道支部大会講演要旨集  2017-  2017
  • 平間友大, 横山想一郎, 山下倫央, 川村秀憲, 鈴木恵二, 和田雅昭  情報科学技術フォーラム講演論文集  16th-  2017
  • 小川一太郎, 横山想一郎, 山下倫央, 川村秀憲, 酒徳哲, 柳原正, 田中英明  人工知能学会全国大会論文集(CD-ROM)  31st-  2017
  • 川村 秀憲, 鈴木 恵二  人工知能 : 人工知能学会誌 : journal of the Japanese Society for Artificial Intelligence  31-  (6)  844  -849  2016/11
  • 細川皓平, 川村秀憲  情報処理学会全国大会講演論文集  78th-  (2)  2016
  • 今野陽子, 川村秀憲, 鈴木恵二, 武田清賢, 横川誠, 古川聡子  情報処理学会全国大会講演論文集  78th-  (3)  2016
  • 伊藤千輝, 篠田孝祐, 小野良太, 川村秀憲, 栗原聡  人工知能学会全国大会論文集(CD-ROM)  30th-  2016
  • 今野陽子, 武田清賢, 横川誠, 鈴木恵二, 川村秀憲  情報処理学会研究報告(Web)  2016-  (ICS-182)  2016
  • 江川知樹, 小野良太, 山下倫央, 川村秀憲  情報処理学会研究報告(Web)  2016-  (ICS-182)  2016
  • SONG Shuang, 斎藤一, 向田茂, 川村秀憲  電気・情報関係学会北海道支部連合大会講演論文集(CD-ROM)  2016-  2016
  • 永田紘也, 飯塚博幸, 山本雅人, 鈴木恵二, 川村秀憲  電気・情報関係学会北海道支部連合大会講演論文集(CD-ROM)  2016-  2016
  • 細川皓平, 川村秀憲  電気・情報関係学会北海道支部連合大会講演論文集(CD-ROM)  2016-  2016
  • 永田紘也, 飯塚博幸, 山本雅人, 鈴木恵二, 川村秀憲  情報処理学会研究報告(Web)  2016-  (ICS-184)  2016
  • 宮森勇作, 川村秀憲  情報処理学会研究報告(Web)  2016-  (ICS-184)  2016
  • MA Shabao, 川村秀憲  電気・情報関係学会北海道支部連合大会講演論文集(CD-ROM)  2016-  2016
  • Uefuji Takayuki, Kawamura Hidenori, Suzuki Keiji  情報科学技術フォーラム講演論文集  14-  (3)  563  -564  2015/08/24
  • 塩治龍三朗, 川村秀憲, 鈴木恵二  IPSJ SIG Notes. ICS  2015-  (2)  1  -8  2015/02/23  
    There are many researches about golf shot relating with distance and accuracy concerning golf. However when aiming to have a better score at golf, it is important not only to practice golf shots but also to correctly know the cause of not being able to get a better score and improving them. Furthermore, there are not many researches about this theme. In this paper, we studied a method to analyze golfers play data to improve skill by using golf simulation and a index called Strokes Gained Stats which evaluate golfers every shot.
  • 今野陽子, 川村秀憲, 鈴木恵二  計測自動制御学会北海道支部学術講演会論文集  47th-  2015
  • 宮森勇作, 川村秀憲, 鈴木恵二  人工知能学会全国大会論文集(CD-ROM)  29th-  2015
  • 今野陽子, 川村秀憲, 鈴木恵二  人工知能学会全国大会論文集(CD-ROM)  29th-  2015
  • 源馬亜希, 増田新一郎, 川村隆貴, 伊東秀憲, 大島杏子, 佐伯仁, 渋井敬志, 畑明宏  日本循環器学会関東甲信越地方会(Web)  235th-  2015
  • 山下 晃弘, 中村 拓哉, 川村 秀憲  知識ベースシステム研究会  103-  19  -24  2014/11/20  [Not refereed][Not invited]
  • 今野 陽子, 川村 秀憲, 鈴木 恵二  システム制御情報学会研究発表講演会講演論文集  58-  4p  2014/05/21
  • Hidenori Kawamura, Ryota Ono, Keiji Suzuki  情報処理学会論文誌  55-  (4)  2014/04/15  
    In this paper, we focus on allocating of social service facilities which are operated under the first-come-first-serve rule. In such facilities, users cannot make a reservation in advance. To reduce congestion, it is desirable to adjust a schedule by communication devices. We propose the user-in-the-loop forecasting with the statement-based cost estimate, and apply to two types of facility allocation models, i.e., the theme park scenario and the highway scenario. The computer experiments show that the proposed estimate caused better results in both scenarios to reduce congestion. In particular, the users in the highway scenario could achieve a near user equilibrium situation without any advance experience of the system.------------------------------This is a preprint of an article intended for publication Journal ofInformation Processing(JIP). This preprint should not be cited. Thisarticle should be cited as: Journal of Information Processing Vol.22(2014) No.2 (online)DOI http://dx.doi.org/10.2197/ipsjjip.22.270------------------------------In this paper, we focus on allocating of social service facilities which are operated under the first-come-first-serve rule. In such facilities, users cannot make a reservation in advance. To reduce congestion, it is desirable to adjust a schedule by communication devices. We propose the user-in-the-loop forecasting with the statement-based cost estimate, and apply to two types of facility allocation models, i.e., the theme park scenario and the highway scenario. The computer experiments show that the proposed estimate caused better results in both scenarios to reduce congestion. In particular, the users in the highway scenario could achieve a near user equilibrium situation without any advance experience of the system.------------------------------This is a preprint of an article intended for publication Journal ofInformation Processing(JIP). This preprint should not be cited. Thisarticle should be cited as: Journal of Information Processing Vol.22(2014) No.2 (online)DOI http://dx.doi.org/10.2197/ipsjjip.22.270------------------------------
  • KIN Shofuku, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report. Artificial intelligence and knowledge-based processing  113-  (459)  31  -35  2014/03/03  
    Multi-Agent Simulation (MAS) is efficient for analysis of various social mechanisms. Recently, there are many studies on massive agent model to explain more complex social phenomena. Then, we aim for implementation of large scale simulation model using Repast HPC toolkit, a platform for massive agent model. In this article, we build "Schelling Segregation Model" for spatial model using geospatial data provided OpenStreetMap, an open source project creating a free editable map. In this model, agents are located continuous space , not grid in original. When an agent is "unhappy" and migrate to new location, it costs agents some simulation time depending on distance between old location and new one. This article reports simulation results using Japanese cities and verification result about execution time.
  • 山形 聖志, 川村 秀憲, 鈴木 恵二  知識ベースシステム研究会  101-  13  -18  2014/03/02
  • Shogo Sugawara, Hidenori Kawamura, Keiji Suzuki  IPSJ SIG Notes. ICS  2014-  (4)  1  -8  2014/02/23  
    ゴルフに関する研究は様々な分野において行われてきたが，多くは飛距離や正確性などのスキルに注目しており，クラブやボールの落としどころを選択する方針である戦略についての研究はほとんど行われていない．本研究はゴルフのスコアアップにつながる戦略を獲得するためのフレームワークを開発することを目的とし，ゴルフをボールの位置が確率的に決定されマルコフ決定過程の性質を満たす確率モデルとして定義し，それをもとに期待スコアを最小化する最適化問題を定義して，Q 学習により最適化を行った．最後に，獲得された戦略を用いたシミュレーションを行うことにより，スキルとコースに応じた戦略が獲得されることを示し，フレームワークの応用例として，ゴルフ戦略における攻略ルートの支援ツールであるバーチャルゴルフコーチの機能と支援例について記述した．
  • Ryota Ono, Akihiro Yamashita, Hidenori Kawamura, Keiji Suzuki  IPSJ SIG Notes. ICS  2014-  (3)  1  -6  2014/02/23  [Not refereed][Not invited]
     
    This paper discusses about problems and solutions in event informations recommender system based on user's browsing history. This paper compares five methods, genre based scoring, provider based scoring, popularity based scoring, user-based collaborate filtering, item-based collaborate filtering. As a result, even in event information which user-item relation matrix is sparse, item-based collaborate filtering demonstrates superior performance.
  • 小野良太, 山下晃弘, 平田圭, 川村秀憲, 鈴木恵二  計測自動制御学会北海道支部学術講演会論文集  46th-  2014
  • 今野陽子, 川村秀憲, 鈴木恵二  精密工学会大会学術講演会講演論文集  2014-  2014
  • 山内翔, 川村秀憲, 鈴木恵二  自律分散システム・シンポジウム(CD-ROM)  26th-  2014
  • 宮森勇作, 川村秀憲, 鈴木恵二  情報処理北海道シンポジウム講演論文集  2014-  2014
  • 川村隆貴, 佐伯仁, 伊東秀憲, 増田新一郎, 大島杏子, 渋井敬志, 畑明宏  日本心臓病学会学術集会抄録(CD-ROM)  62nd-  2014
  • 金田俊雄, 渋井敬志, 川村隆貴, 伊藤秀憲, 大島杏子, 増田新一郎, 佐伯仁, 畑明宏  ICUとCCU  38-  2014
  • 辻順平, 川村秀憲, 鈴木恵二  計測自動制御学会北海道支部学術講演会論文集  46th-  2014
  • YAMAUCHI Sho, KAWAMURA Hidenori, SUZUKI Keiji  ロボティクス・メカトロニクス講演会講演概要集  2013-  "2P1  -I04(1)"-"2P1-I04(4)"  2013/05/22  
    Flocking algorithm of multi agent system is robust and disaster tolerant even though agents face obstacles or destructed. These algorithms are modeled to generate complex behavior such as flock of birds and fished by simple distributed rules. In this paper, we focus on applying these mechanism to single robot by assuming that the robot is the set of agents. We extend flocking algorithm to be capable of using in single robot and apply it to dog-shaped robot to convey baggage with other robots. In baggage conveying task, robots must deal with complex effects from its environment, the baggage and other robots.
  • TSUJI Junpei, YAMAUCHI Sho, KAWAMURA Hidenori, SUZUKI Keiji  電子情報通信学会技術研究報告  112-  (420)  49  -52  2013/01/29  
    In this paper, we propose media board software that is free scale and free media constructed on cloud computing platform We assume that the main interface is constructed on tablet computers and smart phones so we can draw pictures as it is on papers and it is able to paste contents such as pictures or photos By preparing the function to express the relationships between information, we call this function landmark and tour here, information in this media board are structured and shared among the users in groups We construct this media board as platform for people to discuss ideas online and generate collaborative ideas Also we try to make this media take place of current browser as new media platform.
  • 今野陽子, 川村秀憲, 鈴木恵二  日本経営工学会秋季研究大会予稿集  2013-  2013
  • 増田新一郎, 佐伯仁, 川村隆貴, 大島杏子, 伊東秀憲, 渋井敬志, 畑明宏  日本循環器学会関東甲信越地方会(Web)  230th-  2013
  • 辻 順平, 川村 秀憲, 鈴木 恵二  ヒューマンインタフェース学会研究報告集  15-  141  -146  2013
  • 辻順平, 川村秀憲, 鈴木恵二  電子情報通信学会技術研究報告  113-  (227(MVE2013 19-31))  2013
  • 川村 秀憲, 山下 晃弘, 鈴木 恵二  観光と情報 : 観光情報学会誌  9-  (1)  29  -38  2013  [Not refereed][Not invited]
  • 川村秀憲, 鈴木恵二  情報処理  53-  (11)  1146  -1152  2012/10/15  [Not refereed][Not invited]
  • 山形聖志, 川村秀憲, 鈴木恵二  情報処理北海道シンポジウム講演論文集  2012-  59  -62  2012/10/06  [Not refereed][Not invited]
  • 菅原翔悟, 川村秀憲, 鈴木恵二  情報処理北海道シンポジウム講演論文集  2012-  131  -138  2012/10/06  [Not refereed][Not invited]
  • 兼平愛弓, 川村秀憲, 鈴木恵二  情報処理北海道シンポジウム講演論文集  2012-  165  -168  2012/10/06  [Not refereed][Not invited]
  • 山内翔, 川村秀憲, 鈴木恵二  日本ロボット学会学術講演会予稿集(CD-ROM)  30th-  ROMBUNNO.1D2-3  2012/09/17  [Not refereed][Not invited]
  • 小野良太, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  22nd-  ROMBUNNO.2A1-3  2012/08/30  [Not refereed][Not invited]
  • 山内翔, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  22nd-  ROMBUNNO.1C2-3  2012/08/30  [Not refereed][Not invited]
  • 菅原翔悟, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  22nd-  ROMBUNNO.2B2-5  2012/08/30  [Not refereed][Not invited]
  • 兼平愛弓, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  22nd-  ROMBUNNO.2B1-3  2012/08/30  [Not refereed][Not invited]
  • 金正福, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  22nd-  ROMBUNNO.1B1-1  2012/08/30  [Not refereed][Not invited]
  • 山形聖志, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  22nd-  ROMBUNNO.2C3-2  2012/08/30  [Not refereed][Not invited]
  • 川村 秀憲, 鈴木 恵二, 山下 晃弘  日本ソフトウェア科学会大会論文集  29-  129  -132  2012/08/22  [Not refereed][Not invited]
  • YAMAUCHI Sho, KAWAMURA Hidenori, SUZUKI Keiji  ロボティクス・メカトロニクス講演会講演概要集  2012-  "2A1  -J03(1)"-"2A1-J03(4)"  2012/05/27  
    Flocking algorithm of multi agent system is robust and disaster tolerant even though agents face obstacles or destructed. In this paper, we focus on applying these mechanism to single humanoid robot by assuming that the robot is the set of agents. We extend flocking algorithm to be capable of using in single robot and apply it to humanoid robot to maintain standing posture.
  • 小野 良太, 川村 秀憲, 鈴木 恵二  人工知能学会全国大会論文集  26-  1  -4  2012
  • 川村秀憲, 鈴木恵二, 山下晃弘  日本ソフトウェア科学会大会講演論文集(CD-ROM)  29th-  2012
  • Tsuji Junpei, Kawamura Hidenori, Suzuki Keiji, Teramae Hiroki  日本理科教育学会北海道支部大会発表予稿集  2012-  (23)  28  -28  2012
  • 小野良太, 川村秀憲, 鈴木恵二  人工知能学会全国大会論文集(CD-ROM)  26th-  ROMBUNNO.3F2-OS-10-5  2012  [Not refereed][Not invited]
  • 川村 秀憲  開発こうほう  0-  (581)  16  -22  2011/12  [Not refereed][Not invited]
     
    Mobile sensor localization technologies attracts attention for the purpose of goods management in large indoor commercial spaces etc. This study uses ZigBee RSSI for localization and aims to clear up the problems on localization using this method in real indoor spaces. This study made a localization system in a labolatory floor and tried to localize a mobile sensor in this floor.
  • 小林佑輔, 川村秀憲, 鈴木恵二  情報処理北海道シンポジウム講演論文集  2011-  25  -32  2011/10/01  [Not refereed][Not invited]
  • 早坂透, 川村秀憲, 鈴木恵二  情報処理北海道シンポジウム講演論文集  2011-  207  -210  2011/10/01  [Not refereed][Not invited]
  • 山内翔, 川村秀憲, 鈴木恵二  情報処理北海道シンポジウム講演論文集  2011-  177  -182  2011/10/01  [Not refereed][Not invited]
  • 菅原翔悟, 川村秀憲, 鈴木恵二  情報処理北海道シンポジウム講演論文集  2011-  13  -18  2011/10/01  [Not refereed][Not invited]
  • 但野友美, 川村秀憲, 鈴木恵二  日本オペレーションズ・リサーチ学会秋季研究発表会アブストラクト集  2011-  268  -269  2011/09/13  [Not refereed][Not invited]
  • 但野 友美, 川村 秀憲, 鈴木 恵二  日本オペレーションズ・リサーチ学会秋季研究発表会アブストラクト集  2011-  (28)  268  -269  2011/09/13  [Not refereed][Not invited]
  • 新井雅也, 川村秀憲, 鈴木恵二  情報科学技術フォーラム  FIT 2011-  483  -484  2011/08/22  [Not refereed][Not invited]
  • 早坂透, 川村秀憲, 鈴木恵二  情報科学技術フォーラム  FIT 2011-  485  -486  2011/08/22  [Not refereed][Not invited]
  • 辻順平, 川村秀憲, 鈴木恵二, 池田剛, 河本満, 幸島明男, 車谷浩一  情報科学技術フォーラム  FIT 2011-  399  -400  2011/08/22  [Not refereed][Not invited]
  • 小野良太, 川村秀憲, 鈴木恵二  情報科学技術フォーラム  FIT 2011-  493  -494  2011/08/22  [Not refereed][Not invited]
  • 但野友美, 川村秀憲, 鈴木恵二  情報科学技術フォーラム  FIT 2011-  413  -414  2011/08/22  [Not refereed][Not invited]
  • 新井 雅也, 川村 秀憲, 鈴木 恵二  知識ベ-スシステム研究会  93-  (0)  9  -12  2011/08/09  [Not refereed][Not invited]
  • Yamauchi Sho, KAWAMURA Hidenori, SUZUKI Keiji  ロボティクス・メカトロニクス講演会講演概要集  2011-  "1A1  -O15(1)"-"1A1-O15(4)"  2011/05/26  
    Effects of body extension and its relationship to learning in robots is not clear even though lots of research have been done. In this paper, to reveal these characteristics, we make simulation robots and attach some rigid bodies to them in order to extend their bodies. Through the interaction in game, extensions increase the average winning percentage of some rule sets. But it does not affect the winning percentage of a specific rule set. Also, each extension has its own collision property and its average collision time is not proportional to the surface area of extensions. We use simulation environment which cause physical effects to robots by using physics engine.
  • KOBAYASHI Yusuke, KAWAMURA Hidenori, SUZUKI Keiji  ロボティクス・メカトロニクス講演会講演概要集  2011-  "1A1  -M05(1)"-"1A1-M05(4)"  2011/05/26  
    Recently, multiagent systems has attracted much attention. RoboCup Soccer Simulation is treated as a test bed of these. In real soccer, the analysis of games in terms of team behavior has been studied, however, it has not been done in RoboCup Soccer Simulation. In this study, we aim to facilitate the analysis of the team behavior and to clarify the involvement of the team possession type in result of games in RoboCup Soccer Simulation. In particular, we construct a method of detecting counter attack, one of team possession type and we analyze the log files of games. After considering the feature quantities to detect, we detect counter attack using support vector machine based on four feature quantities. As a result, this detector can detect in 77%. Using this detector will reduce the burden of check the log data in visual.
  • MATSUO JUN, KAWAMURA HIDENORI, SUZUKI KEIJI  情報処理学会研究報告(CD-ROM)  2010-  (6)  ROMBUNNO.ICS-162,NO.4  2011/04/15  [Not refereed][Not invited]
  • ONO RYOTA, KAWAMURA HIDENORI, SUZUKI KEIJI  情報処理学会研究報告(CD-ROM)  2010-  (6)  ROMBUNNO.ICS-162,NO.1  2011/04/15  [Not refereed][Not invited]
  • 中野 航, 川村 秀憲, 鈴木 恵二  知識ベ-スシステム研究会  92-  (0)  23  -26  2011/03/07  [Not refereed][Not invited]
  • 辻 順平, 川村 秀憲, 鈴木 恵二  知識ベ-スシステム研究会  92-  (0)  27  -32  2011/03/07  [Not refereed][Not invited]
  • 平田圭, 山下晃弘, 新井雅也, 小野良太, 川村秀憲, 鈴木恵二  人工知能学会知識ベースシステム研究会資料  92nd-  33  -38  2011/03/03  [Not refereed][Not invited]
  • 森翔平, 川村秀憲, 鈴木恵二  電子情報通信学会技術研究報告  110-  (462(AI2010 58-63))  13  -16  2011/03/01  [Not refereed][Not invited]
  • TADANO YUMI, KAWAMURA HIDENORI, SUZUKI KEIJI  電子情報通信学会技術研究報告  110-  (462(AI2010 58-63))  27  -31  2011/03/01  [Not refereed][Not invited]
     
    The analytic hierarchy process (AHP) proposed by T.L.Saaty is a method for decision making that takes into consideration uncertain situations or multiple evaluation criteria. In AHP, a decision maker gives values of pairwise comparisons between evaluation criteria and alternatives. Therefore the comparisons of all pairs are difficult when evaluating many alternatives. In this study, we propose a new method that named "comparison support method" for evaluating many alternatives when decision maker needs to decide the highest priority alternative. The comparison support method stops pairwise comparisons when only one solution, the highest priority alternative, is found even if all comparisons aren't compared.
  • Ryota Ono, Hidenori Kawamura, Keiji Suzuki  IPSJ SIG Notes. ICS  2011-  (1)  1  -6  2011/03/01  [Not refereed][Not invited]
     
    To deal with utilization method of goods by more than one person more applicative, this paper proposes Service Infrastructure Use Problem, and Social Utilization as a desirable condition of society on Service Infrastructure Use Problem. To make sure Social Utilization whether realizable or not, this paper formulates Service Infrastructure TSP as a specific model of Service Infrastructure Use Problem and an extended TSP model. Lastly, this paper does experiment simulation and verifies that.
  • Jun Matsuo, Hidenori Kawamura, Keiji Suzuki  IPSJ SIG Notes. ICS  2011-  (4)  1  -6  2011/03/01  [Not refereed][Not invited]
     
    Twitter, a popular microblogging tool has seen a lot of growth since it launched in October 2006. Now, Twitter is used to show an advertisement with a comment bookmarked URL. We suggest the model of delivery advertisements to show as many people as possible. In this model, the delivery service gives users an advertising which is provided a client. To realize the model, we calculate the click-through count by Twitter comment and advertisement article. In the experiment, we examine correlation between the calculated click-through count and the actual one.
  • MORI Shohei, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report. Artificial intelligence and knowledge-based processing  110-  (462)  13  -16  2011/03/01  [Not refereed][Not invited]
     
    本研究では新聞記事において本文を構成する単語と見出しを構成する単語の調査を行う.新聞記事は見出し,リード,本文から構成され逆三角形の構造をとる.よって見出しは記事の内容を簡潔に表す重要な役目を持つ.ここでは見出しには本文中では重要ではない平易な単語が入っていると考え,その特徴を調査する.
  • FUKUI Tomoko, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report. Artificial intelligence and knowledge-based processing  110-  (462)  17  -20  2011/03/01  [Not refereed][Not invited]
     
    In these days, the internet, chat and weblog have lowered our barriers to the posting comments and information on Web sites. Because they are easy to use, their users are increasing yearly. These comments and information involve user's opinions, impressions and evaluations of certain objects, so there is a need for extraction of valuable information from these comments posted by many people. But it is harder to analyze those free descriptions quantitatively than to analyze numerical data. In this paper, we propose an estimation approach by using Rakuten GORA reviews. It estimates 5-point sc...
  • TADANO Yumi, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report. Artificial intelligence and knowledge-based processing  110-  (462)  27  -31  2011/03/01  [Not refereed][Not invited]
     
    The analytic hierarchy process (AHP) proposed by T.L.Saaty is a method for decision making that takes into consideration uncertain situations or multiple evaluation criteria. In AHP, a decision maker gives values of pairwise comparisons between evaluation criteria and alternatives. Therefore the comparisons of all pairs are difficult when evaluating many alternatives. In this study, we propose a new method that named "comparison support method" for evaluating many alternatives when decision maker needs to decide the highest priority alternative. The comparison support method stops pairwise ...
  • 村上 嘉代子, 川村 秀憲, 鈴木 恵二  特別教育・研究報告集  2011-  231  -234  2011
  • 小野良太, 川村秀憲, 鈴木恵二  人工知能学会全国大会論文集(CD-ROM)  25th-  ROMBUNNO.3J2-OS10-1  2011  [Not refereed][Not invited]
  • 小林佑輔, 川村秀憲, 鈴木恵二  人工知能学会AIチャレンジ研究会(Web)  33rd-  WEB ONLY B101-9  2011  [Not refereed][Not invited]
  • 関谷章吾, 川村秀憲, 鈴木恵二  日本機械学会ロボティクス・メカトロニクス講演会講演論文集(CD-ROM)  2010-  ROMBUNNO.1P1-D25  2010/06/13  [Not refereed][Not invited]
  • 木村卓哉, 川村秀憲, 鈴木恵二  日本機械学会ロボティクス・メカトロニクス講演会講演論文集(CD-ROM)  2010-  ROMBUNNO.1A2-C19  2010/06/13  [Not refereed][Not invited]
  • ONO RYOTA, KAWAMURA HIDENORI, SUZUKI KEIJI  情報処理学会研究報告(CD-ROM)  2009-  (6)  ROMBUNNO.ICS-158,7  2010/04/15  [Not refereed][Not invited]
  • UMEMOTO MASAYUKI, KAWAMURA HIDENORI, SUZUKI KEIJI  情報処理学会研究報告(CD-ROM)  2009-  (6)  ROMBUNNO.ICS-158,11  2010/04/15  [Not refereed][Not invited]
  • 辻 順平, 川村 秀憲, 鈴木 恵二  情報処理学会研究報告  2009-  (6)  1  -8  2010/04
  • 辻 順平, 川村 秀憲, 鈴木 恵二  電子情報通信学会技術研究報告  109-  (474)  529  -536  2010/03/26  [Not refereed][Not invited]
  • TSUJI JUMPEI, TSUJI JUMPEI, KAWAMURA HIDENORI, KAWAMURA HIDENORI, SUZUKI KEIJI, SUZUKI KEIJI, IKEDA TAKESHI, IKEDA TAKESHI, SASHIMA AKIO, SASHIMA AKIO, KURUMATANI KOICHI, KURUMATANI KOICHI  電子情報通信学会技術研究報告  109-  (474(CPSY2009 81-96))  529  -536  2010/03/19  [Not refereed][Not invited]
  • 辻 順平, 川村 秀憲, 鈴木 恵二, 池田 剛, 幸島 明男, 車谷 浩一  情報処理学会研究報告. EMB, 組込みシステム  2010-  (74)  1  -8  2010/03/19  [Not refereed][Not invited]
     
    大型商業施設などの屋内空間における,物品・従業員管理,顧客の動線情報の獲得を目的として,センサネットワークにおける移動センサ測位技術が注目を集めている.本研究では,低コスト・低消費電力を特徴とした ZigBee の RSSI に基づく測位手法を用いて,実環境での精度が保証された測位システム構築に向け,その課題を明らかにすることを目的とする.研究室における端末測位環境を構築し,環境を自由に移動する人の測位実験を行った.
  • Junpei Tsuji, Hidenori Kawamura, Keiji Suzuki, Takeshi Ikeda, Akio Sashima, Koichi Kurumatani  IPSJ SIG technical reports  2010-  (74)  1  -8  2010/03/19  [Not refereed][Not invited]
     
    Mobile sensor localization technologies attracts attention for the purpose of goods management in large indoor commercial spaces etc. This study uses ZigBee RSSI for localization and aims to clear up the problems on localization using this method in real indoor spaces. This study made a localization system in a labolatory floor and tried to localize a mobile sensor in this floor.
  • Junpei Tsuji, Hidenori Kawamura, Keiji Suzuki, Takeshi Ikeda, Akio Sashima, Koichi Kurumatani  情報処理学会研究報告. UBI, [ユビキタスコンピューティングシステム]  2010-  (74)  1  -8  2010/03/19  [Not refereed][Not invited]
     
    Mobile sensor localization technologies attracts attention for the purpose of goods management in large indoor commercial spaces etc. This study uses ZigBee RSSI for localization and aims to clear up the problems on localization using this method in real indoor spaces. This study made a localization system in a labolatory floor and tried to localize a mobile sensor in this floor.
  • 松尾潤, 松尾潤, 辻順平, 辻順平, 川村秀憲, 川村秀憲, 鈴木恵二, 鈴木恵二, 池田剛, 池田剛, 幸島明男, 幸島明男, 車谷浩一, 車谷浩一  情報処理学会全国大会講演論文集  72nd-  (3)  3.341-3.342  2010/03/08  [Not refereed][Not invited]
  • 但野友美, 川村秀憲, 鈴木恵二, 大内東  情報処理学会全国大会講演論文集  72nd-  (1)  1.305-1.306  2010/03/08  [Not refereed][Not invited]
  • Tadano Yumi, Kawamura Hidenori, Suzuki Keiji, Ohuchi Azuma  全国大会講演論文集  72-  (1)  "1  -305"-"1-306"  2010/03/08  [Not refereed][Not invited]
     
    人間の主観的な勘や経験等を数値化した意思決定支援手法にSaatyのAnalytic Hierarchy Process (AHP)がある.AHPは問題を階層構造に分解し,各レベルの項目間で親要素に対する一対比較を行い,全体の総合評価を算出する.そのため,代替案数が多くなると一対比較の総数が増え,全ての対を比較することが困難となる問題がある.本研究では最も良い代替案を一つ求める場合に注目し,一対比較が全て終わらなくても解が一意に求まる場合,それ以上の入力を省略することで,問題を解決する方法として比較支援法を提案する.入力数における解が一意に求まる入力パターン数を調査する実験を行った結果,全入力パターンの33%は従来の半数の一対比較を行った時点で解が求まる可能性があることが明らかとなった.
  • Matsuo Jun, Tsuji Junpei, Kawamura Hidenori, Suzuki Keiji, Ikeda Takeshi, Sashima Akio, Kurumatani Koichi  全国大会講演論文集  72-  (3)  "3  -341"-"3-342"  2010/03/08  [Not refereed][Not invited]
     
    我々の身近にある屋内空間において,空間内を利用するユーザの有する携帯端末が,空間内に構築された無線センサネットワークを介して,サーバと通信することで,屋内のナビゲーションや混雑緩和など様々なサービスの実現を考える.このようなシステムを実際に運用することを考えたとき,ネットワークの構成は大きな問題になる.本研究では,用いるセンサネットワークとしてZigBeeを採用し,携帯端末の台数を変えたときに生じる,ZigBeeルータのパケットロス率について検証を行った.
  • 松尾 潤, 川村 秀憲, 鈴木 恵二  知識ベ-スシステム研究会  88-  (0)  9  -12  2010/03/02  [Not refereed][Not invited]
  • 辻 順平, 川村 秀憲, 鈴木 恵二  知識ベ-スシステム研究会  88-  (0)  13  -18  2010/03/02  [Not refereed][Not invited]
  • 新井 雅也, 川村 秀憲, 鈴木 恵二  知識ベ-スシステム研究会  88-  (0)  19  -25  2010/03/02  [Not refereed][Not invited]
  • ONO RYOTA, KAWAMURA HIDENORI, SUZUKI KEIJI  情報処理学会研究報告. ICS, [知能と複雑系]  158-  (0)  1  -8  2010/03/01  [Not refereed][Not invited]
     
    複数の独立なサブシステムが，限られた共有資源の利用を最適化しようとする共有資源の利用問題を TSP の理論を用いてモデル化し，その意義と有用性について述べる．また，このような問題に対し効率的に解を求める社会的利用の例として行動調整アルゴリズムを提案する．さらに，小規模な例題を解くことでこの問題の解空間の構造をゲーム理論の観点から分析し，行動調整アルゴリズムによって得られる解の効率性について検証する．Model shared resource using problem that independent subsystems want to optimize limited shared resource on TSP theory and discuss this model's meaning and availability. And, propose the Action Coordinate Algorithm as an example of social utilization that can effectively provide good answers. In addition, analyze structures of solution spaces in this problem through solving small examples, and verify efficiency answers provided by the Action Coordinate Algorithm.
  • UMEMOTO MASAYUKI, KAWAMURA HIDENORI, SUZUKI KEIJI  情報処理学会研究報告. ICS, [知能と複雑系]  158-  (0)  1  -6  2010/03/01  [Not refereed][Not invited]
     
    無人へリコプタはホバリング飛行や垂直離着陸といったヘリコプタ特有の飛行特性を有し，農薬散布や火山での観測といった用途に実用化され，開発が進められている．しかし，広域な作業範囲や複雑なタスクに対処する為には，単一機体での作業では限界があり，複数機体で作業する事で作業の効率化や耐障害性の向上が期待される．本研究では，自律制御された小型無人ヘリコプタが相互に通信し，取得したデータを共有・統合するシステムをマルチロボットヘリコプタシステムと定義し，その適用例として，広域を並列的に撮影する航空写真撮影や遭難者救助といった例が考えられる．ここでは遭難者救助，特に時間的制約が厳しい雪崩遭難者救助に着目し，雪崩遭難者救助に要する時間を短縮する事を目的とする．雪崩遭難者の携帯したビーコンをマルチロボットヘリコプタシステムを用いる事で，効率的に探索するフライトプランを検討した．This paper describes beacon search algorithm using multi robot helicopter. Multi robot helicopter is defined as multiple autonomous unmanned Helicopters using ad-hoc network. Unmanned helicopter has several abilities such as hovering and vertical takeoff and landing, Unmanned helicopter is becoming popular in actual applications such as search, recue and photographing. Avalanche rescue is hard time constrained in particular. The time to find and extricate victims is most crucial: once buried by an avalanche, survival chances drop dramatically after the first 15 min. So We apply Multi robot helicopter system to Avalanche rescue. We investigate system configuration, and design hardware configuration. Approach to autonomous unmanned helicopter, develop flight simulator, design a flight controller. investigate beacon search algorithm in simulator, The experimental results show the effectiveness of algorithm using Multi Robot Helicopter.
  • KATAYAMA RYO, KAWAMURA HIDENORI, SUZUKI KEIJI  電子情報通信学会技術研究報告  109-  (439(AI2009 42-52))  11  -16  2010/02/22  [Not refereed][Not invited]
     
    Recently, the quest ion-answer (QA) site, such as Oshiete! goo Yahoo tiebukuro are in widespread use in our life. QA site is a place where anyone can post questions and answers and share knowledge among them. It gets more important as a flexible information search. In an existing QA site, it is necessary for repliers to retrieve attractive questions for themselves. Therefore we seek to recommend appropriate questions for repliers. In this paper, as a first step, we analyze questions which repliers answered, with a history data. Specifically we propose distance between a question and a history data, and compare the distance between questions which repliers answered and those else.
  • 辻順平, 辻順平, 川村秀憲, 川村秀憲, 鈴木恵二, 鈴木恵二, 池田剛, 池田剛, 幸島明男, 幸島明男, 車谷浩一, 車谷浩一  人工知能学会知識ベースシステム研究会資料  88th-  13  -18  2010/02/22  [Not refereed][Not invited]
  • TADANO YUMI, KAWAMURA HIDENORI, SUZUKI KEIJI  電子情報通信学会技術研究報告  109-  (439(AI2009 42-52))  59  -63  2010/02/22  [Not refereed][Not invited]
     
    The analytic hierarchy process (AHP) proposed by T.L.Saaty is a method for decision making that takes into consideration uncertain situations or multiple evaluation criteria. In AHP, a decision maker gives values of pairwise comparisons between evaluation criteria and alternatives. Therefore the comparisons of all pairs are difficult when evaluating many alternatives. In this study, we propose a new method that named "comparison support method" for evaluating many alternatives when decision maker needs to decide the highest priority alternative. The comparison support method stops pairwise comparisons when only one solution, the highest priority alternative, is found even if all comparisons aren't compared.
  • GODO YOSHIYUKI, HATA MASAYUKI, KAWAMURA HIDENORI, SUZUKI KEIJI  電子情報通信学会技術研究報告  109-  (439(AI2009 42-52))  1  -5  2010/02/22  [Not refereed][Not invited]
     
    Magnification of Embedded system is developed in recent years, and management is becoming difficult. Therefore self-management function is desired. The architecture which makes function management in removal of an element self-controlled is proposed in the distributed network type Embedded system by this research. As approach, Autonomic Computing Architecture, the SQL parser function is expanded. A prototype is made and contrived architecture is inspected.
  • EBATA YUSUKE, KAWAMURA HIDENORI, SUZUKI KEIJI  電子情報通信学会技術研究報告  109-  (439(AI2009 42-52))  7  -10  2010/02/22  [Not refereed][Not invited]
     
    These days video sharing site such as YouTube is being popular. With that, studies using comments of videos are also paid much attention. In this study, we show the related videos for which a comment of videos was used. Specifically, we regarded all comments of one animation as one document, and calculated feature vector on every document. We used the feature vector to show as related videos by calculating the similarity with the other videos.
  • YAMASHITA Akihiro, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report  109-  (439)  29  -34  2010/02/22  [Not refereed][Not invited]
     
    Collaborative filtering is one of the most popular and effective recommendation algorithms based on user-user or item-item similarity. Generally, distance metrics such as Pearson's correlation coefficient are used as the similarity. Although, effectiveness of similarity computation method was widely discussed from various perspectives, there are few considerations of computation methods for optimal similarity in collaborative filtering. In this research, similarity optimization problem were formulated by defining similarities between a active user and the other users as a vector variable. Then, a quasi-optimal solution was obtained and it was compared with Pearson's correlation coefficient. Additionally, we propose and evaluate similarity computation method based on optimization.
  • GODO Yoshiyuki, HATA Masayuki, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report. Artificial intelligence and knowledge-based processing  109-  (439)  1  -5  2010/02/22  [Not refereed][Not invited]
     
    Magnification of Embedded system is developed in recent years, and management is becoming difficult. Therefore self-management function is desired. The architecture which makes function management in removal of an element self-controlled is proposed in the distributed network type Embedded system by this research. As approach, Autonomic Computing Architecture, the SQL parser function is expanded. A prototype is made and contrived architecture is inspected.
  • EBATA Yusuke, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report. Artificial intelligence and knowledge-based processing  109-  (439)  7  -10  2010/02/22  [Not refereed][Not invited]
     
    These days video sharing site such as YouTube is being popular. With that, studies using comments of videos are also paid much attention. In this study, we show the related videos for which a comment of videos was used. Specifically, we regarded all comments of one animation as one document, and calculated feature vector on every document. We used the feature vector to show as related videos by calculating the similarity with the other videos.
  • KATAYAMA Ryo, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report. Artificial intelligence and knowledge-based processing  109-  (439)  11  -16  2010/02/22  [Not refereed][Not invited]
     
    Recently, the quest ion-answer (QA) site, such as Oshiete! goo Yahoo tiebukuro are in widespread use in our life. QA site is a place where anyone can post questions and answers and share knowledge among them. It gets more important as a flexible information search. In an existing QA site, it is necessary for repliers to retrieve attractive questions for themselves. Therefore we seek to recommend appropriate questions for repliers. In this paper, as a first step, we analyze questions which repliers answered, with a history data. Specifically we propose distance between a question and a histo...
  • YAMASHITA Akihiro, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report  109-  (439)  29  -34  2010/02/22  [Not refereed][Not invited]
     
    Collaborative filtering is one of the most popular and effective recommendation algorithms based on user-user or item-item similarity. Generally, distance metrics such as Pearson's correlation coefficient are used as the similarity. Although, effectiveness of similarity computation method was widely discussed from various perspectives, there are few considerations of computation methods for optimal similarity in collaborative filtering. In this research, similarity optimization problem were formulated by defining similarities between a active user and the other users as a vector variable. Then, a quasi-optimal solution was obtained and it was compared with Pearson's correlation coefficient. Additionally, we propose and evaluate similarity computation method based on optimization.
  • TADANO Yumi, KAWAMURA Hidenori, SUZUKI Keiji  IEICE technical report. Artificial intelligence and knowledge-based processing  109-  (439)  59  -63  2010/02/22  [Not refereed][Not invited]
     
    The analytic hierarchy process (AHP) proposed by T.L.Saaty is a method for decision making that takes into consideration uncertain situations or multiple evaluation criteria. In AHP, a decision maker gives values of pairwise comparisons between evaluation criteria and alternatives. Therefore the comparisons of all pairs are difficult when evaluating many alternatives. In this study, we propose a new method that named "comparison support method" for evaluating many alternatives when decision maker needs to decide the highest priority alternative. The comparison support method stops pairwise ...
  • 小野良太, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  20th-  ROMBUNNO.S1-1-2  2010  [Not refereed][Not invited]
  • 但野友美, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  20th-  ROMBUNNO.S4-4-4  2010  [Not refereed][Not invited]
  • 新井雅也, 川村秀憲, 鈴木恵二  人工知能学会全国大会論文集(CD-ROM)  24th-  ROMBUNNO.3E3-2  2010  [Not refereed][Not invited]
  • 新井雅也, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  20th-  ROMBUNNO.S1-1-5  2010  [Not refereed][Not invited]
  • 関谷章吾, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム(CD-ROM)  20th-  ROMBUNNO.S3-1-4  2010  [Not refereed][Not invited]
  • 小野良太, 川村秀憲, 鈴木恵二  人工知能学会全国大会論文集(CD-ROM)  24th-  ROMBUNNO.2I1-OS5-8  2010  [Not refereed][Not invited]
  • KIMURA Takuya, KAWAMURA Hidenori, SUZUKI Keiji  ロボティクス・メカトロニクス講演会講演概要集  2010-  (0)  "1A2  -C19(1)"-"1A2-C19(4)"  2010  [Not refereed][Not invited]
     
    In this paper, we propose a method of estimation position with camera for autonomous landing system of small helicopter. Since the small helicopter has limited payload, it can't put a lot of sensors or heavy sensors. In this study, The camera putting on the helicopter is used as the acquisition device of the position information. We constructed the system that in real time estimating the position of the helicopter, especially the position of the direction of height by using the camera and the landmark. We experimented and considered whether the system was able to be used to control the heli...
  • SEKIYA Shogo, KAWAMURA Hidenori, SUZUKI Keiji  ロボティクス・メカトロニクス講演会講演概要集  2010-  (0)  "1P1  -D25(1)"-"1P1-D25(4)"  2010  [Not refereed][Not invited]
     
    We want to work humanoid robot instead of the person in the sea area. In this paper, for purpose extending applied area of humanoid robot, we aim at the adjustment of a humanoid robot to an underwater area. The property of the action in the water is different compared with the property of the action in the land because the influence of resistance from the wave. Therefore, We think that we should change the action between land and water. As a basic research, land or water is detected with the sensor. As a result, autonomous behavior switching is acquired to humanoid robot that put on wet suit.
  • Adaptive Fusion Method for User-based and Item-based Collaborative Filtering
    The Fifth International Workshop on Emergent Intelligence in Networked Agents (WEIN2010)  1  -8  2010  [Not refereed][Not invited]
  • Interactive Comparison Support with Comparison Pattern Search for Analytic Hierarchy Process
    24th European Conference on Operational Rsearch, Lisbon  255  -255  2010  [Not refereed][Not invited]
  • Estimation of ZigBee’s RSSI fluctuated by Crowd Behavior in Indoor Space
    Proceedings of SICE Annual Conference 2010 in Taiwan  cd-rom  2010  [Not refereed][Not invited]
  • Junpei Tsuji, Hidenori Kawamura, Keiji Suzuki, Takeshi Ikeda, Akio Sashima, Koichi Kurumatani  IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010)  1115  -1120  2010  [Not refereed][Not invited]
     
    Highly-functional mobile devices, such a smart phone, have appeared. Location based services of the mobile devices are assimilated in a variety of ways. Then, Indoor localization sensor is necessary to access the location based services seamlessly. This paper researched the performance of indoor localization with ZigBee based particle filter. This paper showed this method can localize a resting target within 2.0 meter accuracy and can localize a moving target with an area levels localizarion. ZigBee based particle filter can be one of some options for location based services in indoor spaces.
  • Neural Network based Estimation of Crowd Behavior using RSSI in Indoor Space
    The 14th Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES2010)  cd-rom  2010  [Not refereed][Not invited]
  • Game Analysis and Modeling the Social Utilization of Shared Resources Based on Traveling Salesperson Problem
    The 14th Asia Pacific Symposium on Intelligent and Evolutionary Systems(IES2010)  cd-rom  2010  [Not refereed][Not invited]
  • Performance evaluation of private cloud computing with Eucalyptus
    Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems (SCIS&ISIS2010)  SA-C1-3  2010  [Not refereed][Not invited]
  • Parameter Estimation Method Based on Simulated Recommendation Process for Collaborative Filtering
    Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems (SCIS&ISIS2010)  FR-C4-4  2010  [Not refereed][Not invited]
  • 梅本雅之, 川村秀憲, 鈴木恵二  計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)  2009-  ROMBUNNO.1B1-1  2009/11/24  [Not refereed][Not invited]
  • 平田圭, 川村秀憲, 鈴木恵二  計測自動制御学会システム・情報部門学術講演会講演論文集(CD-ROM)  2009-  ROMBUNNO.1B1-2  2009/11/24  [Not refereed][Not invited]
  • 但野友美, 川村秀憲, 鈴木恵二, 大内東  インテリジェント・システム・シンポジウム講演論文集  19th-  (CD-ROM)  ROMBUNNO.B4,1  2009/09/17  [Not refereed][Not invited]
  • YE Tao, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム講演論文集  19th-  (CD-ROM)  ROMBUNNO.C5,2  2009/09/17  [Not refereed][Not invited]
  • 山下晃弘, 山下晃弘, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム講演論文集  19th-  (CD-ROM)  ROMBUNNO.B4,2  2009/09/17  [Not refereed][Not invited]
  • 松村有祐, 川村秀憲, 鈴木恵二, 松村有祐, 川村秀憲, 鈴木恵二  インテリジェント・システム・シンポジウム講演論文集  19th-  (CD-ROM)  ROMBUNNO.B5,1  2009/09/17  [Not refereed][Not invited]
  • 松尾潤, 川村秀憲, 鈴木恵二, 池田剛, 幸島明男, 車谷浩一, 松尾潤, 川村秀憲, 鈴木恵二, 池田剛, 幸島明男, 車谷浩一  インテリジェント・システム・シンポジウム講演論文集  19th-  (CD-ROM)  ROMBUNNO.B3,3  2009/09/17  [Not refereed][Not invited]
  • 辻順平, 川村秀憲, 鈴木恵二, 池田剛, 幸島明男, 車谷浩一, 辻順平, 川村秀憲, 鈴木恵二, 池田剛, 幸島明男, 車谷浩一  インテリジェント・システム・シンポジウム講演論文集  19th-  (CD-ROM)  ROMBUNNO.B3,4  2009/09/17  [Not refereed][Not invited]
  • Kawamura Hidenori  Journal of Japanese Society for Artificial Intelligence  24-  (4)  568  -571  2009/07/01  [Not refereed][Not invited]
  • 山下 晃弘, 川村 秀憲, 飯塚 博幸, 大内 東  情報処理学会論文誌数理モデル化と応用（TOM）  2-  (2)  47  -57  2009/03/27  [Not refereed][Not invited]
     
    The problem of information overload spreading across the Internet has been causing serious inefficiency in browsing and searching for information. As a way to overcome the problem, the recommender systems are recently used in many E-commerce sites. Many algorithms have been proposed to improve the accuracy of recommendation based on user ratings. The relation between recommender systems and users is rather interactive in the sense that recommendations decides which items are recommended to users and the results of ratings by users will affect the next recommendations. However, conventional studies have not considered the interactive aspects so much. Therefore, our aim of this paper is to propose a new evaluation model using multiagent modeling where the recommender system and agents (as users) interacts with each other. The properties of typical recommendation algorithms such as user-based and itembased collaborative filtering will be analyzed with our proposed model. Our results also suggest the possibilities to propose a novel and effective recommendation algorithm.
  • 寺西俊樹, 川村秀憲, 鈴木恵二, 大内東  情報処理学会全国大会講演論文集  71st-  (1)  1.389-1.390  2009/03/10  [Not refereed][Not invited]
  • Teranishi Toshiki, Kawamura Hidenori, Suzuki Keiji, Ohuchi Azuma  全国大会講演論文集  71-  (1)  "1  -389"-"1-390"  2009/03/10  [Not refereed][Not invited]
  • YAMASHITA AKIHIRO, YAMASHITA AKIHIRO, KAWAMURA HIDENORI, SUZUKI KEIJI, OUCHI AZUMA  人工知能学会知識ベースシステム研究会資料  85th-  107  -112  2009/02/25  [Not refereed][Not invited]
  • YAMASHITA Akihiro, KAWAMURA Hidenori, SUZUKI Keiji, OHUCHI Azuma  IPSJ SIG Notes. ICS  154-  (16)  105  -110  2009/02/23  [Not refereed][Not invited]
     
    In many E-commerce sites, recommender systems, which provide personalized recommendation from among a large number of items, are recently introduced. Collaborative filtering (CF) is one of the most successful algorithms which provide recommendations using ratings of items by the users. There are two approaches such as user-based CF and item-based CF. Additionally an algorithm which improves recommendation accuracy by unifying both of user-based CF and item-based CF was proposed. In the algorithm, a weight for unifying is a constant which obtained empirically. However, because the optimal weight for unifying is actually different by the situation, the algorithm should estimate an appropriate weight dynamically, and use it. In this research, we propose an approach for estimation of the appropriate weight based on collected ratings. Moreover, we discussed the effectiveness by using Movie Lens data.
  • YAMASHITA Akihiro, KAWAMURA Hidenori, SUZUKI Keiji, OHUCHI Azuma  IEICE technical report  108-  (456)  105  -110  2009/02/23  [Not refereed][Not invited]
     
    In many E-commerce sites, recommender systems, which provide personalized recommendation from among a large number of items, are recently introduced. Collaborative filtering (CF) is one of the most successful algorithms which provide recommendations using ratings of items by the users. There are two approaches such as user-based CF and item-based CF. Additionally an algorithm which improves recommendation accuracy by unifying both of user-based CF and item-based CF was proposed. In the algorithm, a weight for unifying is a constant which obtained empirically. However, because the optimal weight for unifying is actually different by the situation, the algorithm should estimate an appropriate weight dynamically, and use it. In this research, we propose an approach for estimation of the appropriate weight based on collected ratings. Moreover, we discussed the effectiveness by using Movie Lens data.
  • 山下晃弘, 山下晃弘, 川村秀憲, 飯塚博幸, 大内東  情報処理学会論文誌トランザクション(CD-ROM)  2008-  (2)  2009
  • 川村 秀憲, 伊藤 直哉, 鈴木 恵二  観光と情報  5-  (1)  101  -104  2009  [Not refereed][Not invited]
  • Indoor Positioning Method Based on RSSI Pre-Observation with ZigBee Network
    13th Asia Pacific Symposium on Intelligent and Evolutionary Systems  CD-ROM  2009  [Not refereed][Not invited]
  • The Method for Evaluating Many Alternatives of Analytic Hierarchy Process
    The 20th National Conference of Australian Society for Operations Research  120  2009  [Not refereed][Not invited]
  • Termination Process of the Analytic Hierarchy Process
    13th Asia Pacific Symposium on Intelligent and Evolutionary Systems  CD-ROM  2009  [Not refereed][Not invited]
  • 高谷敏彦, 川村秀憲, 山本雅人, 大内東  Ricoh Tech Rep  (34)  119  -130  2008/12/01  [Not refereed][Not invited]
  • 川村 秀憲, 伊藤 直哉, 鈴木 恵二, 大内 東  日本オペレーションズ・リサーチ学会秋季研究発表会アブストラクト集  2008-  (0)  136  -137  2008/09/10  [Not refereed][Not invited]
  • 丸山加奈, 大内東, 川村秀憲  情報処理学会全国大会講演論文集  70th-  (4)  4.455-4.456  2008/03/13  [Not refereed][Not invited]
  • 丸山 加奈, 大内 東, 川村 秀憲  全国大会講演論文集  70-  (4)  "4  -455"-"4-456"  2008/03/13  [Not refereed][Not invited]
  • SAKAMOTO HIRONORI, OUCHI AZUMA, KAWAMURA HIDENORI  情報処理学会研究報告  2008-  (28(GI-19))  33  -36  2008/03/12  [Not refereed][Not invited]
     
    In recent years, the number of Internet user is increased as the personal computer and the portable terminal spread. So the cases used Social Networking Service or Consumer Generated Media, etc. as an information exchange and a communication means have risen. A lot of research such as the community analysis and making to visible from the structure analysis, plot out a new mechanism and business model, information recommendation, have already been done to those media. However there are few researches that stares at the future like forecast and analyze the appearance of the development of new media. In this research, we tried to analyze how the knowledge accumulate on user participation media.
  • UMEMOTO MASAYUKI, NISHIOKA RYOTA, YAMAGATA YOSHIFUMI, KAWAMURA HIDENORI, OUCHI AZUMA, TAKAYA TOSHIHIKO  情報処理学会研究報告  2008-  (26(EC-9))  37  -42  2008/03/07  [Not refereed][Not invited]
     
    Autonomous Flying Object (AFO) is an autonomously controlled indoor robot that is developed to realize autonomous flights for an entertainment. The balloon robot can fly freely in a three dimensional space. In this paper, the tag game by two robots is concerned as an application of the entertainment flights. The complexity or highly technical strategy of behaviors for the game can be an important factor for the entertainment. The combination of genetic algorithm and neural networks is used to co-evolve the behavioral strategies for the robots, The complexity of the evolved behaviors and techniques is investigated in response to the space and motor characteristics.
  • Umemoto Masayuki, Nishioka Ryota, Yamagata Yoshihumi, Kawamura Hidenori, Ohuchi Azuma, Takaya Toshihiko  IPSJ SIG technical reports  2008-  (26)  37  -42  2008/03/07  [Not refereed][Not invited]
     
    Autonomous Flying Object (AFO) is an autonomously controlled indoor robot that is developed to realize autonomous flights for an entertainment. The balloon robot can fly freely in a three dimensional space. In this paper, the tag game by two robots is concerned as an application of the entertainment flights. The complexity or highly technical strategy of behaviors for the game can be an important factor for the entertainment. The combination of genetic algorithm and neural networks is used to co-evolve the behavioral strategies for the robots, The complexity of the evolved behaviors and tec...
  • NAKABAYASHI YUTA, NISHIOKA RYOTA, YAMAGATA YOSHIFUMI, KAWAMURA HIDENORI, OHUCHI AZUMA, TAKAYA TOSHIHIKO  IPSJ SIG Notes. ICS  2008-  (20)  91  -96  2008/03/05  [Not refereed][Not invited]
     
    Autonomous indoor balloon robots cannot have enough battery for long flight, because they have limitation of payload. For this feature, it is important for indoor balloon robot to move efficiently. The air resistance greatly influences balloon robots flight. Birds also have this feature, By getting self-organized formation, birds are enable to move efficiently. In this paper, we aim to realize to get self-organized multi-flying suitable for efficient move by using learning method for neural network with genetic algorithm. In the experiment, we confirmed the realization of self-organized mul...
  • SAKAMOTO HIRONORI, OHUCHI AZUMA, KAWAMURA HIDENORI  IPSJ SIG Notes. ICS  2008-  (20)  133  -134  2008/03/05  [Not refereed][Not invited]
     
    In recent years, the number of Internet user is increased as the personal computer and the portable terminal spread. So the cases used Social Networking Service or Consumer Generated Media, etc. as an information exchange and a communication means have risen. A lot of researches such as the community analysis and making to visible from the structure analysis, plot out a new mechanism and business model, information recommendation, have already been done to those media. However there are few researches that stares at the future like forecast and analyze the appearance of the development of n...
  • YAMASHITA AKIHIRO, KAWAMURA HIDENORI, IIZUKA HIROYUKI, OHUCHI AZUMA  IPSJ SIG Notes  68-  (17(MPS-68))  141  -144  2008/03/04  [Not refereed][Not invited]
     
    Information overload problem has expanded further more. A recommender system provides personalized recommendation for each user to reduce the problem. Many techniques to maximize the accuracy of recommendation based on browse history or purchase of certain products have been already proposed. Moreover, the recommendation result influences the user's behavior. Basically, the recommender system and the users are interactive, however, this dynamics had not been researched. In this research, we modeled the user as a purchase-rating agent, and analyzed the performance of the recommendation algorithm considering the system-user interaction. In this paper, we report a result of the analysis of user-based and and item-based collaborative filtering.
  • YAMASHITA AKIHIRO, KAWAMURA HIDENORI, IIZUKA HIROYUKI, OHUCHI AZUMA  IPSJ SIG Notes  68-  (17)  141  -144  2008/03/04  [Not refereed][Not invited]
     
    Information overload problem has expanded further more. A recommender system provides personalized recommendation for each user to reduce the problem. Many techniques to maximize the accuracy of recommendation based on browse history or purchase of certain products have been already proposed. Moreover, the recommendation result influences the user's behavior. Basically, the recommender system and the users are interactive, however, this dynamics had not been researched. In this research, we modeled the user as a purchase-rating agent, and analyzed the performance of the recommendation algorithm considering the system-user interaction. In this paper, we report a result of the analysis of user-based and and item-based collaborative filtering.
  • SAKAMOTO HIRONORI, OUCHI AZUMA, KAWAMURA HIDENORI  電子情報通信学会技術研究報告  107-  (523(AI2007 44-66))  133  -134  2008/02/27  [Not refereed][Not invited]
     
    In recent years, the number of Internet user is increased as the personal computer and the portable terminal spread. So the cases used Social Networking Service or Consumer Generated Media, etc. as an information exchange and a communication means have risen. A lot of researches such as the community analysis and making to visible from the structure analysis, plot out a new mechanism and business model, information recommendation, have already been done to those media. However there are few researches that stares at the future like forecast and analyze the appearance of the development of new media. In this research, perceive these media as a network and node as an information public on the media, edge as a relationship between those nodes, then we tried the analysis of the network about how it grows.
  • NAKABAYASHI YUTA, NISHIOKA RYOTA, YAMAGATA YOSHIFUMI, KAWAMURA HIDENORI, KAWAMURA HIDENORI, OUCHI AZUMA, OUCHI AZUMA, TAKAYA TOSHIHIKO  電子情報通信学会技術研究報告  107-  (523(AI2007 44-66))  91  -96  2008/02/27  [Not refereed][Not invited]
     
    Autonomous indoor balloon robots cannot have enough battery for long flight, because they have limitation of payload. For this feature, it is important for indoor balloon robot to move efficiently. The air resistance greatly influences balloon robots flight. Birds also have this feature, By getting self-organized formation, birds are enable to move efficiently. In this paper, we aim to realize to get self-organized multi-flying suitable for efficient move by using learning method for neural network with genetic algorithm. In the experiment, we confirmed the realization of self-organized multi-flying.
  • NAKABAYASHI YUTA, NISHIOKA RYOTA, YAMAGATA YOSHIFUMI, KAWAMURA HIDENORI, OHUCHI AZUMA, TAKAYA TOSHIHIKO  IEICE technical report. Artificial intelligence and knowledge-based processing  107-  (523)  91  -96  2008/02/27  [Not refereed][Not invited]
     
    Autonomous indoor balloon robots cannot have enough battery for long flight, because they have limitation of payload. For this feature, it is important for indoor balloon robot to move efficiently. The air resistance greatly influences balloon robots flight. Birds also have this feature, By getting self-organized formation, birds are enable to move efficiently. In this paper, we aim to realize to get self-organized multi-flying suitable for efficient move by using learning method for neural network with genetic algorithm. In the experiment, we confirmed the realization of self-organized mul...
  • SAKAMOTO HIRONORI, OHUCHI AZUMA, KAWAMURA HIDENORI  IEICE technical report. Artificial intelligence and knowledge-based processing  107-  (523)  133  -134  2008/02/27  [Not refereed][Not invited]
     
    In recent years, the number of Internet user is increased as the personal computer and the portable terminal spread. So the cases used Social Networking Service or Consumer Generated Media, etc. as an information exchange and a communication means have risen. A lot of researches such as the community analysis and making to visible from the structure analysis, plot out a new mechanism and business model, information recommendation, have already been done to those media. However there are few researches that stares at the future like forecast and analyze the appearance of the development of n...
  • 中山優季, 小倉朗子, 松田千春, 川村佐和子, 川村佐和子, 大西秀憲  フランスベッド・メディカルホームケア研究・助成財団研究助成・事業助成報告書  18th-  2008
  • 川村秀憲, 伊藤直哉, 鈴木恵二, 大内東  日本オペレーションズ・リサーチ学会秋季研究発表会アブストラクト集  2008-  136  -137  2008  [Not refereed][Not invited]
  • KAWAMURA HIDENORI, KAWAMURA HIDENORI, KAWAMURA HIDENORI, KURUMATANI KOICHI, KURUMATANI KOICHI, OUCHI AZUMA, OUCHI AZUMA  人工知能学会全国大会論文集(CD-ROM)  22nd-  3A3-06  2008  [Not refereed][Not invited]
  • 高谷 敏彦, 川村 秀憲, 山本 雅人  Ricoh technical report  0-  (34)  119  -130  2008  [Not refereed][Not invited]
  • Cooperative Control of Multiple Neural Networks for Indoor Blimp Robot
    The Thirteenth International Symposium on Artificial Life and Robotics 2008  131  -134  2008  [Not refereed][Not invited]
  • Hidenori Kawamura, Masahito Yamamoto, Toshihiko Takaya, Azuma Ohuchi  Artificial Life and Robotics  12-  (1-2)  116  -121  2008  [Refereed][Not invited]
     
    We report on learning landing control for the self-energy recharging of indoor blimp robots. Indoor blimp robots have potential applications in monitoring, surveillance, and entertainment. It might be necessary for blimp robots to fly for a long time to achieve these tasks. Since blimp robots cannot have a heavy battery, it is difficult to fly for long time. Therefore, we solved this problem by developing self-energy recharging control, i.e., docking to an energy charging station. We call it landing control. We introduce a way to learn landing control to tackle an unstable flying condition. The results of experiments show the effectiveness of the landing control. © 2008 International Symposium on Artificial Life and Robotics (ISAROB).
  • Simulation and implement of Memory-based PID control for indoor blimp robot
    The thirteenth International Symposium on Artificial Life and Robotics 2008  CD-ROM  2008  [Not refereed][Not invited]
  • MATSUMURA YUSUKE, MATSUMURA YUSUKE, MATSUMURA YUSUKE, KAWAMURA HIDENORI, KAWAMURA HIDENORI, KAWAMURA HIDENORI, KAWAMURA HIDENORI, KURUMATANI KOICHI, KURUMATANI KOICHI, OUCHI AZUMA, OUCHI AZUMA  情報処理学会研究報告  2007-  (128(MPS-67 BIO-11))  69  -72  2007/12/20  [Not refereed][Not invited]
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, KURUMATANI KOICHI, OHUCHI AZUMA  IPSJ SIG technical reports  2007-  (128)  69  -72  2007/12/20  [Not refereed][Not invited]
     
    The complex network research in recent years revealed that growth process of real-world networks paying attention to growing networks. This paper proposes a phased network structure design problem in the standpoint of designing the growing network and a solving method based on the hill-climbing method. Effectiveness of the solving method was verified by a numerical experiment.
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, KURUMATANI KOICHI, OHUCHI AZUMA  IPSJ SIG Notes  2007-  (128)  69  -72  2007/12/20  [Not refereed][Not invited]
     
    The complex network research in recent years revealed that growth process of real-world networks paying attention to growing networks. This paper proposes a phased network structure design problem in the standpoint of designing the growing network and a solving method based on the hill-climbing method. Effectiveness of the solving method was verified by a numerical experiment.
  • 山下晃弘, 川村秀憲, 山本雅人, 大内東  情報科学技術フォーラム  FIT 2007-  349  -352  2007/08/22  [Not refereed][Not invited]
  • 高橋春樹, 川村秀憲, 山本雅人, 大内東  情報科学技術フォーラム  FIT 2007-  157  -160  2007/08/22  [Not refereed][Not invited]
  • Takahashi Haruki, Kawamura Hidenori, Yamamoto Masato, Ohuchi Azuma  情報科学技術レターズ  6-  (0)  157  -160  2007/08/22  [Not refereed][Not invited]
  • Yamashita Akihiro, Kawamura Hidenori, Yamamoto Masahito, Ohuchi Azuma  情報科学技術フォーラム一般講演論文集  6-  (2)  349  -352  2007/08/22  [Not refereed][Not invited]
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, OHUCHI AZUMA  IPSJ journal  48-  (6)  2097  -2105  2007/06/15  
    The high-quality service provided by the large-scale tele-communication network constructed in the Internet such as the Gnutella is thought to be achieved by a certain feature network structure. Moreover, a feature structure is assumed to be generated with a certain simple generation rule in another research. This shows that there is a possibility that an effective design approach of the large scale network can be established if the design of the generation rule that generates the optimal structure becomes possible. Authors tried to archive a structural generation rule to make the communication efficiency on the telecommunication network considering these in this paper. Concretely, the network was modeled with the queueing network and a structural generation rule to minimize waiting time was investigated. As the result, it made clear that the generation rule can generate structures with small enough waiting time under som conditions.
  • NISHIOKA Ryouta, KAWAMURA Hidenori, YAMAMOTO Masahito, TAKAYA Toshihiko, OHUCHI Azuma  ロボティクス・メカトロニクス講演会講演概要集  2007-  (0)  "2A2  -A08(1)"-"2A2-A08(4)"  2007/05/11  [Not refereed][Not invited]
     
    We report on line following control for indoor blimp robot. Indoor blimp robot can be moved to the altitude and the place with differences in the building. There are applications of the guide and the round in the building by using those features. It is generable target trajectory to put the one that becomes a landmark on the moved place. Therefore, we put the line as a landmark. The line is showing flat information in the target trajectory, and information of height can be obtained according to the width of the line. In this paper, we report the extraction method of the line in the camera i...
  • KASAWAKI Hiroto, KAWAMURA Hidenori, YAMAMOTO Masahito, TAKAYA Toshihiko, OHUCHI Azuma  ロボティクス・メカトロニクス講演会講演概要集  2007-  (0)  "2A2  -B02(1)"-"2A2-B02(4)"  2007/05/11  [Not refereed][Not invited]
     
    This paper describes that an indoor balloon control system based on flight plan with constraint time. Indoor balloon robots have the features of using buoyancy to move three dimensional movements, moving less energy. Furthermore, balloon robot has high safety to crash, and can use it safely also in indoor space. For these features, indoor balloon robots have enormous potential for applications such as an entertainment flight, automatic surveillance. Our goal is synchronized flying. However, they have difficulties to control because of nonlinear thrust and air resistance. We develop of the c...
  • NISHIOKA RYOTA, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, TAKAYA TOSHIHIKO, OUCHI AZUMA  日本機械学会ロボティクス・メカトロニクス講演会講演論文集(CD-ROM)  2007-  2A2-A08  2007/05/10  [Not refereed][Not invited]
  • KASAWAKI HIROTO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, TAKAYA TOSHIHIKO, OUCHI AZUMA  日本機械学会ロボティクス・メカトロニクス講演会講演論文集(CD-ROM)  2007-  2A2-B02  2007/05/10  [Not refereed][Not invited]
  • YAMASHITA Akihiro, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IEICE technical report  106-  (586)  75  -80  2007/03/15  [Not refereed][Not invited]
     
    As the number of individual tourists increases, Web browsing is becoming one of the methods to gather tourism information such as restaurants and accommodations. However, it is difficult to search for necessary and valuable tourism information. Meanwhile, the services which are called Web2.0 dramatically increase. These features are information collection from users, information sharing and user adaptive recommendation. This information distribution form will extend increasingly, and the influence on the tourism industry will be significant. This research constructs user-centred tourism information system with objective information and subjective ratings. Then it innovates tourism website using Web2.0 technologies. This study proposes to use the Weblog interface for the system to collect much tourism information. Further, to recommend some products for users, it utilizes Collaborative Filtering Algorithm to resolve which products should be suggested. This paper introduces an application to a restaurant information website.
  • IMAKAWA TAKAHIRO, IMAKAWA TAKAHIRO, KAWAMURA HIDENORI, KAWAMURA HIDENORI, KURUMATANI KOICHI, KURUMATANI KOICHI, OUCHI AZUMA, OUCHI AZUMA  情報処理学会研究報告  2007-  (26(ICS-147))  1  -6  2007/03/14  [Not refereed][Not invited]
     
    Recently ubiquitous environment is being realized with the development of ICT (Information Communications Technology). The ubiquitous environment realizes a new type of supports called mass user support. In this paper, we proposed schedule-sharing system for congestion reduction, and apply to model of theme park problem. As the result, numerical experiment verified that the proposed system can decrease staying time in the theme park of whole visitor.
  • YAMASHITA Akihiro, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IPSJ SIG Notes. ICS  147-  (26(ICS-147))  133  -138  2007/03/14  [Not refereed][Not invited]
     
    As the number of individual tourists increases, Web browsing is becoming one of the methods to gather tourism information such as restaurants and accommodations. However, it is difficult to search for necessary and valuable tourism information. Meanwhile, the services which are called Web2.0 dramatically increase. These features are information collection from users, information sharing and user adaptive recommendation. This information distribution form will extend increasingly, and the influence on the tourism industry will be significant. This research constructs user-centred tourism information system with objective information and subjective ratings. Then it innovates tourism website using Web2.0 technologies. This study proposes to use the Weblog interface for the system to collect much tourism information. Further, to recommend some products for users, it utilizes Collaborative Filtering Algorithm to resolve which products should be suggested. This paper introduces an application to a restaurant information website.
  • MATSUMURA YUSUKE, MATSUMURA YUSUKE, KAWAMURA HIDENORI, KAWAMURA HIDENORI, KURUMATANI KOICHI, KURUMATANI KOICHI, OUCHI AZUMA, OUCHI AZUMA  情報処理学会研究報告  2007-  (26(ICS-147))  203  -210  2007/03/14  [Not refereed][Not invited]
  • IMAKAWA Takahiro, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2007-  (26)  1  -6  2007/03/14  [Not refereed][Not invited]
     
    Recently ubiquitous environment is being realized with the development of ICT (Information Communications Technology). The ubiquitous environment realizes a new type of supports called mass user support. In this paper, we proposed schedule-sharing system for congestion reduction, and apply to model of theme park problem. As the result, numerical experiment verified that the proposed system can decrease staying time in the theme park of whole visitor.
  • YAMASHITA Akihiro, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IPSJ SIG Notes. ICS  147-  (26)  133  -138  2007/03/14  [Not refereed][Not invited]
     
    As the number of individual tourists increases, Web browsing is becoming one of the methods to gather tourism information such as restaurants and accommodations. However, it is difficult to search for necessary and valuable tourism information. Meanwhile, the services which are called Web2.0 dramatically increase. These features are information collection from users, information sharing and user adaptive recommendation. This information distribution form will extend increasingly, and the influence on the tourism industry will be significant. This research constructs user-centred tourism information system with objective information and subjective ratings. Then it innovates tourism website using Web2.0 technologies. This study proposes to use the Weblog interface for the system to collect much tourism information. Further, to recommend some products for users, it utilizes Collaborative Filtering Algorithm to resolve which products should be suggested. This paper introduces an application to a restaurant information website.
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, KURUMATANI KOICHI, OHUCHI AZUMA  IPSJ SIG Notes. ICS  2007-  (26)  203  -210  2007/03/14  [Not refereed][Not invited]
     
    Recent research revealed that the high quality service provided by large scale telecommunication network constructed on the Internet such as Gnutella is realized by characteristic structure of network. Another research found that these characteristic structures are constructed by simple generation rules. Up to now, the authors have been researching the method of designing the rule that makes the communication efficiency on the telecommunication network paying attention to these works. Authors propose the structural optimization problem with the link exchange, and examine the structure to ac...
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, KURUMATANI KOICHI, OHUCHI AZUMA  IEICE technical report. Artificial intelligence and knowledge-based processing  106-  (587)  53  -60  2007/03/09  [Not refereed][Not invited]
     
    Recent research revealed that the high quality service provided by large scale telecommunication network constructed on the Internet such as Gnutella is realized by characteristic structure of network. Another research found that these characteristic structures are constructed by simple generation rules. Up to now, the authors have been researching the method of designing the rule that makes the communication efficiency on the telecommunication network paying attention to these works. Authors propose the structural optimization problem with the link exchange, and examine the structure to ac...
  • IMAKAWA Takahiro, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  106-  (585)  1  -6  2007/03/07  [Not refereed][Not invited]
     
    Recently ubiquitous environment is being realized with the development of ICT (Information Communications Technology). The ubiquitous environment realizes a new type of supports called mass user support. In this paper, we proposed schedule-sharing system for congestion reduction, and apply to model of theme park problem. As the result, numerical experiment verified that the proposed system can decrease staying time in the theme park of whole visitor.
  • 武邑光裕, 梅村匡史, 及川純, 川村秀憲, 黒河内俊二, 五反田英利, 杉山幹夫, 田倉和男, 千葉孝志, 樋泉実, 中村卓三, 日浦正博, 見付均, 吉村匠  北海道における地域映像活用調査検討報告書 北海道における映像コンテンツの現状と活用例を探る 平成19年  100P  2007  [Not refereed][Not invited]
  • Akihiro Yamashita, Hidenori Kawamura, Hiroyuki Iizuka, Azuma Ohuchi  INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2007  4881-  1112  -+  2007  [Refereed][Not invited]
     
    Recommender System provides certain products adapted to a target user, from a large number of products. One of the most successful recommendation algorithms is Collaborative Filtering, and it is used in many websites. However, the recommendation result is influenced by community characteristics such as the number of users and bias of users' preference, because the system uses ratings of products by the users at the recommendation. In this paper, we evaluate an effect of community characteristics on recommender system, using multi-agent based simulation. The results show that a certain number of ratings are necessary to effective recommendation based on collaborative filtering. Moreover, the results also indicate that the number of necessary ratings for recommendation depends on the number of users and bias of the users' preference.
  • Development of User-Adaptive Tourism Website with Weblog and Recommender System
    Work in Progress Proceedings of the 14th International ENTER Conference  173  -181  2007  [Not refereed][Not invited]
  • A study on improvement of the surveillance system of an indoor robot
    Toshihiko Takaya, Hidenori Kawamura, Yoshihiro Minagawa, Masahito Yamamoto, Azuma Ohuchi  The Twelfth International Symposium on Artificial Life and Robotics 2007 (CD-ROM)  -1  2007  [Not refereed][Not invited]
  • Vision based control for line following blimp robot
    The Twelfth International Symposium on Artificial Life and Robotics 2007 (CD-ROM)  -1  2007  [Not refereed][Not invited]
  • Self-Assessment System for Hotel Classification in Japan
    Work in Progress Proceedings of the 14th International ENTER Conference  183  -193  2007  [Not refereed][Not invited]
  • Relations Between Structure of Networks and Effectiveness of Mass-User Support System
    In proceedings of International Conference on Economic Science with Heterogeneous Interacting Agents 2007 (ESHIA2007)  CD-ROM  2007  [Not refereed][Not invited]
  • OYANAGI YUKIHIKO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA, YANAGIMORI TOSHINOBU, MAGOTA SHIGEKI  ファジィシステムシンポジウム講演論文集(CD-ROM)  22nd-  8A3-1  -722  2006/09/06  [Not refereed][Not invited]
  • NAGAO MITSUYOSHI, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA, NAGAO MITSUYOSHI, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  ファジィシステムシンポジウム講演論文集(CD-ROM)  22nd-  8C2-1  -818  2006/09/06  [Not refereed][Not invited]
  • MINAGAWA YOSHIHIRO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, TAKAYA TOSHIHIKO, TAKAYA TOSHIHIKO, OUCHI AZUMA  ファジィシステムシンポジウム講演論文集(CD-ROM)  22nd-  8A1-2  -692  2006/09/06  [Not refereed][Not invited]
  • TAKAYA TOSHIHIKO, KAWAMURA HIDENORI, MINAGAWA YOSHIHIRO, YAMAMOTO MASAHITO, OUCHI AZUMA  ファジィシステムシンポジウム講演論文集(CD-ROM)  22nd-  8A1-1  2006/09/06  [Not refereed][Not invited]
  • YAMASHITA AKIHIRO, KAWAMURA HIDENORI, OUCHI AZUMA  ファジィシステムシンポジウム講演論文集(CD-ROM)  22-  827  -830  2006/09/06  [Not refereed][Not invited]
  • 山下晃弘, 川村秀憲, 大内東  情報科学技術フォーラム  FIT 2006-  139  -142  2006/08/21  [Not refereed][Not invited]
  • 皆川良弘, 川村秀憲, 山本雅人, 高谷敏彦, 高谷敏彦, 大内東  情報科学技術フォーラム  FIT 2006-  301  -303  2006/08/21  [Not refereed][Not invited]
  • Yamashita Akihiro, Kawamura Hidenori, Ohuchi Azuma  情報科学技術フォーラム一般講演論文集  5-  (4)  139  -142  2006/08/21  [Not refereed][Not invited]
  • Minagawa Yoshihiro, Kawamura Hidenori, Yamamoto Masahito, Takaya Toshihiko, Ohuchi Azuma  情報科学技術フォーラム一般講演論文集  5-  (3)  301  -303  2006/08/21  [Not refereed][Not invited]
  • KAWAMURA HIDENORI, ONODERA MASAKI, OHUCHI AZUMA  IPSJ journal  47-  (7)  2202  -2211  2006/07/15  
    We focus on a method to calculate the estimated value for a probabilistic model in which each event is defined as a combination of several other independent events. The partially exhaustive investigation Monte Carlo method has been proposed by the authors for such model, and it can show higher performance than simple weighted sampling Monte Carlo method on the condition that the used sample number for estimating is limited. This method divides the event into two parts by a threshold parameter; one is composed by high-probability events, and another is by remaining events. To make this method for practical use, these are unclear appropriate threshold setting and a condition that this method works effectively. In this paper, we investigate the condition that this method works effectively, and propose the partially exhaustive investigation Monte Carlo method with automatic threshold parameter setting.
  • 松村 有祐, 川村 秀憲, 大内 東  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2006-  (0)  204  -205  2006/03/14  [Not refereed][Not invited]
  • 長尾光悦, 川村秀憲, 山本雅人, 大内東  情報処理学会全国大会講演論文集  68th-  (4)  345  -346  2006/03/07  [Not refereed][Not invited]
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, KAWAMURA HIDENORI, OUCHI AZUMA, OUCHI AZUMA  情報処理学会研究報告  2006-  (2(ICS-142))  1  -8  2006/01/12  [Not refereed][Not invited]
     
    As the important product of the Complex Network research in recent years, many network dynamics lying on large scale networks are revealed by developing many network models, being affected by discovery of the Small-World and the Scale-Free networks. Although to understand current mechanisms is important, it's also necessary to discuss about features of desirable structure, when we have more engineered perspective. This research reveals desirable structure for various networks by use of knowledge obtained with the recent research, aiming to suggest knowledge of desirable design for developing small network which we never knew. For this paper, we discuss desirable designs for some queueing networks, constructing mathematical model of the Queueing Network excluding linking costs.
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, OHUCHI AZUMA  IPSJ SIG Notes. ICS  2006-  (2)  1  -8  2006/01/12  [Not refereed][Not invited]
     
    As the important product of the Complex Network research in recent years, many network dynamics lying on large scale networks are revealed by developing many network models, being affected by discovery of the Small-World and the Scale-Free networks. Although to understand current mechanisms is important, it's also necessary to discuss about features of desirable structure, when we have more engineered perspective. This research reveals desirable structure for various networks by use of knowledge obtained with the recent research, aiming to suggest knowledge of desirable design for developin...
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, KAWAMURA HIDENORI, OUCHI AZUMA, OUCHI AZUMA  電子情報通信学会技術研究報告  105-  (509(AI2005 21-27))  1  -8  2006/01/05  [Not refereed][Not invited]
     
    As the important product of the Complex Network research in recent years, many network dynamics lying on large scale networks are revealed by developing many network models, being affected by discovery of the Small-World and the Scale-Free networks. Although to understand current mechanisms is important, it's also necessary to discuss about features of desirable structure, when we have more engineered perspective. This research reveals desirable structure for various networks by use of knowledge obtained with the recent research, aiming to suggest knowledge of desirable design for developing small network which we never knew. For this paper, we discuss desirable designs for some queueing networks, constructing mathematical model of the Queueing Network excluding linking costs.
  • MATSUMURA YUSUKE, KAWAMURA HIDENORI, OHUCHI AZUMA  IEICE technical report. Artificial intelligence and knowledge-based processing  105-  (509)  1  -8  2006/01/05  [Not refereed][Not invited]
     
    As the important product of the Complex Network research in recent years, many network dynamics lying on large scale networks are revealed by developing many network models, being affected by discovery of the Small-World and the Scale-Free networks. Although to understand current mechanisms is important, it's also necessary to discuss about features of desirable structure, when we have more engineered perspective. This research reveals desirable structure for various networks by use of knowledge obtained with the recent research, aiming to suggest knowledge of desirable design for developin...
  • 松村有祐, 川村秀憲, 川村秀憲, 大内東, 大内東  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2006-  204  -205  2006  [Not refereed][Not invited]
  • 大内東, 梅村匡史, 荒井功, 伊藤一, 稲村秀人, 岩田勝男, 片倉康治, 照井幸一, 川村秀憲, 沓沢正司, 黒河内俊二, 伊藤邦宏, 澤邊正彦, 杉山幹夫, 高橋道裕, 土屋敦司, 樋泉実, 馬場俊, 中田ヒロ, 堀清敬, 脇山潤, 高畑勝人, 簑島新一, 漁島直  北海道の観光におけるICT利活用調査検討報告書 北海道観光をより快適に 発信!発進!!ICTツーリズム 平成18年  71P  2006  [Not refereed][Not invited]
  • Toshihiko Takaya, Hidenori Kawamura, Yoshihiro Minagawa, Masahito Yamaruo, Azuma Ouchi  2006 SICE-ICASE INTERNATIONAL JOINT CONFERENCE, VOLS 1-13  5653  -+  2006  [Not refereed][Not invited]
     
    Blimp robots are attractive as indoor flying robots because they can float in the air, land safely with low energy, and stay in motion for a long time compared with other flying robots. However, controlling of blimp robots is difficult, because they have nonlinear characteristics, are influenced by air streams, and is easy to be influenced of inertia. Therefore a robust and adaptive control system is needed for blimp robots. The applied research that paid its attention to the feature of indoor flying robot in recent years has prospered. Operating an indoor blimp robot for a long time is difficult for the payload is small, many batteries cannot be stacked. and the design of a thruster that has freedom and the entire blimp robot. Therefore, an autonomous charge that enables operation for a long time is needed. We developed a round orbit control to the Surveillance point for an autonomous of a blimp robot. The possibility of round surveillance three dimensional orbit controls was shown.
  • MINAGAWA YOSHIHIRO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, TAKAYA TOSHIHIKO, OUCHI AZUMA, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, TAKAYA TOSHIHIKO, OUCHI AZUMA  情報処理学会研究報告  2005-  (125(EC-2))  1  -5  2005/12/17  [Not refereed][Not invited]
     
    In this paper, we propose a method of docking control of autonomous recharging for indoor balloon robot. Indoor balloon robot might be applied to entertainment flight in an event hall, such as synchronized flight of multiple balloon robots, interactive balloon robot. It might be necessary for long term flight to achieve entertainment flight. However, indoor balloon robot cannot load heavy battery for long term flight. To achieve long term flight, one approach is autonomous recharging. In the case of low battery remainder, indoor balloon robot moves to charging station for recharging. For autonomous recharging, we designed charging station and docking control for indoor balloon robot.
  • Minagawa Yoshihiro, Kawamura Hidenori, Yamamoto Masahito, Takaya Toshihiko, Ohuchi Azuma  IPSJ SIG technical reports  2005-  (125)  1  -5  2005/12/17  [Not refereed][Not invited]
     
    In this paper, we propose a method of docking control of autonomous recharging for indoor balloon robot. Indoor balloon robot might be applied to entertainment flight in an event hall, such as synchronized flight of multiple balloon robots, interactive balloon robot. It might be necessary for long term flight to achieve entertainment flight. However, indoor balloon robot cannot load heavy battery for long term flight. To achieve long term flight, one approach is autonomous recharging. In the case of low battery remainder, indoor balloon robot moves to charging station for recharging. For au...
  • KAWAMURA HIDENORI, ONODERA MASAKI, OHUCHI AZUMA  IPSJ journal  46-  (12)  3218  -3227  2005/12/15  
    To design an autonomous-trading software agent for some kinds of game and electric commerce, the agent often has to cope with the situation that result of decision-making includes stochastic phenomena. In such case, it is necessary for the agent to consider expected evaluation value for possible results according to the probability of results, and Monte Carlo Method is generally used to calculate the expected evaluation value for such situation. In this paper, we suppose the situation that it is easy to enumerate high-probability results at low computation cost, and propose an improved version of Monte Carlo Method, i.e., Partially EXhaustive Investigation (PEXI) Monte Carlo Method. Moreover, we show the effectiveness of the proposed method by some computer experiments including the designing of TAC CLASSIC trading agent.
  • TAKAYANAGI TOSHIAKI, KAWAMURA HIDENORI, OUCHI AZUMA  情報処理学会シンポジウム論文集  2005-  (11)  107  -112  2005/10/11  [Not refereed][Not invited]
  • HONDA Takatomo, YAMAMOTO Masahito, KAWAMURA Hidenori, OHUCHI Azuma  IPSJ SIG Notes. ICS  2005-  (78)  1  -4  2005/08/01  [Not refereed][Not invited]
     
    A website is considered to be belonging to a certain category such as accommodations, restaurants, facilities and so on, as shown in the directory-typed search engines. Generally, a website includes valuable information such as links to or from other sites, many files with extensions and many text data, in terms of the category classification. In this paper, we investigate whether many websites belonging to a certain category have some common features or not. In particular, we show that some keywords are very important to classify websites to the categories. By using these analyzed keyword ...
  • NAGAO Mitsuyoshi, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IPSJ SIG Notes. ICS  2005-  (78)  23  -28  2005/08/01  [Not refereed][Not invited]
     
    In this paper, we propose an extraction method of activity information on circular tour from GPS log. In this research, we focus on circular tour with rent-a-car. The proposed method extracts basic activity information which includes the information about destinations and movements from GPS log which consist of the position information on circular tour. The analysis for circular tour is performed on the basis of the extracted basic activity information. We confirm the effectiveness of the proposed method through the experiment using GPS log collected from actual tourists on Hokkaido circula...
  • HONDA TAKATOMO, YAMAMOTO MASAHITO, KAWAMURA HIDENORI, OUCHI AZUMA  電子情報通信学会技術研究報告  105-  (224(AI2005 7-14))  1  -4  2005/07/25  [Not refereed][Not invited]
     
    A website is considered to be belonging to a certain category such as accommodations, restaurants, facilities and so on, as shown in the directory-typed search engines. Generally, a website includes valuable information such as links to or from other sites, many files with extensions and many text data, in terms of the category classification. In this paper, we investigate whether many websites belonging to a certain category have some common features or not. In particular, we show that some keywords are very important to classify websites to the categories. By using these analyzed keyword information, we present that many websites could be classified to an appropriate category with high precision when three categories (museum, restaurant and accommodations) related to tourism are treated as examples.
  • NAGAO MITSUYOSHI, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  電子情報通信学会技術研究報告  105-  (224(AI2005 7-14))  23  -28  2005/07/25  [Not refereed][Not invited]
     
    In this paper, we propose an extraction method of activity information on circular tour from GPS log. In this research, we focus on circular tour with rent-a-car. The proposed method extracts basic activity information which includes the information about destinations and movements from GPS log which consist of the position information on circular tour. The analysis for circular tour is performed on the basis of the extracted basic activity information. We confirm the effectiveness of the proposed method through the experiment using GPS log collected from actual tourists on Hokkaido circular tour. In addition, we analyze Hokkaido circular tour and discuss the analysis result.
  • HONDA Takatomo, YAMAMOTO Masahito, KAWAMURA Hidenori, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  105-  (224)  1  -4  2005/07/25  [Not refereed][Not invited]
     
    A website is considered to be belonging to a certain category such as accommodations, restaurants, facilities and so on, as shown in the directory-typed search engines. Generally, a website includes valuable information such as links to or from other sites, many files with extensions and many text data, in terms of the category classification. In this paper, we investigate whether many websites belonging to a certain category have some common features or not. In particular, we show that some keywords are very important to classify websites to the categories. By using these analyzed keyword ...
  • NAGAO Mitsuyoshi, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  105-  (224)  23  -28  2005/07/25  [Not refereed][Not invited]
     
    In this paper, we propose an extraction method of activity information on circular tour from GPS log. In this research, we focus on circular tour with rent-a-car. The proposed method extracts basic activity information which includes the information about destinations and movements from GPS log which consist of the position information on circular tour. The analysis for circular tour is performed on the basis of the extracted basic activity information. We confirm the effectiveness of the proposed method through the experiment using GPS log collected from actual tourists on Hokkaido circula...
  • MINAGAWA YOSHIHIRO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, TAKAYA TOSHIHIKO, OUCHI AZUMA  日本機械学会ロボティクス・メカトロニクス講演会講演論文集(CD-ROM)  2005-  2P1-S-059  2005/06/09  [Not refereed][Not invited]
  • KAWAMURA HIDENORI, KADOTA HISAO, YAMAMOTO MASAHITO, TAKAYA TOSHIHIKO, OUCHI AZUMA  日本機械学会ロボティクス・メカトロニクス講演会講演論文集(CD-ROM)  2005-  1P1-S-060  2005/06/09  [Not refereed][Not invited]
  • Kawamura Hidenori, Kadota Hisao, Yamamoto Masahito, Takaya Toshihiko, Ohuchi Azuma  ロボティクス・メカトロニクス講演会講演概要集  2005-  (0)  89  -89  2005/06/09  [Not refereed][Not invited]
  • Minagawa Yoshihiro, Kawamura Hidenori, Yamamoto Masahito, Takaya Toshihiko, Ohuchi Azuma  Proceeding of The 2005 JSME Conference on Robotics and Mechatronics, (ROBOMEC2005), Kobe  2005-  (0)  2005/06/09  [Not refereed][Not invited]
  • ONODERA Masaki, KAWAMURA Hidenori, OHUCHI Azuma  IPSJ SIG Notes. ICS  139-  (0)  1  -6  2005/03/14  [Not refereed][Not invited]
     
    In this paper, we propose the partially exhaustive evaluation Monte Carlo Method, which improves the accuracy of estimation of expected value, and evaluate the effectiveness of the proposed method. Moreover, we apply the proposed method to the Tour Planning Problem, which includes the uncertainty that a result to a single solution cannot be determined uniquely. From experimental results, it has been confirmed that the accuracy of estimation is improved by the proposed method, and as a result, the effectiveness of searching is improved.
  • MORI Yasunao, KAWAMURA Hidenori, OHUCHI Azuma  情報処理学会研究報告. ICS, [知能と複雑系]  139-  (0)  13  -18  2005/03/14  [Not refereed][Not invited]
  • MATSUMOTO Takashi, KAWAMURA Hidenori, OHUCHI Azuma  情報処理学会研究報告. ICS, [知能と複雑系]  139-  (0)  91  -96  2005/03/14  [Not refereed][Not invited]
  • IMAKAWA Takahiro, KAWAMURA Hidenori, OHUCHI Azuma  情報処理学会研究報告. ICS, [知能と複雑系]  139-  (0)  97  -102  2005/03/14  [Not refereed][Not invited]
  • ONODERA Masaki, KAWAMURA Hidenori, OHUCHI Azuma  IPSJ SIG Notes. ICS  2005-  (24)  1  -6  2005/03/14  [Not refereed][Not invited]
     
    In this paper, we propose the partially exhaustive evaluation Monte Carlo Method, which improves the accuracy of estimation of expected value, and evaluate the effectiveness of the proposed method. Moreover, we apply the proposed method to the Tour Planning Problem, which includes the uncertainty that a result to a single solution cannot be determined uniquely. From experimental results, it has been confirmed that the accuracy of estimation is improved by the proposed method, and as a result, the effectiveness of searching is improved.
  • MORI Yasunao, KAWAMURA Hidenori, OHUCHI Azuma  IPSJ SIG Notes. ICS  2005-  (24)  13  -18  2005/03/14  [Not refereed][Not invited]
     
    In a distributed computer system configurated by some kinds of servers, it becomes pupular that the research and development of technology which allocate dynamically resource to each server adapiting to changing workloads. In this paper, We propose the dynamic network resource allocation system by using response threshold reinforcement model in social insects, and verify the effect by simulation.
  • MATSUMOTO Takashi, KAWAMURA Hidenori, OHUCHI Azuma  IPSJ SIG Notes. ICS  2005-  (24)  91  -96  2005/03/14  [Not refereed][Not invited]
     
    In this paper, we propose the auction system protocol which trading of CPU usage cycles among companies. This proposal system realize that anyone cannot identify bidder illegally unless the auctioneer and participants majority act in collusion, by using cryptographic technologies such like public key encryption, hash function and Secret Sharing Scheme. Moreover, this system is considered anonymous of bidder regarding the trading method and transmission method of bid. In addition, we developed an auction system with the proposal technique, and verified the proposal technique runs as a system...
  • IMAKAWA Takahiro, KAWAMURA Hidenori, OHUCHI Azuma  IPSJ SIG Notes. ICS  2005-  (24)  97  -102  2005/03/14  [Not refereed][Not invited]
     
    Currently, there are various types of online community. Because of anonymity, it is difficult to evaluate the information on Web. It is expected that the problem gets worse as the number of users on Web increase. In this paper, we propose reviewer emergence model with meta evaluation and verify effectiveness of it.
  • KATAOKA Takashi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2005-  (24)  133  -138  2005/03/14  [Not refereed][Not invited]
     
    In this paper, we propose a new congestion information system. There is a problem caused by time delay between decision-making and emergence of its effect in a general congestion information system. In our system, users register their next destination when they select it, and we try to solve its problem with providing congestion information taken in the registration information. Moreover, to stimulate registrations of many users, we propose to make the exclusive queue. As the result of having applied to Theme Park Problem, our system was effective of reduction of waiting time in any topology.
  • MATSUMOTO TAKASHI, KAWAMURA HIDENORI, OUCHI AZUMA  電子情報通信学会技術研究報告  104-  (727(AI2004 80-94))  37  -42  2005/03/08  [Not refereed][Not invited]
     
    In this paper, we propose the auction system protocol which trading of CPU usage cycles among companies. This proposal system realize that anyone cannot identify bidder illegally unless the auctioneer and participants majority act in collusion, by using cryptographic technologies such like public key encryption, hash function and Secret Sharing Scheme. Moreover, this system is considered anonymous of bidder regarding the trading method and transmission method of bid. In addition, we developed an auction system with the proposal technique, and verified the proposal technique runs as a system and the effect of CPU resource trading.
  • KATAOKA TAKASHI, KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  電子情報通信学会技術研究報告  104-  (727(AI2004 80-94))  79  -84  2005/03/08  [Not refereed][Not invited]
     
    In this paper, we propose a new congestion information system. There is a problem caused by time delay between decision-making and emergence of its effect in a general congestion information system. In our system, users register their next destination when they select it, and we try to solve its problem with providing congestion information taken in the registration information. Moreover, to stimulate registrations of many users, we propose to make the exclusive queue. As the result of having applied to Theme Park Problem, our system was effective of reduction of waiting time in any topology.
  • IMAKAWA TAKAHIRO, KAWAMURA HIDENORI, OUCHI AZUMA  電子情報通信学会技術研究報告  104-  (727(AI2004 80-94))  43  -48  2005/03/08  [Not refereed][Not invited]
     
    Currently, there are various types of online community. Because of anonymity, it is difficult to evaluate the information on Web. It is expected that the problem gets worse as the number of users on Web increase. In this paper, we propose reviewer emergence model with meta evaluation and verify effectiveness of it.
  • MATSUMOTO Takashi, KAWAMURA Hidenori, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  104-  (727)  37  -42  2005/03/08  [Not refereed][Not invited]
     
    In this paper, we propose the auction system protocol which trading of CPU usage cycles among companies. This proposal system realize that anyone cannot identify bidder illegally unless the auctioneer and participants majority act in collusion, by using cryptographic technologies such like public key encryption, hash function and Secret Sharing Scheme. Moreover, this system is considered anonymous of bidder regarding the trading method and transmission method of bid. In addition, we developed an auction system with the proposal technique, and verified the proposal technique runs as a system...
  • IMAKAWA Takahiro, KAWAMURA Hidenori, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  104-  (727)  43  -48  2005/03/08  [Not refereed][Not invited]
     
    Currently, there are various types of online community. Because of anonymity, it is difficult to evaluate the information on Web. It is expected that the problem gets worse as the number of users on Web increase. In this paper, we propose reviewer emergence model with meta evaluation and verify effectiveness of it.
  • KATAOKA Takashi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  104-  (727)  79  -84  2005/03/08  [Not refereed][Not invited]
     
    In this paper, we propose a new congestion information system. There is a problem caused by time delay between decision-making and emergence of its effect in a general congestion information system. In our system, users register their next destination when they select it, and we try to solve its problem with providing congestion information taken in the registration information. Moreover, to stimulate registrations of many users, we propose to make the exclusive queue. As the result of having applied to Theme Park Problem, our system was effective of reduction of waiting time in any topology.
  • MORI YASUNAO, KAWAMURA HIDENORI, OUCHI AZUMA  電子情報通信学会技術研究報告  104-  (726(AI2004 71-79))  13  -18  2005/03/07  [Not refereed][Not invited]
  • ONODERA MASAKI, KAWAMURA HIDENORI, OUCHI AZUMA  電子情報通信学会技術研究報告  104-  (726(AI2004 71-79))  1  -6  2005/03/07  [Not refereed][Not invited]
     
    In this paper, we propose the partially exhaustive evaluation Monte Carlo Method, which improves the accuracy of estimation of expected value, and evaluate the effectiveness of the proposed method. Moreover, we apply the proposed method to the Tour Planning Problem, which includes the uncertainty that a result to a single solution cannot be determined uniquely. From experimental results, it has been confirmed that the accuracy of estimation is improved by the proposed method, and as a result, the effectiveness of searching is improved.
  • 森 康真, 川村 秀憲, 大内 東  電子情報通信学会技術研究報告. AI, 人工知能と知識処理  104-  (726)  13  -18  2005/03/07  [Not refereed][Not invited]
  • ONODERA Masaki, KAWAMURA Hidenori, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  104-  (726)  1  -6  2005/03/07  [Not refereed][Not invited]
     
    In this paper, we propose the partially exhaustive evaluation Monte Carlo Method, which improves the accuracy of estimation of expected value, and evaluate the effectiveness of the proposed method. Moreover, we apply the proposed method to the Tour Planning Problem, which includes the uncertainty that a result to a single solution cannot be determined uniquely. From experimental results, it has been confirmed that the accuracy of estimation is improved by the proposed method, and as a result, the effectiveness of searching is improved.
  • MORI Yasunao, KAWAMURA Hidenori, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  104-  (726)  13  -18  2005/03/07  [Not refereed][Not invited]
     
    In a distributed computer system configurated by some kinds of servers, it becomes pupular that the research and development of technology which allocate dynamically resource to each server adapiting to changing workloads. In this paper, We propose the dynamic network resource allocation system by using response threshold reinforcement model in social insects, and verify the effect by simulation.
  • 川村秀憲, 本山恵子, 山本雅人, 大内東  情報処理学会全国大会講演論文集  67th-  (3)  83  -84  2005/03/02  [Not refereed][Not invited]
  • 川村秀憲, 大内東  日本オペレーションズ・リサーチ学会和文論文誌  48-  2005
  • TAKAYA TOSHIHIKO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  飛行機シンポジウム講演集(CD-ROM)  43rd-  2D5  2005  [Not refereed][Not invited]
  • Qualititative Analysis of Self-organizing Multiagent Interaction with Entropy and Mutual Information
    Proceedings of the Tenth International Symposium on Artificial Life and Robotics (AROB 10th '05)  CD-ROM  2005  [Not refereed][Not invited]
  • Evaluating a Solution of Tour Planning Problem Based on the Partially Exhaustive Exploration Monte Carlo Method
    Proceedings of the Tenth International Symposium on Artificial Life and Robotics (AROB 10th '05)  CD-ROM  2005  [Not refereed][Not invited]
  • Multiagent Simulation of Customer-driven Reservation Adjustment Mechanism
    Proceedings of the 9th Japan and Australia Joint Workshop on Intelligent and Evolutionary Systems 2005  CD-ROM  2005  [Not refereed][Not invited]
  • M Nagao, H Kawamura, M Yamamoto, A Ohuchi  Soft Computing as Transdisciplinary Science and Technology  285  -294  2005  [Not refereed][Not invited]
     
    Recently, tourism activity analysis has been required in order to construct effective tourism policy and strategy for personal tour which became the mainstream Of Japan. In conventional tourism activity analysis, the information for analysis, i.e., tourism activity information, is collected on each tourist by using questionnaire, and then the analysis is carried out on the basis of it. However, it is difficult to realize effective tourism activity analysis in conventional method because the difficulty in collecting accurate questionnaire-based information collection has and detailed tourism activity information. In this paper, we propose a GPS log mining method in order to implement effective tourism activity analysis. GPS can automatically and continuously collect the position information where the GPS receiver exists. It is likely that an effective tourism activity analysis can be realized by extracting accurate tourism activity information from the information which is collected by GPS. We confirm the effectiveness of the proposed method through the experiments using the GPS log data collected from actual tourists in Hokkaido.
  • CPU Resource Double Auction System with An Anonymous Protocol
    Proceedings of the Tenth International Symposium on Artificial Life and Robotics (AROB 10th '05)  CD-ROM  2005  [Not refereed][Not invited]
  • Toshihiko Takaya, Hidenori Kawamura, Yoshihiro Minagawa, Masahito Yamamoto, Azuma Ohuchi  Artificial Life and Robotics  10-  (2)  177  -184  2005  [Not refereed][Not invited]
     
    Blimp robots are attractive as indoor flying robots because they can float in the air, land safely with low energy, and stay in motion for a long time compared with other flying robots. However, controlling blimp robots is difficult because they have nonlinear characteristics, are influenced by air streams, and can easily be influenced by inertia. Therefore, a robust and adaptive control system is needed for blimp robots. The applied research that has studied the features of indoor flying robots in recent years has prospered. Operating an indoor blimp robot for a long time is difficult because the payload is small, multiple batteries cannot be stacked, and the design of a thruster that gives freedom to the entire blimp robot is difficult. Therefore, an autonomous charge that allows operation for a long time is needed. We have developed a method of landing with orbital control of the charge point that gives autonomy to a blimp robot. The possibility of landing with orbital control is shown. © ISAROB 2006.
  • K Nishikawa, H Kawamura, A Ohuchi  Soft Computing as Transdisciplinary Science and Technology  316  -323  2005  [Not refereed][Not invited]
     
    In the research of a multiagent system, the indicators such as a task achievement ratio and a payoff have been used for analyzing a system. These indicators are important for the point that agents need to accomplish a task. However they are inadequate to make clear the entity of phenomena that occur in complex system, because they are specialized in the target system and the analysis is also specialized. In these respects the approaches that analyze a system quantitatively are begun to investigate in recent years. In our research, we propose the approach that analyzes a multiagent system quantitatively by focusing on the dynamics of a system and interaction among multiagents. We use two indicators, i.e., entropy and mutual information, for analyzing a system. Entropy estimates the behavior of an agent and mutual information estimates interactions between two agents. For verifying these propositions, we conduct verification experiment in the simple slime mold model. The result shows a relationship between agents ' behavioral patterns and two indicators, therefore our approach using entropy and mutual information is available for analyzing a multiagent system.
  • A Location-based Search Engine for Official Web-sites
    IFORS2005 (17th Triennial Conference of the International Federation of Operations Research Societies)  CD-ROM  2005  [Not refereed][Not invited]
  • TAKAYANAGI TOSHIAKI, KAWAMURA HIDENORI, OUCHI AZUMA  情報処理学会シンポジウム論文集  2004-  (12)  349  -354  2004/10/26  [Not refereed][Not invited]
  • Kadota Hisao, Kawamura Hidenori, Yamamoto Masahito, Takaya Toshihiko, Ohuchi Azuma  The ... international conference on advanced mechatronics : toward evolutionary fusion of IT and mechatronics : ICAM : abstracts  2004-  (4)  47  -47  2004/10/03  [Not refereed][Not invited]
  • 安田恵一郎, 石亀篤司, 黒川太, 小木曽望, 北川慎治, 相吉英太郎, 飯間等, 貝原俊也, 加地太一, 川村秀憲, 北山哲士, 木村孝, 小あくつ成一, 小林容子, 坂本義行, 鈴木昌和, 田村公良, 西川昌宏, 福山良和, 藤川英司, 藤野篤哉, 宮崎道雄, 村山茂樹, 森一之, 森直樹, 安部恵介, 井出東, 岩崎信弘, 岡本卓, 金沢貴彦, 河野幸弘, 河原崎浩一朗, 岸田太一, 北村聖一, 桜内貴彦, 進藤静一, 袖子田志保, 塚田龍也, 中沢親志, 野原勉  電気学会技術報告  (983 CD-ROM)  203P  2004/09/30  [Not refereed][Not invited]
  • 川村 秀憲  システム/制御/情報 : システム制御情報学会誌  48-  (8)  2004/08/15  [Not refereed][Not invited]
  • KADOTA HISAO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, TAKAYA TOSHIHIKO, OHUCHI AZUMA  IPSJ journal  45-  (6)  1715  -1724  2004/06/15  
    Balloon robots have attracted attention as new type indoor robots for various applications, e.g., observation, guidance, and amusement flying. A balloon robot can float and move long time in 3-dimensional space by low energy. However, it is difficult to control positioning of a balloon robot because it has great inertia and is easily effected by a little air stream of a conditioner. Positioning control under usual indoor environment is key technology to realize an autonomous balloon robot. In this paper, we develop the indoor-type balloon robot system with a light wireless vision camera. The balloon robot is controlled to keep at the target position based on simple vision processing and PD-controller. Vision processing is realized by perceiving a red circle on the floor as a landmark. In the experiments, several PD settings are investigated for positioning control, and we conclude the paper by that P-controller is suitable to keep at the target position and PD-controller successfully works to go in the direction of target from far position.
  • ONO TAKASHI, NAKATSUGAWA MASASHI, YAMAMOTO MASAHITO, KAWAMURA HIDENORI, NAKANO SABURO, HASHIMOTO NOBUO, OUCHI AZUMA  電気学会情報システム研究会資料  IS-04-  (31-36)  11  -15  2004/06/09  [Not refereed][Not invited]
  • SHINOHARA TOSHIO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  電子情報通信学会技術研究報告  103-  (726(AI2003 99-109))  1  -6  2004/03/17  [Not refereed][Not invited]
  • OKADA YASUSHI, KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  電子情報通信学会技術研究報告  103-  (726(AI2003 99-109))  17  -22  2004/03/17  [Not refereed][Not invited]
  • KATAOKA TAKASHI, KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  電子情報通信学会技術研究報告  103-  (725(AI2003 81-98))  47  -52  2004/03/16  [Not refereed][Not invited]
  • YANAGISAWA NORIKO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  電子情報通信学会技術研究報告  103-  (725(AI2003 81-98))  71  -76  2004/03/16  [Not refereed][Not invited]
  • NAGAO MITSUYOSHI, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  電子情報通信学会技術研究報告  103-  (724(AI2003 76-80))  7  -12  2004/03/15  [Not refereed][Not invited]
  • ONODERA MASAKI, KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  電子情報通信学会技術研究報告  103-  (724(AI2003 76-80))  13  -18  2004/03/15  [Not refereed][Not invited]
  • TSUJI MASAYUKI, KAWAMURA HIDENORI, OUCHI AZUMA  電子情報通信学会技術研究報告  103-  (724(AI2003 76-80))  19  -24  2004/03/15  [Not refereed][Not invited]
  • NAGAO Mitsuyoshi, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IPSJ SIG Notes. ICS  2004-  (29)  7  -12  2004/03/15  [Not refereed][Not invited]
     
    In this paper, we propose a GPS log data mining method for acquisition of tourism information. Recently, the number of tourists which utilize rent-a-car has extremely increased according to shift of tourism type from group tour to personal tour. Therefore, in this research, we perform the extraction of personal behavior information which is effective for tourism information from GPS log data in rent-a-car tour. Currently, the position detection with high accuracy can be performed by using GPS because SA which leads to decrease of accuracy has been removed. However, when GPS is independently...
  • ONODERA Masaki, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2004-  (29)  13  -18  2004/03/15  [Not refereed][Not invited]
     
    About automatic decision-making by the software in fields, such as electronic commerce, the action-value function, which is in consideration of the uncertainty using the expected value, was designed. Moreover, as a way method which raises the accuracy of calculation of an expected value, Monte Carlo method with partial exhaustive investigation was proposed, and the validity was verified by experiment. At the end, the action-value function was applied to TAG CLASSIC, and the validity was checked.
  • TSUJI Masayuki, KAWAMURA Hidenori, OHUCHI Azuma  IPSJ SIG Notes. ICS  2004-  (29)  19  -24  2004/03/15  [Not refereed][Not invited]
     
    In this paper, we design a multiagent market model with network externality, and evaluate the effectiveness of present strategy, which is one of sales promortion like that a sales corporation chooses customers in a market and gives him/her a product without compensation. The proposed multiagent model can clearly involve a customers interaction network, and we can clarify the relationship between the effectiveness of network externality and the structure of customers interaction network. In the computer simulations, we evaluate the effectiveness of two present strategies ; a simple present s...
  • KATAOKA Takashi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2004-  (29)  77  -82  2004/03/15  [Not refereed][Not invited]
     
    Recently it is considered that the congestion information services will provide with a development of ubiquitous environment. But it has been cleared that congestion avoidance behavior based on congestion information is not always optimum. In this paper, we investigate effect of congestion information with multiagent simulation in theme park problem. Then we focus on degree of congestion and delay time between selecting destination and arriving, which is considered to affect the effect of congestion information.
  • YANAGISAWA Noriko, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IPSJ SIG Notes. ICS  2004-  (29)  101  -106  2004/03/15  [Not refereed][Not invited]
     
    In most presented researches on multi agent systems, the macroscopic system performance is discussed with such specific measures as gain or achievement. These measures are still important, but when we observe the complex system, it is impossible to understand the essentials of its behavior only using these measures. Therefore we propose an analysis method with entropy and mutual information, the essential terms to analyze the complex system related to macroscopic characteristics. Consequently, we verify the validity of quantitative analysis using entropy and mutual information.
  • SHINOHARA Toshio, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IPSJ SIG Notes. ICS  2004-  (29)  137  -142  2004/03/15  [Not refereed][Not invited]
     
    Reservation systems, such as an airline ticket and a concert ticket, are first-come firest-served resource allocation mechanisms. In this paper, we propose a resource allocation adjustment mechanism which performs reservation adjustment by customer driven, and verify effectiveness of the mechanism for various demand structures by the multi-agent simulation.
  • OKADA Yasushi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2004-  (29)  153  -158  2004/03/15  [Not refereed][Not invited]
     
    In this study, we simulate the case in which distributed generations spread using the artificial electricity market by X-Economy System, and analize the surplus arose in power generation equipment of a power producer with distributed generations spread, the effect, the influence of at the time of cutting down and the level of the sale price in that case, and the influence on stability, consequently distributed power supplies. As the result, we found that competition in a market increased by that and a market price fell was obtained. Moreover, when the users who employ a distributed power su...
  • SHINOHARA Toshio, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  103-  (726)  1  -6  2004/03/10  [Not refereed][Not invited]
     
    Reservation systems, such as an airline ticket and a concert ticket, are first-come firest-served resource allocation mechanisms. In this paper, we propose a resource allocation adjustment mechanism which performs reservation adjustment by customer driven, and verify effectiveness of the mechanism for various demand structures by the multi-agent simulation.
  • OKADA Yasushi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  103-  (726)  17  -22  2004/03/10  [Not refereed][Not invited]
     
    In this study, we simulate the case in which distributed generations spread using the artificial electricity market by X-Economy System, and analize the surplus arose in power generation equipment of a power producer with distributed generations spread, the effect, the influence of at the time of cutting down and the level of the sale price in that case, and the influence on stability, consequently distributed power supplies. As the result, we found that competition in a market increased by that and a market price fell was obtained. Moreover, when the users who employ a distributed power su...
  • KATAOKA Takashi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  103-  (725)  47  -52  2004/03/09  [Not refereed][Not invited]
     
    Recently it is considered that the congestion information services will provide with a development of ubiquitous environment. But it has been cleared that congestion avoidance behavior based on congestion information is not always optimum. In this paper, we investigate effect of congestion information with multiagent simulation in theme park problem. Then we focus on degree of congestion and delay time between selecting destination and arriving, which is considered to affect the effect of congestion information.
  • YANAGISAWA Noriko, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  103-  (725)  71  -76  2004/03/09  [Not refereed][Not invited]
     
    In most presented researches on multi agent systems, the macroscopic system performance is discussed with such specific measures as gain or achievement. These measures are still important, but when we observe the complex system, it is impossible to understand the essentials of its behavior only using these measures. Therefore we propose an analysis method with entropy and mutual information, the essential terms to analyze the complex system related to macroscopic characteristics. Consequently, we verify the validity of quantitative analysis using entropy and mutual information.
  • NAGAO MItsuyoshi, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  103-  (724)  7  -12  2004/03/08  [Not refereed][Not invited]
     
    In this paper, we propose a GPS log data mining method for acquisition of tourism information. Recently, the number of tourists which utilize rent-a-car has extremely increased according to shift of tourism type from group tour to personal tour. Therefore, in this research, we perform the extraction of personal behavior information which is effective for tourism information from GPS log data in rent-a-car tour. Currently, the position detection with high accuracy can be performed by using GPS because SA which leads to decrease of accuracy has been removed. However, when GPS is independently...
  • ONODERA Masaki, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  103-  (724)  13  -18  2004/03/08  [Not refereed][Not invited]
     
    About automatic decision-making by the software in fields, such as electronic commerce, the action-value function, which is in consideration of the uncertainty using the expected value, was designed. Moreover, as a way method which raises the accuracy of calculation of an expected value, Monte Carlo method with partial exhaustive investigation was proposed, and the validity was verified by experiment. At the end, the action-value function was applied to TAG CLASSIC, and the validity was checked.
  • TSUJI Masayuki, KAWAMURA Hidenori, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  103-  (724)  19  -24  2004/03/08  [Not refereed][Not invited]
     
    In this paper, we design a multiagent market model with network externality, and evaluate the effectiveness of present strategy, which is one of sales promortion like that a sales corporation chooses customers in a market and gives him/her a product without compensation. The proposed multiagent model can clearly involve a customers interaction network, and we can clarify the relationship between the effectiveness of network externality and the structure of customers interaction network. In the computer simulations, we evaluate the effectiveness of two present strategies; a simple present st...
  • Mutliagent Analysis of Customer-Driven Reservation System
    Proceedings of the Fifth Asia-Pacific Industrial Engineering and Management Systems Conference 2004  CD-ROM  2004  [Not refereed][Not invited]
  • A Study on Digital Archive For Field (Outdoor) Sculpture on Constructing Hokkaido Sculpture Web
    Proceedings of the Fifth Asia-Pacific Industrial Engineering and Management Systems Conference 2004  CD-ROM  2004  [Not refereed][Not invited]
  • Vision-Based Motion Control of Indoor Blimp Robot
    Proceedings of The 4th International Conference on Advanced Mechatronics -Toward Evolutionary Fusion of IT and Mechatronics- 2004  CD-ROM  2004  [Not refereed][Not invited]
  • Acquisition of Personal Tourism Activity Information Based on GPS Log Mining Method
    Mitsuyoshi Nagao, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi  Proceedings of the Fifth Asia-Pacific Industrial Engineering and Management Systems Conference 2004  CD-ROM  2004  [Not refereed][Not invited]
  • Vision-based Positioning System for Indoor Blimp Robot
    Hisao Kadota, Hidenori Kawamura, Masahito Yamamoto, Toshihiko Takaya, Azuma Ohuch  Proceedings of 5th IFAC/EURON Symposium on Intelligent Autonomous Vehicles (2004)  CD-ROM  2004  [Not refereed][Not invited]
  • Design of Vision-Based Motion Control System for Balloon Robot
    Proceedings of The Ninth International Symposium on Artificial Life and Robotics, AROB 9th '04  325  -328  2004  [Not refereed][Not invited]
  • An Efficient Collection Method of Official Websites by Robot Program
    Proceedings of the Fifth Asia-Pacific Industrial Engineering and Management Systems Conference 2004  CD-ROM  2004  [Not refereed][Not invited]
  • Hidenori Kawamura, Koichi Kurumatani, Azuma Ohuchi  MULTI-AGENT FOR MASS USER SUPPORT  3012-  48  -69  2004  [Refereed][Not invited]
     
    We propose the Theme Park Problem as one example of test bed for mass user support. The objective of the problem's solution is to coordinate many visiting agents' behavior in a way that increases social welfare without reducing individual satisfaction. For the computer simulation, we design four types of basic coordination algorithms, and the simulation's results are used to discuss the basic characteristics of the problem.
  • OHUCHI Azuma, KURIHARA Masahito, MITAMURA Tamotsu, KAWAMURA Hidenori, MIYAKOSHI Akio, NAKAGAWA Toshio, MIYAMOTO Shin-ichi, YAMAMOTO Naoya, YANAI Osamu  医療情報学 = Japan journal of medical informatics  23-  (4)  293  -302  2003/10/01  [Not refereed][Not invited]
     
    郡市医師会へのテレビ会議システムの導入可能性を，効果と費用の観点から定量的に検討するために，北海道医師会をモデルとした費用効果を試算した．テレビ会議システムの典型的なモデル仕様を構築し，北海道医師会における会議や集会の一定割合をテレビ会議に置き換えた場合の移動距離および移動時間の短縮を時間的効果として評価した．費用については，旅費，旅費削減率，システム構築費用，通信料，および置換率の５つのパラメータに基づいて，年次毎の費用節約の累積を評価した．その結果，置換率が100％のときは２年間，置換率が50％のときは３年間で，旅費節約の累積がシステム構築維持費用を上回るとの試算を得た．したがって，北海道医師会におけるテレビ会議システムの導入は，費用対効果の観点から望ましいと結論できる．In order to evaluate the cost and effect quantitatively in the feasibility study of deployingvideoconferencing systems in prefectural medical associations, we developed and applied acost-effect model to Hokkaido Medical Association (HMA). We introduced a ...
  • TAKAGI Kohichiro, YAMAMOTO Masahito, NAKATSUGAWA Masashi, KAWAMURA Hidenori, OHUCHI Azuma  IPSJ SIG Notes. ICS  2003-  (90)  99  -104  2003/09/14  [Not refereed][Not invited]
     
    It is becoming increasingly difficult to find desired information from the World Wide Web (WWW) due to its rapid growth, and especially, to find web pages belonging to a certain category. For example, it is difficult for tourists to search for official accommodation websites such as hotels and pensions in the area that they will visit. Existing search engines are not suitable for this purpose because these search engines utilize some keywords to extract the information, and accommodation websites do not always contain the most common words. In this paper, we develop an automatic collection ...
  • TAKAGI Kohichiro, YAMAMOTO Masahito, NAKATSUGAWA Masashi, KAWAMURA Hidenori, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  103-  (305)  31  -36  2003/09/08  [Not refereed][Not invited]
     
    It is becoming increasingly difficult to find desired information from the World Wide Web (WWW) due to its rapid growth, and especially, to find web pages belonging to a certain category. For example, it is difficult for tourists to search for official accommodation websites such as hotels and pensions in the area that they will visit. Existing search engines are not suitable for this purpose because these search engines utilize some keywords to extract the information, and accommodation websites do not always contain the most common words. In this paper, we develop an automatic collection ...
  • KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  情報処理学会研究報告  2003-  (39(UBI-1))  57  -64  2003/04/25  [Not refereed][Not invited]
  • HAMADA TAKAHIRO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  電子情報通信学会技術研究報告  102-  (615(AI2002 47-60))  7  -12  2003/01/31  [Not refereed][Not invited]
  • KANEHIRA DAISUKE, KAWAMURA HIDENORI, KURUMATANI KOICHI, IZUMI KIYOSHI, OUCHI AZUMA  電子情報通信学会技術研究報告  102-  (614(AI2002 33-46))  47  -52  2003/01/30  [Not refereed][Not invited]
  • SASAKI YUICHI, KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  電子情報通信学会技術研究報告  102-  (614(AI2002 33-46))  41  -46  2003/01/30  [Not refereed][Not invited]
  • KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  電子情報通信学会技術研究報告  102-  (613(AI2002 23-32))  25  -30  2003/01/29  [Not refereed][Not invited]
  • OKADA YASUSHI, KAWAMURA HIDENORI, NAKAMURA JIN'YA, IZUMI KIYOSHI, KURUMATANI KOICHI, KAWANO KOJI, OUCHI AZUMA  電子情報通信学会技術研究報告  102-  (613(AI2002 23-32))  53  -58  2003/01/29  [Not refereed][Not invited]
     
    In this study, we make a model of electricity market supposing that power industry is separated into the power generation section and the power distribution section. We assume that electricity market consists of day-ahead market and realtime market. In order to research effect that consumer type has on the power distribution agent's tactics, we simulate electricity market. As a result, we found that power distribution agents that have consumers that demand much power of high costs choose tactics to buy much power in day-ahead market.
  • KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2003-  (8)  25  -30  2003/01/29  [Not refereed][Not invited]
     
    In this paper, we propose "theme park problem" as one of test bet problem with huge agents' scheduling problem. Especially, we develop typical Mass-User support with coordination shceduling algorithm, and investigate the possibility of mass-user support based on multiagent computer simulations.
  • OKADA Yasushi, KAWAMURA Hidenori, NAKAMURA Jinya, IZUMI Kiyoshi, KURUMATANI Koichi, KAWANO Koji, OHUCHI Azuma  IPSJ SIG Notes. ICS  2003-  (8)  53  -58  2003/01/29  [Not refereed][Not invited]
     
    In this study, we make a model of electricity market supposing that power industry is separated into the power generation section and the power distribution section. We assume that electricity market consists of day-ahead market and realtime market. In order to research effect that consumer type has on the power distribution agent's tactics, we simulate electricity market. As a result, we found that power distribution agents that have consumers that demand much power of high costs choose tactics to buy much power in day-ahead market.
  • SASAKI Yuichi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2003-  (8)  99  -104  2003/01/29  [Not refereed][Not invited]
     
    In this research, we take up the key currency as an important factor of considering world economy and international trade. We propose an international trade model with the currency credibility as a criterion of selection of the payment method. We observe the process of emergence of key currency.
  • KANEHIRA Daisuke, KAWAMURA Hidenori, KURUMATANI Koichi, IZUMI Kiyoshi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2003-  (8)  105  -110  2003/01/29  [Not refereed][Not invited]
     
    Recent years. Much researchers study an agent base artificial market model. However whose model of the market built by research of these many was either the model of itayose system, or a model of a zaraba system. In our experiment which builds both the market of itayose system, and the market of a zaraba system as a market model. Supplies a study agent as a trader in it in this paper, and verifies the action of the market As a result of comparing the theoretical equilibrium price obtained from a demand curve and a supply curve with the agreement price actually obtained, in the market built ...
  • HAMADA Takahiro, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IPSJ SIG Notes. ICS  2003-  (8)  145  -150  2003/01/29  [Not refereed][Not invited]
     
    A simple model of tag-mediated decision making for players playing the one-shot prisoner's dilemma game is described. In our simulation, tags, which are visible from each other, and there is no relation between the player's tag and the one's strategy firstly. The player's decision making is based on the partner's tag, and the player's strategy is evolved within the same tag members. We examine the effect of the difference in the rate, which is the number of the members having the same tag, and consider which is more advantageous between the minority group and majority one.
  • HAMADA Takahiro, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  102-  (615)  7  -12  2003/01/24  [Not refereed][Not invited]
     
    A simple model of tag-mediated decision making for players playing the one-shot prisoner's dilemma game is described. In our simulation, tags, which are visible from each other, and there is no relation between the player's tag and the one's strategy firstly. The player's decision making is based on the partner's tag, and the player's strategy is evolved within the same tag members. We examine the effect of the difference in the rate, which is the number of the members having the same tag, and consider which is more advantageous between the minority group and majority one.
  • SASAKI Yuichi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  102-  (614)  41  -46  2003/01/23  [Not refereed][Not invited]
     
    In this research, we take up the key currency as an important factor of considering world economy and international trade. We propose an international trade model with the currency credibility as a criterion of selection of the payment method. We observe the process of emergence of key currency.
  • KANEHIRA Daisuke, KAWAMURA Hidenori, KURUMATANI Koichi, IZUMI Kiyoshi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  102-  (614)  47  -52  2003/01/23  [Not refereed][Not invited]
     
    Recent years. Much researchers study an agent base artificial market model. However whose model of the market built by research of these many was either the model of itayose system, or a model of a zaraba system. In our experiment which builds both the market of itayose system, and the market of a zaraba system as a market model. Supplies a study agent as a trader in it in this paper, and verifies the action of the market As a result of comparing the theoretical equilibrium price obtained from a demand curve and a supply curve with the agreement price actually obtained, in the market built ...
  • KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  102-  (613)  25  -30  2003/01/22  [Not refereed][Not invited]
     
    In this paper, we propose "theme park problem" as one of test bet problem with huge agents' scheduling problem. Especially, we develop typical Mass-User support with coordination scheduling algorithm, and investigate the possibility of mass-user support based on multiagent computer simulations.
  • OKADA Yasushi, KAWAMURA Hidenori, NAKAMURA Jinya, IZUMI Kiyoshi, KURUMATANI Koichi, KAWANO Koji, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  102-  (613)  53  -58  2003/01/22  [Not refereed][Not invited]
     
    In this study, we make a model of electricity market supposing that power industry is separated into the power generation section and the power distribution section. We assume that electricity market consists of day-ahead market and realtime market. In order to research effect that consumer type has on the power distribution agent's tactics, we simulate electricity market. As a result, we found that power distribution agents that have consumers that demand much power of high costs choose tactics to buy much power in day-ahead market.
  • NISHIMURA AYAKO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  情報処理学会シンポジウム論文集  2003-  (1)  13  -18  2003/01/13  [Not refereed][Not invited]
  • YANAGISAWA NORIKO, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  情報処理学会シンポジウム論文集  2003-  (1)  1  -6  2003/01/13  [Not refereed][Not invited]
  • Analysis of the Competition in Electricity Market Using Multi-Agent Simulation Model
    Proceedings of the International Workshop on Agent-Based Modeling in Conjunction with the 17th Annual Conference of the Japanese Society for Artificial Intelligence 2003  67  -78  2003  [Not refereed][Not invited]
  • Design of Adaptive Trading Strategy for Trading Agent Competition
    Masaki Onodera, Hidenori Kawamura, Masahito Yamamoto, Koichi Kurumatani, Azuma Ohuchi  Proceedings of International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) 2003  337  -340  2003  [Not refereed][Not invited]
  • Keiko Motoyama, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi  IFIP Advances in Information and Communication Technology  112-  191  -198  2003  [Not refereed][Not invited]
     
    The purpose of this study is to realize an autonomous robotic blimp. While this robot can pass over terrain that may be impossible for land-based robots to negotiate, it is hard to control autonomously because it is subjected to strong inertial forces and air resistance. We are now designing an autonomously controlled indoor blimp, which will be suitable for use in for inspections or monitoring tasks and as an amusement robot or guide robot. © 2003 by Springer Science+Business Media New York.
  • Investigation of Global Performance Effected by Congestion Avoidance Behavior in Theme Park Problem
    Proceedings of 2003 Asia Pacific Symposium on Intelligent and Evolutionary Systems: Technology and Applications  63  -70  2003  [Not refereed][Not invited]
  • Design of Evaluation Function in Motion Planning for Autonomous Balloon Robot
    Proceedings of 2003 Asia Pacific Symposium on Intelligent and Evolutionary Systems: Technology and Applications  190  -195  2003  [Not refereed][Not invited]
  • Vision-based Control of Autonomous Flying Airship Robot
    Proceedings of International Technical Conference on Circuits/Systems,Computers and Communications(ITC-CSCC) 2003  628  -631  2003  [Not refereed][Not invited]
  • 岡田靖司, 川村秀憲, 車谷浩一, 大内東  情報科学技術フォーラム  FIT 2002-  287  -288  2002/09/13  [Not refereed][Not invited]
  • 川村秀憲, 車谷浩一, 大内東  情報科学技術フォーラム  FIT 2002-  71  -72  2002/09/13  [Not refereed][Not invited]
  • Kawamura Hidenori, Kurumatani Koichi, Ohuchi Azuma  情報科学技術フォーラム学術系・企業系予稿集  2002-  (0)  71  -72  2002/09/13  [Not refereed][Not invited]
  • Okada Yasushi, Kawamura Hidenori, Kurumatani Koichi, Ohuchi Azuma  情報科学技術フォーラム一般講演論文集  2002-  (2)  287  -288  2002/09/13  [Not refereed][Not invited]
  • 川村 秀憲, 車谷 浩一, 大内 東  シンポジウム  0-  (48)  33  -37  2002/09/10  [Not refereed][Not invited]
  • 大内東, 川村秀憲  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2002-  70  -71  2002/03/27  [Not refereed][Not invited]
  • 大内 東, 川村 秀憲  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2002-  (0)  70  -71  2002/03/27  [Not refereed][Not invited]
  • SASAKI YUICHI, KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  電子情報通信学会技術研究報告  101-  (536(AI2001 68-81))  49  -56  2002/01/10  [Not refereed][Not invited]
  • KANEHIRA DAISUKE, KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  電子情報通信学会技術研究報告  101-  (536(AI2001 68-81))  57  -64  2002/01/10  [Not refereed][Not invited]
  • HAMADA Takahiro, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IPSJ SIG Notes. ICS  2002-  (1)  127  -134  2002/01/09  [Not refereed][Not invited]
     
    In generally, we often play a game against the entity, which we do not know what really is. In the case, the result of the game is often dependent on the scale of participant and the other players' strategies, but we may not get their information. And all we can know is the result. We are to investigate the player's behavior and the behavior as a whole of players in such the environment. So, we make a simple model to study the behavior of players when against the entity whose decision-making system is not clearly known to them.
  • SASAKI Yuichi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2002-  (1)  143  -150  2002/01/09  [Not refereed][Not invited]
     
    In this research we take up the key currency as an important factor of considering world economy and international trade. We propose an international trade model with the currency credibility as a criterion of selection of the payment method, and construct artificial international trade markets. In proposed model, we observe the process of emergence of key currency. In the simulation, we consider how the behavior of market would change, by altering combination of agents. The results of simulations show that the agents, which deal in currencies for speculation, not only stabilize currency ex...
  • KANEHIR Daisuke, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IPSJ SIG Notes. ICS  2002-  (1)  151  -158  2002/01/09  [Not refereed][Not invited]
     
    This paper describes the research about a relationship between complexity of information structure and behavior of artificial market with learning trader agent. We attempt three experiments with two kinds of traders, and adopt correlation dimension analysis in order to measure behavior of artificial market. As a result, we show the information structure is related with the macro behavior of market although the information is not related with the essential worth of the stock.
  • HAMADA Takahiro, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  101-  (536)  33  -40  2002/01/03  [Not refereed][Not invited]
     
    In generally, we often play a game against the entity, which we do not know what really is. In the case, the result of the game is often dependent on the scale of participant and the other players' strategies, but we may not get their information. And all we can know is the result. We are to investigate the player's behavior and the behavior as a whole of players in such the environment. So, we make a simple model to study the behavior of players when against the entity Whose decision-making system is not clearly known to them.
  • SASAKI Yuichi, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  101-  (536)  49  -56  2002/01/03  [Not refereed][Not invited]
     
    In this research we take up the key currency as an important factor of considering world economy and international trade. We propose an international trade model with the currency credibility as a criterion of selection of the payment method, and construct artificial international trade markets. In proposed model, we observe the process of emergence of key currency. In the simulation, we consider how the behavior of market would change, by altering combination of agents. The results of simulations show that the agents, which deal in currencies for speculation, not only stabilize currency ex...
  • KANEHIR Daisuke, KAWAMURA Hidenori, KURUMATANI Koichi, OHUCHI Azuma  IEICE technical report. Artificial intelligence and knowledge-based processing  101-  (536)  57  -64  2002/01/03  [Not refereed][Not invited]
     
    This paper describes the research about a relationship between complexity of information structure and behavior artificial market with learning trader agent. We attempt three experiments with two kinds of traders, and adopt correlation dimension analysis in order to measure behavior of artificial market. As a result, we show the information structure is related with the macro behavior of market although the information is not related with the essential worth of the stock.
  • KAWAMURA HIDENORI, KURUMATANI KOICHI, OUCHI AZUMA  エージェント合同シンポジウム(JAWS2002)講演論文集 平成14年  423  -424  2002  [Not refereed][Not invited]
  • T Hamada, H Kawamura, M Yamamoto, A Ohuchi  CEC'02: PROCEEDINGS OF THE 2002 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2  101-  (536(AI2001 68-81))  2011  -2016  2002  [Not refereed][Not invited]
     
    We analyze the behavior of players in the situation where they recognize an identical situation as a simple market-like place differently. In our. model a player considers the others as a representative player. We examine the player's behavior when with and without fluidity of players.
  • T Hamada, H Kawamura, M Yamamoto, A Ohuchi  CEC'02: PROCEEDINGS OF THE 2002 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2  2011  -2016  2002  [Not refereed][Not invited]
     
    We analyze the behavior of players in the situation where they recognize an identical situation as a simple market-like place differently. In our. model a player considers the others as a representative player. We examine the player's behavior when with and without fluidity of players.
  • Improved Multiple Ant Colonies System for Traveling Salesman Problems
    "Operations Research/Management Science at Work" in the International Series in Operations Research & Management Science  43-  41  -52  2002  [Not refereed][Not invited]
  • H Kawamura, K Kurumatani, A Ohuchi  PROCEEDINGS OF THE 6TH JOINT CONFERENCE ON INFORMATION SCIENCES  1069  -1072  2002  [Not refereed][Not invited]
     
    We propose a common simulation platform in artificial market and economy called "X-Economy," which provides common agent libraries and a server for multi-agent modeling and simulations in financial and economic systems. Multi-agent approach to economic systems have been successfully developing, and many simulation-based researches have been carried out. Since they basically lack compatibility about agent architecture and communication protocol design, it is difficult to examine and compare the works which are, achieved by others. In X-Economy, we provide a common communication protocol and agent architecture and we aim to increase easiness of exchanging agents used for modeling, simulation, and analysis of financial and economic systems. Especially, we introduce some research programs in X-Economy.
  • Y Sasaki, T Yamashita, H Kawamura, K Kurumatani, A Ohuchi  PROCEEDINGS OF THE 6TH JOINT CONFERENCE ON INFORMATION SCIENCES  1073  -1076  2002  [Not refereed][Not invited]
     
    In this research, we observe the emergence of the key currency in the artificial markets model. The results of simulations show that the existence of the country without the extensive economic power is unnecessary to emerge the key currency.
  • D Kanehira, H Kawamura, K Kurumatani, A Ohuchi  PROCEEDINGS OF THE 6TH JOINT CONFERENCE ON INFORMATION SCIENCES  1077  -1080  2002  [Not refereed][Not invited]
     
    This paper describes research about a relationsip between complexity of information structure and behavior of artificial market with learning trader agent. We attempt Three experiments with two kinds of traders, and adopt correlation dimension analysis in order to measur behavior of artificial market. As a result, we. show the information structure is related with the macro behavior of market although the information is not related with the essential worth of the stock.
  • KAWAMURA Hidenori, OHUCHI Azuma, KURUMATANI Koichi  セルオートマトン・シンポジウム講演論文集  2001-  (0)  40  -44  2001/11/14  [Not refereed][Not invited]
     
    The economic and finance systems related to dynamic real world are too huge complex systems to understand the principles of these behavior. Many researchers, i.e., economists, mathematicians, sociologists, computer scientists, and so on, have hoped for long time to model and clarify the inner meaning of such phenomenon. The one of difficulty for these researches is for lack of paradigm that describes the relationship between realistic economic agents with bounded learning or evolving rationality and the emergence macro behavior as aggregation of such agents. Since the first success of resea...
  • KANEHIRA Daisuke, KAWAMURA Hidenori, OHUCHI Azuma, KURUMATANI Koichi  セルオートマトン・シンポジウム講演論文集  2001-  (0)  51  -56  2001/11/14  [Not refereed][Not invited]
     
    In the field of economics, it is said that a market price shows random-walk behavior and cannot be expected. The theory of "Efficient Market Hypothesis" is the basis of this behavior. This theory is considered that all traders are homogeneous. However, it is appropriate to a trader is heterogeneous. And price fluctuation like a bubble phenomenon in recent years is the phenomenon which cannot explain sufficiently in the economics. Then, the artificial market research by the agent base simulation is appearing as new approach for solving such a phenomenon. There are many factors, such as econo...
  • YAMAMOTO Takahito, KAWAMURA Hidenori, OHUCHI Azuma, KURUMATANI Koichi  セルオートマトン・シンポジウム講演論文集  2001-  (0)  57  -62  2001/11/14  [Not refereed][Not invited]
     
    In recent years, it has been popular that economic and financial system is researched by multi-agent approach of Artificial Intelligence. The representative system is Artificial Market. Almost all of the researchers report the behavior of macro market prices constracted by micro trading agents who invest in single investment. But market participants in real Market make decision on plural investment outlets. If we extends a market model dealing plural investments, the market participants can make the portfolio dealing with the plural brands. Portfolio means the composition of assets. If mark...
  • 川村秀憲, 大内東, 車谷浩一  オペレーションズ・リサーチ  46-  (10)  537  -543  2001/10/01  [Not refereed][Not invited]
  • 兼平大輔, 川村秀憲, 大内東, 車谷浩一  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2001-  252  -253  2001/05/01  [Not refereed][Not invited]
  • 佐々木雄一, 川村秀憲, 大内東, 車谷浩一  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2001-  254  -255  2001/05/01  [Not refereed][Not invited]
  • 川村秀憲, 山本雅人, 大内東, 車谷浩一  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2001-  250  -251  2001/05/01  [Not refereed][Not invited]
  • 川村 秀憲, 山本 雅人, 大内 東, 車谷 浩一  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2001-  (0)  250  -251  2001/05/01  [Not refereed][Not invited]
  • 兼平 大輔, 川村 秀憲, 大内 東, 車谷 浩一  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2001-  (0)  252  -253  2001/05/01  [Not refereed][Not invited]
  • 佐々木 雄一, 川村 秀憲, 大内 東, 車谷 浩一  日本オペレーションズ・リサーチ学会春季研究発表会アブストラクト集  2001-  (0)  254  -255  2001/05/01  [Not refereed][Not invited]
  • KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA, KURUMATANI KOICHI  電子情報通信学会技術研究報告  100-  (529(AI2000 41-55))  61  -66  2001/01/10  [Not refereed][Not invited]
  • Kawamura Hidenori, Yamamoto Masahito, Ohuchi Azuma, Kurumatani Kouichi  IPSJ SIG Notes. ICS  2001-  (1)  61  -66  2001/01/10  [Not refereed][Not invited]
     
    In this paper, we report the prototype architecture of X-Economy System including X-Economy Server and Clients. X-Economy is the project aiming for foundation of standard problem as artificial social and economic systems. By X-Economy system, it will be possible to construct arbitrary system design for investigation of behavior of social and economic systems between micro scale agents and macro scale.
  • Kawamura Hidenori, Yamamoto Masahito, Ohuchi Azuma, Kurumatani Kouichi  IEICE technical report. Artificial intelligence and knowledge-based processing  100-  (529)  61  -66  2001/01/03  [Not refereed][Not invited]
     
    In this paper, we report the prototype architecture of X-Economy System including X-Economy Server and Clients.X-Economy is the project aiming for foundation of standard problem as artificial social and economic systems.By X-Economy system, it will be possible to construct arbitrary system design for investigation of behavior of social and economic systems between micro scale agents and macro scale.
  • T Yamashita, H Kawamura, M Yamamoto, A Ohuchi  ICCIMA 2001: FOURTH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND MULTIMEDIA APPLICATIONS, PROCEEDINGS  195  -199  2001  [Not refereed][Not invited]
     
    In this paper We introduce mutual choice mechanism into the norms game instead of direct penal regulation and reformulate the norms game with mutual choice. In order to examine how the proportion of metanorm players to all players influences on the establishment of norm in the metanorms game with mutual choice, we perform simulation under several proportions of metanorm players. We exclude the game theoretic assumption of uniformity as the metanorm player and observe thf frequency of the establishment of the norm. As a result, we confirm the robustness of mutual choice against insufficiency of the metanorm players.
  • Analysis of Norms Game with Mutual Choice
    Tomohisa Yamashita, Hidenori Kawamura, Masahito Yamamoto, Azuma Ohuchi  Proceedings of JSAI 2001 Internal Workshop on Agent-based Approaches in Economic and Social Complex Systems (AESCS 2001)  123  -130  2001  [Not refereed][Not invited]
  • Development of X-Economy System for Introduction of Artificial Market
    Hidenori Kawamura, Azuma Ohuchi, Koichi Kurumatani  Proceedings of JSAI 2001 Internal workshop on Agent-based Approaches in Economic and Social Complexs (AESCS 2001)  51  -58  2001  [Not refereed][Not invited]
  • KAWAI TAKASHI, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  医療情報学  20-  (Supplement 2)  782  -783  2000/11/23  [Not refereed][Not invited]
  • TANAKA SUGURU, KAWAMURA HIDENORI, YAMAMOTO MASAHITO, OUCHI AZUMA  医療情報学  20-  (Supplement 2)  664  -665  2000/11/23  [Not refereed][Not invited]
  • TANAKA Suguru, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  医療情報学連合大会論文集  20-  (0)  664  -665  2000/11/23  [Not refereed][Not invited]
  • KAWAI Takashi, KAWAMURA Hidenori, YAMAMOTO Masahito, OHUCHI Azuma  医療情報学連合大会論文集  20-  (0)  782  -783  2000/11/23  [Not refereed][Not invited]
  • 川村 秀憲  Journal of Japanese Society for Artificial Intelligence  15-  (6)  992  -992  2000/11/01  [Not refereed][Not invited]
     
    本論文は, 社会性昆虫における生物学的フェロモンコミュニケーションのマルチエージェント工学におけるモデル化と, その応用に関するもので5章よりなる.第1章では生物学と工学における関連研究を概観している.また, それらの研究に立脚してフェロモンの本質を場として捉え, ベクトル空間としてモデル化することでフェロモン型コミュニケーションに基づくエージェントシステムの統一的定義を提案している.続く第2章ではColorni等の最適化アルゴリズムであるアントアルゴリズムに着目し, その欠点を明らかにした上でその克服のため, 複数コロニーの概念とコロニーレベルフェロモン型コミュニケーションを導入したMultiple Ant Colonies Algorithmを提案し, 巡回セールスマン問題に対する性能評価実験によって有効性を示している.第3章ではフェロモン型コミュニケーションに基づく分散型協調問題解決アルゴリズムを提案し, 多目的最適の要素をもつ配送経路問題への適用でその有効性を示している.第4章ではフェロモン型コミュニケーションの自律的獲得に関して述べており, そこではニューラルネットワークと遺伝的アルゴリズムに基づくエージェントが, 動的な環境において進化的コミュニケーションと創発的群知能に基づいて問題解決が図れることを実験によって示している.第5章では一連の研究成果を取りまとめ, ...
  • KAWAMURA HIDENORI, YAMAMOTO MASAHITO, SUZUKI KEIJI, OUCHI AZUMA  自律分散システム・シンポジウム資料  12th-  17  -20  2000/01/21  [Not refereed][Not invited]
  • KAWAMURA Hidenori, YAMAMOTO Masahito, SUZUKI Keiji, OHUCHI Azuma  自律分散システム・シンポジウム資料 = SICE Symposium on Decentralized Autonomous Systems  12-  (0)  17  -20  2000/01/21  [Not refereed][Not invited]
  • H Kawamura, M Yamamoto, K Suzuki, A Ohuchi  INTELLIGENT AUTONOMOUS SYSTEMS 6  527  -534  2000  [Not refereed][Not invited]
     
    In this paper, we focus on evolutionary emergence of communication among multi-agents. As the stage of investigation, we prepare the ants war which needs artificial ant agents to interact each other to win the opponent. Ant agents are constructed with 2-layers neural networks, and evolved by genetic algorithm. Throughout several trials of evolutionary processes, we observed the emergence of two types of pheromones, i.e., the attractive pheromone and the repulsive pheromone. The evolved pheromones were very effective when used in larger number of agents, and this fact represents the emergence of collective intelligence and pheromone communication. According to these results, the collective intelligence and communication among agents are discussed.
  • TERASHIMA MASATO, KAWAMURA HIDENORI, SUZUKI KEIJI, OUCHI AZUMA  インテリジェント・システム・シンポジウム講演論文集  9th-  187  -190  1999/10/20  [Not refereed][Not invited]
  • TERASHIMA Masato, KAWAMURA Hidenori, SUZUKI Keiji, OHUCHI Azuma  インテリジェント・システム・シンポジウム講演論文集 = FAN Symposium : fuzzy, artificial intelligence, neural networks and computational intelligence  9-  (0)  187  -190  1999/10  [Not refereed][Not invited]
  • 北爪秀憲, 中村き良, 川村佳子  電子情報通信学会技術研究報告  99-  (314(US99 44-51))  1999
  • 北爪秀憲, 中村き良, 川村佳子  電子情報通信学会大会講演論文集  1999-  1999
  • 川村佳子, 中村き良, 北爪秀憲  電子情報通信学会大会講演論文集  1999-  1999
  • KAWAMURA HIDENORI, YAMAMOTO MASAHITO, SUZUKI KEIJI, OUCHI AZUMA  最適化シンポジウム講演論文集  3rd-  255  -260  1998/08  [Not refereed][Not invited]
  • KAWAMURA Hidenori, YAMAMOTO Masahito, SUZUKI Keiji, OHUCHI Azuma  インテリジェント・システム・シンポジウム講演論文集 = FAN Symposium : fuzzy, artificial intelligence, neural networks and computational intelligence  7-  (0)  501  -504  1997/11/10  [Not refereed][Not invited]
  • KAWAMURA HIDENORI, YAMAMOTO MASAHITO, SUZUKI KEIJI, OUCHI AZUMA  インテリジェント・システム・シンポジウム講演論文集  7th-  501  -504  1997/11  [Not refereed][Not invited]
  • KAWAMURA Hidenori, MITAMURA Tamotsu, OHUCHI Azuma  全国大会講演論文集  54-  (1)  401  -402  1997/03/12  [Not refereed][Not invited]
     
    配送計画問題 (Vehicle Routing Problem, 以下VRP) は組合わせ最適化問題の一つであり, 従来シミュレーテイッドアニーリング (Simulated Annealing, 以下SA) 法やタブサーチ, 遺伝的アルゴリズムなどによるメタヒューリステイック解法が提案されている. 本稿ではSA法を基礎とし, 探索の履歴を用いた近傍解の生成を提案する.
  • KAWAMURA HIDENORI, MITAMURA TAMOTSU, OUCHI AZUMA  情報処理学会全国大会講演論文集  54th-  (1)  1.401-1.402  1997/03  [Not refereed][Not invited]
  • KAWAMURA HIDENORI, MITAMURA TAMOTSU, YAMAMOTO MASAHITO, OUCHI AZUMA  電気関係学会北海道支部連合大会講演論文集  1996-  12  1996  [Not refereed][Not invited]

Industrial Property Rights

  • 特許第 6900007号:配信装置  
    蕨野 貴之, 酒徳 哲, 大岸 智彦, 川村 秀憲, 山下 倫央, 横山 想一郎  ＫＤＤＩ株式会社, 国立大学法人北海道大学

Awards & Honors

  • 2024/05 The Thirteenth International Conference on Intelligent Systems and Applications(INTELLI 2024) Best Paper Award
     Generation of Captions Highlighting the Differences between a Clothing Image Pair with Attribute Prediction 
    受賞者: Kohei Abe;Soichiro Yokoyama;Tomohisa Yamashita;Hidenori Kawamura
  • 2024/05 8th International Conference on Intelligent Systems Metaheuristics & Swarm Intelligence (ISMSI 2024) Excellent Oral Presentation Award
     
    受賞者: Hirotaka Ooe;Soichiro Yokoyama;Tomohisa Yamashita;Hidenori Kawamura;Mitsuo Tada
  • 2024/03 第123回（令和5年度第3回）福祉情報工学研究会 WIT学生研究奨励賞
     前腕支持型ロボット歩行器の歩行支援を目的とした歩行状態のモデル化と歩行状態の計測 
    受賞者: 森 雄斗;横山 想一郎;山下 倫央;川村 秀憲;森 正人
  • 2024/03 情報処理学会第86回全国大会 学生奨励賞
     大規模言語モデルとChain of Thought Promptingを用いた俳句の評価 
    受賞者: 冨澤峻己;川村秀憲;山下倫央;横山想一郎
  • 2023/12 第95回 高度交通システムとスマートコミュニティ研究会(ITS) 優秀論文賞
     道路ネットワーク階層化における媒介中心性に基づくサブネットワークの連結手法の提案 
    受賞者: 清水 雅之;横山 想一郎;山下 倫央;川村 秀憲
  • 2023/10 北海道大学 第9回 北海道大学部局横断シンポジウム研究助成採択銅賞
     歴史的文書のコーパス分析に対する人工知能技術の応用 
    受賞者: 横山想一郎;山下倫央;川村秀憲;伊藤孝行
  • 2023/10 情報処理北海道シンポジウム2023 研究奨励賞
     ChatGPTを用いた俳句の選句とその評価 
    受賞者: 冨澤峻己;岸田 武竜;横山 想一郎;山下 倫央;川村 秀憲
  • 2023/06 ソフトウェア・シンポジウム 2023 in 仙台 論文奨励賞
     除雪出動決定支援のための除雪関連情報共有サイトの構築 
    受賞者: 大倉 博貴;横山 想一郎;山下 倫央;川村 秀憲
  • 2023/06 ソフトウェア・シンポジウム 2023 in 仙台 論文奨励賞
     人物追跡手法とマッチングアルゴリズムを用いた路線バスにおける乗客 OD 推定 
    受賞者: 西浦 翼;横山 想一郎;山下 倫央;川村 秀憲
  • 2023/03 情報処理学会第85回全国大会 学生奨励賞
     有季定型句の生成における深層学習モデル評価用データセットの作成と適用 
    受賞者: 平田 航大;横山 想一郎;山下 倫央;川村 秀憲
  • 2022/12 The 17th International Conference on Knowledge, Information and Creativity Support Systems (KICSS2022) Outstanding student Paper
     Implementation of Autoregressive Language Models for Generation of Seasonal Fixed-form Haiku in Japanese 
    受賞者: 平田航大;横山想一郎;山下倫央;川村秀憲
  • 2022/12 第91回 高度交通システムとスマートコミュニティ研究会 (ITS) 奨励賞
     灯油配送計画の最適化に向けた道路ネットワークの階層化手法の検証 
    受賞者: 清水 雅之;横山 想一郎;山下 倫央;川村 秀憲
  • 2022/11 情報処理北海道シンポジウム2022 技術研究賞
     タブーサーチを用いた灯油配送のローリングホライズンスケジューリング 
    受賞者: 大江弘峻, 横山想一郎, 山下倫央,川村秀憲, 多田満朗(株式会社ゼロスペック)
  • 2022/11 情報処理北海道シンポジウム2022 研究奨励賞
     人物追跡手法によるバス乗降者数の推定における対象者特定アルゴリズムの開発 
    受賞者: 西浦翼, 横山想一郎, 山下倫央, 川村秀憲, 弓崎潔, 佐藤好美(株式会社シーズラボ)
  • 2022/11 情報処理北海道シンポジウム2022 学術研究賞
     着衣人物画像に対する印象評価と衣服推薦に関する情報提示システムの開発 
    受賞者: 右田幹, 横山想一郎,山下倫央,川村秀憲
  • 2022/03 情報処理学会第84回全国大会 大会優秀賞
     深層学習による自己回帰モデルを用いた俳句生成器の評価 
    受賞者: 平田 航大, 横山 想一郎, 山下 倫央, 川村 秀憲
  • 2022/03 情報処理学会第84回全国大会 学生奨励賞
     深層学習による自己回帰モデルを用いた俳句生成器の評価 
    受賞者: 平田 航大, 横山 想一郎, 山下 倫央, 川村 秀憲
  • 2022/03 情報処理学会第84回全国大会 学生奨励賞
     マスク化言語モデル RoBERTa を用いた俳句の評価 
    受賞者: 花野 愛里咲, 横山 想一郎, 山下 倫央, 川村 秀憲
  • 2021/10 情報処理北海道シンポジウム2021 優秀プレゼンテーション賞
     ECサイト掲載商品の紹介文作成支援システムの開発とメールマガジンによる紹介文評価 
    受賞者: 阿部 涼介;横山 想一郎;山下 倫央;川村 秀憲
  • 2021/10 情報処理北海道シンポジウム2021 技術研究賞
     食品ロス削減に向けた家庭料理の献立作成アルゴリズムの検証 
    受賞者: 細川 万維, 横山 想一郎, 山下 倫央, 川村 秀憲, 関屋 英理子
  • 2021 総務省北海道総合通信局 令和3年度「情報通信月間」北海道総合通信局長表彰
     
    受賞者: 川村 秀憲
  • 2020 情報処理北海道シンポジウム2020 研究奨励賞
     EC サイト掲載商品の紹介文作成支援システムにおける複数文組合せ機能の開発 
    受賞者: 阿部 涼介, 横山 想一郎 , 山下 倫央, 川村 秀憲
  • 2020 情報処理北海道シンポジウム2020 技術研究賞
     前腕支持型四輪歩行器の歩行支援機能の開発, 情報処理北海道シンポジウム2020 
    受賞者: 森 雄斗,横山 想一郎,山下 倫央,川村 秀憲,森 正人,加藤 士雄
  • 2020 情報処理北海道シンポジウム2020 研究奨励賞
     屋内エンターテイメント用バルーンロボットの自律制御システムの開発 
    受賞者: 永田 紘也, 横山 想一郎, 山下 倫央, 川村 秀憲
  • 2020 第20回複雑系マイクロシンポジウム 優秀プレゼンテーション賞
     RC カーを用いた自動運転車両シミュレーション環境の構築 
    受賞者: 織田 智矢, 横山 想一郎, 山下 倫央, 川村 秀憲, 蕨野 貴之, 大岸 智彦, 田中 英明
  • 2019 人工知能学会 研究会優秀賞
     競輪予想記事の自動生成に向けた深層学習によるレース結果予測 
    受賞者: 吉田 拓海, 横山 想一郎, 山下 倫央, 川村 秀憲
  • 2019 情報処理北海道シンポジウム2019 優秀ポスター賞
     自動運転車両の群制御に向けた RC カーを用いたシミュレーション環境の構築 
    受賞者: 織田 智矢, 横山 想一郎, 山下 倫央, 川村 秀憲, 蕨野 貴之, 大岸 智彦, 田中 英明
  • 2019 一般社団法人情報処理学会 山下記念研究賞
     競輪予想記事の自動配信に向けた的中車券予測 
    受賞者: 吉田 拓海, 横山 想一郎, 山下 倫央, 川村 秀憲
  • 2019 人工知能学会現場イノベーション賞銀賞
     畳み込みニューラルネットワークを用いたロードヒーティングコントローラの開発 
    受賞者: 川村 秀憲;永田 紘也;横山 想一郎;山下 倫央;横川 誠;武田 清賢
  • 2019 一般社団法人情報処理学会 調査研究運営委員会 研究会活動貢献賞
     
    受賞者: 川村 秀憲
  • 2018 人工知能学会全国大会 学生奨励賞
     Deep Q-Networkを用いた自動運転車のゆずりあいによる交通流の効率化 
    受賞者: 小川 一太郎, 横山 想一郎, 山下 倫央, 川村 秀憲, 酒 徳哲, 柳原 正, 大岸 智彦, 田中 英明
  • 2018 2018年度7月電子情報通信学会 研究奨励賞
     深層学習を用いた車内動画の運転手領域に基づく異常行動の検出 
    受賞者: 木戸口 稜, 横山 想一郎, 山下 倫央, 川村 秀憲
  • 2018 情報処理北海道シンポジウム2018 優秀ポスター賞
     献立自動生成システムに向けての考察 
    受賞者: 桶 智輝, 横山 想一郎, 山下 倫央, 川村 秀憲
  • 2018 The 22nd Asia Pacific Symposium on Intelligent and Evolutionary Systems Best student paper
     Prediction of Race Results and Generation of Predicted Articles in Keirin 
    受賞者: 吉田 拓海, 横山 想一郎, 山下 倫央, 川村 秀憲
  • 2018 北海道科学技術奨励賞
     
    受賞者: 川村 秀憲
  • 2016 情報処理北海道シンポジウム2016 優秀ポスター賞
     寒冷地における家庭用コージェネレーションシステム利用のための電力・給湯の需要予測と運転評価 
    受賞者: 今野 陽子, 武田 清賢, 横川 誠, 鈴木 恵二, 川村 秀憲
  • 2015 情報処理学会北海道支部 技術研究賞
     北海道のコージェネレーション活用に向けた電力需要予測 
    受賞者: 今野 陽子, 楳田 健斗, 川村 秀憲, 鈴木 恵二
  • 2014 観光情報学会第8回研究発表会 研究発表会奨励賞
     地域イベント情報配信サイトにおける利用者の閲覧履歴を用いた情報推薦 
    受賞者: 小野 良太, 川村 秀憲, 鈴木 恵二
  • 2014 第14回複雑系マイクロシンポジウム 優秀講演賞
     探索の多様化と集中化を考慮した構造化局所クラスタリングの提案 
    受賞者: 今野 陽子, 川村 秀憲, 鈴木 恵二
  • 2012 観光情報学会第5回研究発表会 優秀賞
     人気ブログから日本旅行への関心を探る 
    受賞者: 村上 嘉代子, 川村 秀憲, 鈴木 恵二
  • 2011 情報処理北海道シンポジウム2011 情報処理学会北海道支部学術研究賞
     ロボカップシミュレーションにおける異方性評価指標を用いた支配タイプの検出 
    受賞者: 小林 佑輔, 川村 秀憲, 鈴木 恵二
  • 2010 情報処理北海道シンポジウム2010 情報処理学会北海道支部優秀ポスター賞
     類似内容を含む新聞記事を連結するオントロジーの試作 
    受賞者: 森 翔平, 川村 秀憲, 鈴木 恵二
  • 2009 情報処理北海道シンポジウム2009 情報処理学会北海道支部学術研究賞
     ZigBeeセンサネットワークを用いたリアルタイム屋内測位システムの性能評価 
    受賞者: 辻 順平, 川村 秀憲, 鈴木 恵二, 池田 剛,幸島 明男, 車谷 浩一
  • 2008 情報処理北海道シンポジウム2008 学術研究賞
     推薦システムにおけるユーザ間・アイテム間協調フィルタリングの適応的な融合手法の提案 
    受賞者: 山下 晃弘, 川村 秀憲, 鈴木 恵二, 大内 東
  • 2007 情報処理北海道シンポジウム2007 学術研究賞
     オークションにおける情報開示戦略の分析 
    受賞者: 寺西 俊樹, 川村 秀憲, 大内 東
  • 2005 AFO’05 in Hakodate 技術賞
     デモ飛行 
    受賞者: 皆川 良弘, 川村 秀憲, 山本 雅人, 高谷 敏彦, 大内 東
  • 2005 情報処理北海道シンポジウム2005 奨励賞
     室内飛行船ロボットの自律充電システムの開発 
    受賞者: 皆川 良弘;川村 秀憲;山本 雅人;大内 東;高谷 敏彦
  • 2004 合同エージェントワークショップ&シンポジウム2004 (JAWS2004) 論文賞
     マルチエージェントが構成するネットワークと相互作用の分析 
    受賞者: 西川 浩司, 川村 秀憲, 山本 雅人, 大内 東
  • 2001 人工知能学会 ロボカップ・ジャパンオープン2001 JSAI賞
     
    受賞者: Team Harmony(橋本;圭輔;西村 絢子;山下 倫央;川村 秀憲;山本 雅人;大内 東)
  • 2000 人工知能学会 ロボカップ・ジャパンオープン2000 JSAI賞
     
    受賞者: Team Harmony(飯塚;博之;平本 雅俊;川村 秀憲;山本 雅人;大内 東)

Research Grants & Projects

  • AIによるテクニカルライティング文章の作成（言語AIアルゴリズム構築）
    YAMAGATA株式会社：
    Date (from‐to) : 2023/04 -2025/12 
    Author : 山下 倫央, 川村 秀憲, 横山 想一郎
  • 株式会社堀口組：
    Date (from‐to) : 2022/04 -2025/03 
    Author : 山下 倫央, 川村 秀憲, 横山 想一郎
  • 株式会社シーズ・ラボ：
    Date (from‐to) : 2019/05 -2025/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 北海道のスマートエネルギーネットワーク構築とコージェネレーション等の有効活用に向けた基礎研究
    北海道ガス株式会社：
    Date (from‐to) : 2017/03 -2025/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • IoTと人工知能技術を活用したエネルギー供給の効率化に関する研究
    ゼロスペック株式会社：
    Date (from‐to) : 2020/06 -2024/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 人工知能を活用したオークションの最適化戦略およびブランド品査定自動化に関する研究
    バリュエンステクノロジーズ株式会社：
    Date (from‐to) : 2019/05 -2024/02 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • AIとIoTを活用したデータ駆動型灯油配送の実現
    財団法人北海道科学技術総合振興センター（ノーステック財団）研究開発助成事業 イノベーション創出研究支援事業 研究成果展開（発展・橋渡し研究）補助金：
    Date (from‐to) : 2022/08 -2023/03 
    Author : 山下 倫央, 川村 秀憲, 横山 想一郎, 多田 満朗, 神 大地, 山中 繁幸
  • コネクティッドネットワークにおけるAI活用の研究開発
    株式会社ＫＤＤＩ総合研究所：
    Date (from‐to) : 2021/10 -2022/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 人工知能対応先進的計算機システムを用いたAI俳句の機能深化
    北海道大学情報基盤センター：北海道大学情報基盤センター人工知能対応先進的計算機システム共同研究
    Date (from‐to) : 2020/04 -2022/03 
    Author : 川村 秀憲, 横山 想一郎, 山下 倫央, 杉木 章義
  • 料理の構造化に関する研究
    株式会社ニチレイ：
    Date (from‐to) : 2019/05 -2022/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 業界初！高齢者の生活に寄り添う自立走行・歩行支援の歩行器「 smartNexus®Walker」の製品化
    株式会社サンクレエ：
    Date (from‐to) : 2021/10 -2022/02 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 競輪競技におけるデータ解析とシミュレーション
    株式会社チャリ・ロト：
    Date (from‐to) : 2021/03 -2021/04 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 業界初！高齢者の生活に寄り添う自動運転の木製歩行器 smartNexus®Walker 試作開発
    株式会社サンクレエ：
    Date (from‐to) : 2020/09 -2021/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 深層学習を用いたバス車内モニタリングシステムの開発
    財団法人北海道科学技術総合振興センター (ノーステック財団)：イノベーション創出研究支援事業 発展・橋渡し研究補助金
    Date (from‐to) : 2020/08 -2021/03 
    Author : 山下 倫央, 川村 秀憲, 横山 想一郎, 佐藤 好美, 弓崎 潔
  • コネクティッドカーの協調学習に関する検討
    株式会社ＫＤＤＩ総合研究所：
    Date (from‐to) : 2020/07 -2021/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • デジタルマーケティングのためのAI技術の開発
    株式会社セブン＆アイ・ホールディングス：
    Date (from‐to) : 2019/03 -2020/12 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 次期運輸業務システムにおける乗務員勤務の最適化導入に向けた検討
    北海道旅客鉄道株式会社：
    Date (from‐to) : 2019/11 -2020/03 
    Author : 山下 倫央, 川村 秀憲, 横山 想一郎
  • ネットワーク運用自動化に関するAI活用の研究開発
    株式会社ＫＤＤＩ総合研究所：
    Date (from‐to) : 2019/10 -2020/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 人工知能技術を用いた川柳自動生成システム
    日本放送協会：
    Date (from‐to) : 2019/04 -2020/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 人工知能に関する人材育成教材開発
    AI TOKYO LAB株式会社：
    Date (from‐to) : 2017/07 -2019/09 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • コールセンター業務におけるシフト調整へのAI技術応用
    株式会社ＴＭＪ：
    Date (from‐to) : 2018/10 -2019/06 
    Author : 川村 秀憲
  • ヘルスケア商品の企画開発・販売における人工知能の活用に関する研究
    ジェイフロンティア株式会社：
    Date (from‐to) : 2018/05 -2019/06 
    Author : 川村 秀憲
  • 深層学習を用いた定置網内魚種推定システムの開発
    財団法人北海道科学技術総合振興センター (ノーステック財団)：イノベーション創出研究支援事業 発展・橋渡し研究補助金
    Date (from‐to) : 2018/08 -2019/03 
    Author : 山下 倫央, 横山 想一郎, 川村 秀憲, 泉 卓真
  • AI技術を使った部品検査装置の開発
    シンセメック株式会社：
    Date (from‐to) : 2018/08 -2019/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • コネクティッドカーの協調学習に関する検討
    株式会社ＫＤＤＩ総合研究所：
    Date (from‐to) : 2018/06 -2019/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 競輪競技におけるデータ解析とシミュレーション
    株式会社チャリ・ロト：
    Date (from‐to) : 2017/06 -2019/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Young Scientists (B)
    Date (from‐to) : 2013/04 -2019/03 
    Author : Murakami Kayoko, Suzuki Keiji, Kawamura Hidenori, Oyabu Takashi
     
    The number of foreign tourists visiting Japan has been increasing. It is essential to analyze the needs of foreign tourists in order to promote inbound tourism in Japan. This research was carried out by analyzing word-of-mouth about Japan travel from Japanese tourists and foreign tourists to investigate the differences in destination image of a particular tourist attraction using a text mining approach. Moreover, the information in the official sightseeing websites was analyzed with respect to Japanese and English text data in order to compare the results of Japanese and foreign tourists’ destination images of the tourist attraction. The framework that extracts distinctive tourism information from three perspectives: Japanese tourists, foreign tourists, and tourism promoters was proposed for the purpose of developing regional tourism support tool.
  • CNNを用いた画像認識とタグ生成アルゴリズムの開発
    株式会社デジタルガレージ：
    Date (from‐to) : 2019/01 -2019/02 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 安心を見える化する介護支援システム「smartNexus®Care」の研究開発
    株式会社サンクレエ：
    Date (from‐to) : 2018/11 -2019/02 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 不動産販売のウェブマーケティングにおける人工知能の活用に関する研究
    株式会社イー・ステート・オンライン：
    Date (from‐to) : 2017/09 -2018/12 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • ディープラーニングを用いた運転動画の状態認識に関する研究
    株式会社サンクレエ：
    Date (from‐to) : 2017/06 -2018/11 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 気象予報図におけるキャプション配置最適化に関する研究
    株式会社マイクロネット：
    Date (from‐to) : 2017/11 -2018/08 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • コネクティッドカーの協調学習に関する検討
    株式会社KDDI総合研究所：
    Date (from‐to) : 2017/07 -2018/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 人工知能を用いたアパレル商品画像のタギングに関する研究
    株式会社TSIホールディングス：
    Date (from‐to) : 2017/06 -2018/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 家電製品の販売予測
    ジーエフケーマーケティングサービスジャパン株式会社：
    Date (from‐to) : 2017/06 -2018/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • 人工知能によるマーケティングデータの分析アルゴリズム開発
    フュージョン株式会社：
    Date (from‐to) : 2017/06 -2018/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • SFAにおける人工知能技術の応用に関する研究
    株式会社インターパーク：
    Date (from‐to) : 2017/04 -2018/03 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • ディープラーニングによるAI融雪コントローラの開発
    財団法人北海道科学技術総合振興センター (ノーステック財団)：イノベーション創出研究支援事業 発展・橋渡し研究補助金
    Date (from‐to) : 2017/04 -2018/03 
    Author : 川村 秀憲, 武田 清賢, 山下 倫央, 横山 想一郎
  • 物流倉庫管理の人工知能技術応用に関する研究
    株式会社PAL：
    Date (from‐to) : 2017/04 -2017/11 
    Author : 川村 秀憲, 山下 倫央, 横山 想一郎
  • コネクティッドカーの協調学習に関する研究
    株式会社KDDI研究所：
    Date (from‐to) : 2016/06 -2017/03 
    Author : 川村 秀憲
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Challenging Exploratory Research
    Date (from‐to) : 2014/04 -2017/03 
    Author : Kawamura Hidenori
     
    This research is a study on environment to execute large scale multi agent simulation. As a simulation target, Segregation model by Thomas Schelling is taken up, tens of thousands of agents select a place of residence in an environment constructed using data as an open street map, how residential areas are segmented by social status etc. We succeeded in large - scale agent simulation as to whether to go.
  • 総務省：scope
    Date (from‐to) : 2014/04 -2017/03 
    Author : 川村 秀憲
  • 北海道のスマートエネルギーネットワーク構築とコージェネレーション等の有効活用に向けた基礎研究
    北海道ガス株式会社：
    Date (from‐to) : 2016/04 -2016/09 
    Author : 川村 秀憲
  • コールセンター業務におけるシフト調整へのAI技術応用
    株式会社TMJ：
    Date (from‐to) : 2016/04 -2016/09 
    Author : 川村 秀憲
  • 機械学習の商業的利用へ向けた調査・研究について
    株式会社クレスコ：
    Date (from‐to) : 2016/01 -2016/03 
    Author : 川村 秀憲
  • ディープラーニングによる北海道イベント情報の特徴量抽出と応用
    財団法人北海道科学技術総合振興センター (ノーステック財団)：イノベーション創出研究支援事業 スタートアップ研究補助金
    Date (from‐to) : 2015/08 -2016/03 
    Author : 川村 秀憲, 小野 良太, 今野 陽子, 中村 拓哉
  • 飛行船ロボット制御に関する研究開発
    株式会社キャンパスクリエイト, 日本ステージ株式会社：
    Date (from‐to) : 2015/07 -2016/03 
    Author : 川村 秀憲
  • 北海道のガス利用におけるコージェネ・スマートグリッドに向けた基礎研究
    北海道ガス株式会社：
    Date (from‐to) : 2014/09 -2015/08 
    Author : 川村 秀憲
  • リアルタイム興味解析に基づく地域情報最適化フレームワークの提案
    総務省：戦略的情報通信研究開発推進事業(SCOPE)
    Date (from‐to) : 2013/10 -2015/03 
    Author : 川村 秀憲, 鈴木 恵二, 平田 圭
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)
    Date (from‐to) : 2011 -2013 
    Author : SUZUKI Keiji, KAWAMURA Hidenori
     
    The analytic hierarchy process (AHP) is a method for decision-making that considers uncertain situations or multiple evaluation criteria. In the AHP, a decision maker compares two elements between evaluation criteria and alternatives. Therefore, comparing all pairs is difficult when evaluating many alternatives. In this study, we present the comparison support method for evaluating many alternatives when a decision maker needs to decide the highest priority alternative. The comparison support method stops pairwise comparisons when the best solution, i.e., the highest priority alternative, is found, even if all pairs have not been compared. We represented a modeling of determine the best alternative using the AHP include comparison support system.
  • ツイッター分析による北海道の盛り上がりリアルタイム抽出
    財団法人北海道開発協会：研究助成
    Date (from‐to) : 2011/04 -2012/03 
    Author : 鈴木 恵二, 川村 秀憲, 山下 晃弘
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Young Scientists (A)
    Date (from‐to) : 2009 -2012 
    Author : KAWAMURA Hidenori, SUZUKI Keiji
     
    In this research, we focused on the service infrastructure on a society, which is a set of facilities utilized by many citizens, and developed a simulation model with many citizen agents and service facilities for studying the way to reduce social congestion. In computer simulation model, the visiting plans of agents are shared via the central server and each agent plan is individually optimized by the information based on the server. Through the experiments, we showed that the social congestion is reduced by such information sharing.
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)
    Date (from‐to) : 2007 -2008 
    Author : OHUCHI Azuma, KAWAMURA Hidenori, NAGAO Mitsuyoshi, SUTO Kazuhiro
     
    本研究では,ネットニュースから中心的に扱っている話題を語の共起情報や出現頻度に基づいて抽出し,その時系列的な変化を提示するアルゴリズムの提案した.また,提案したアルゴリズムを2007年に発生した新潟県中越沖地震発生時のネットニュースに適用し,当時のネットニュースでの報道状況を解析した.これにより,提案アルゴリズムの検証を行うと共に,ネット上の情報にバイアスがかかり歪められていく過程を明らかにした.
  • 日本学術振興会：科学研究費助成事業 特定領域研究
    Date (from‐to) : 2002 -2006 
    Author : 大内 東, 山本 雅人, 川村 秀憲
     
    1.自由エネルギーに基づいたハイブリダイゼーション過程の解析 本研究では,ある一本鎖DNAとその完全相補配列,及び,競合する塩基配列を混合した溶液中で起こるハイブリダイゼーションの特徴を自由エネルギーや融解温度の立場から明らかにした. ある塩基配列Aと完全相補な塩基配列B,及び,Aと部分的に相補な配列を含む塩基配列Cが競合する反応系において,AとBの結合体の最小自由エネルギー,および,融解温度,また,AとCの結合体の最小自由エネルギー,および,融解温度との関係からAとCが結合してしまうミスハイブリダイゼーションの発生割合の分析を行った.検出にはDNAに修飾した蛍光のクエンチングを利用した.結果的に,最小自由エネルギー,および,融解温度の差がミスハイブリダイゼーションに与える影響について,実験結果からモデル式を導出することに成功した. 2.DNAタイルのための塩基配列設計支援システムの構築 昨年度の研究成果を受けて,DNAタイル設計のための塩基配列設計支援システムの構築を行った.DNAタイルは,ナノ構造の形成やタイル計算に用いることが可能であることから近年注目を浴びている.しかしながら,DNAタイルは何本もの一本鎖DNAの結合体であることからその構造安定性を求めることは困難であり,これまで,ヒューリスティックな方法として,重複する連続した部分塩基配列を避ける方法が使用されてきていた. 本研究では,DNAタイルの構造安定性を見積もる方法として,自由エネルギーを用いることにした.2本の一本鎖DNAからできる主な結合体の自由エネルギーを見積もる方法は,これまでの研究で洗練されたものとなっている.このため,DNAタイルの構造体を2本の一本鎖DNAからなる部分に分けて,DNAタイルが望み通りに生成されたときの結合体の自由エネルギーが最も安定となるような尺度を設計することを目的としている.本研究では,設計支援のためのツールを開発した.DNAタイル設計の際には,各部分配列同士の非特異的結合を避けたり,融解温度やGC含量などを考慮したり必要があり,それらを見積もるツールが必要である.また,作成した配列の解析や,山登り法による最適化手法による配列の自動生成も可能である.
  • 日本学術振興会：科学研究費助成事業 若手研究(B)
    Date (from‐to) : 2003 -2005 
    Author : 川村 秀憲
     
    本研究では「テーマパーク問題」を提案し,インテリジェントマスサポート理論に関する理論構築を目的とする.テーマパーク問題とは,複数のアトラクションに対する選好を持ったエージェントがテーマパーク内を巡回する際,個人の効用を下げずに全体の混雑度を減少させる巡回プランを提示するための動的・複合的スケジューリング問題である. 平成17年度は,エージェントが混雑情報に基づいて近視眼的に混雑回避行動をとると仮定したとき,どのような混雑情報を提示することが全体の混雑緩和に寄与するかに焦点をあてて研究を行った. 具体的には,ユーザが次に訪問するアトラクションを混雑情報システムに入力させ,各アトラクションの混雑状況に未来の混雑の予測という情報を付加することで各エージェントが自律分散的に混雑回避した際の効果が全体の混雑緩和に寄与するということが確かめられた。 また,エージェントから情報収集を行いながら適切に混雑情報を提示するだけではなく,事前に全てのエージェントの制約条件が明らかになった状態で遺伝的アルゴリズムを用いて静的に訪問順序を最適化したものとの比較を行った. その結果から テーマパークのように限られた資源をたくさんのユーザで利用しなければならない場合,単純に均一的に負荷を分散させるよりも,わざと1,2のアトラクションにエージェントを集中させ,残ったほかのアトラクションでの資源利用効率を上げることが全体の混雑緩和に大きく寄与することがわかった.これは,特定のアトラクションの利用効率を悪化させても,残りのアトラクションの利用効率を上げることでシステム全体内のエージェントの数を減少させることができるので,結果的に全体の利用効率化を図ることができると言うことである. この結果は,例えばユビキタス通信を装備したインテリジェントカーナビなどを開発する際に応用可能な成果が得られたと思われる.
  • ハンディGPSを用いたレンタカー利用観光客の観光動態調査
    財団法人北海道科学技術総合振興センター (ノーステック財団)：社会科学研究支援事業 社会科学研究補助金
    Date (from‐to) : 2003/08 -2004/03 
    Author : 大内 東, 山本 雅人, 川村 秀憲, 北山 憲武
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B)
    Date (from‐to) : 2002 -2004 
    Author : OHUCHI Azuma, YAMAMOTO Masahito, KAWAMURA Hidenori
     
    In this research project, we proposed the new information security system at the molecular level for personal genome data. Important data such as Personal genome data can be stored as a DNA sequences, and can be readout when it is needed. In the proposed system, however, it is impossible or so hard to readout without the keys, because some kind of dummy DNA data are included in the pool with the stored data. We proposed two kind of security system. (1)Data lock by DNA modification Data is stored into DNA with some modifications, which can be removed only by the key primer. We demonstrated that the target data can be readout only if we can use the key primer by some chemical experiments. (2)Data lock by the hierarchical DNA memory based the nested PCR Data is stored with some DNA blocks, which are regarded as addresses of memory. In order to readout the data from the pool of these DNA memories including some dummy DNA, nested PCR with some key DNA are used. We verified that the target data can be extracted and readout from 27 kinds of DNA memories by some chemical experiments. Furthermore, we demonstrated that the target data can be extracted from 65,536 kinds of the pool of DNA memories.
  • 北海道観光産業の活性化のためのネットワークビジネス実現に関する提案
    財団法人北海道科学技術総合振興センター (ノーステック財団)：社会科学研究支援事業 社会科学研究補助金
    Date (from‐to) : 2002/08 -2003/03 
    Author : 大内 東, 山本 雅人, 川村 秀憲
  • 日本学術振興会：科学研究費助成事業 若手研究(B)
    Date (from‐to) : 2001 -2002 
    Author : 川村 秀憲
     
    本年度は,作成したシミュレーションサーバを実際に使用し,いくつかのタイプの人工市場についてモデル化と実験を行った.具体的に,本研究によるシミュレーションサーバを用いて,以下のテーマを取り扱うことが可能となった. ・電力自由化における仮想電力市場モデルと制度設計に関する研究 ・強化学習に基づく学習エージェントの構築と均衡価格への収束に関する研究 ・多数・多種のエージェントに基づく人工国際貿易モデルの構築とそのダイナミクスの研究 これらの研究では,本補助金によって作成したサーバを使用し,効率のよいシミュレーションシステムの開発が行えた.特に,エージェントのテンプレートを用意しているので,それを改造することで複雑なモデルが簡単に構築できることを確かめられた.それぞれのモデルは,人工市場研究において重要なテーマであり,この分町の研究の発展に寄与することができた. また,本補助金によって作成したシステムは,オープンソースとしてインターネット上で公開し,この分野の研究者に広く使ってもらうための準備を行った.実際にいくつかの研究グループよりコンタクトがあり,試験的に使用してもらい,システムの汎用性や拡張性を確認した.これらの研究成果について,いくつかの論文を発表し,国内外に広く成果を公表した.2年間という短い期間ではあったが,当初の目標以上の成果をあげることができた.
  • 日本学術振興会：科学研究費助成事業 特別研究員奨励費
    Date (from‐to) : 1999 -1999 
    Author : 川村 秀憲

Educational Activities

Teaching Experience

  • Inter-Graduate School Classes(General Subject):Natural and Applied Sciences
    開講年度 : 2021
    課程区分 : 修士課程
    開講学部 : 大学院共通科目
    キーワード : マルチエージェントシステム，分散制約充足問題，分散最適化，非協力ゲーム理論，ベイジアンゲーム，混雑ゲーム，提携ゲーム理論
  • Harmonious Systems Engineering
    開講年度 : 2021
    課程区分 : 修士課程
    開講学部 : 情報科学研究科
    キーワード : マルチエージェントシステム，分散制約充足問題，分散最適化，非協力ゲーム理論，ベイジアンゲーム，混雑ゲーム，提携ゲーム理論
  • Harmonious Systems Engineering
    開講年度 : 2021
    課程区分 : 修士課程
    開講学部 : 情報科学院
    キーワード : マルチエージェントシステム，分散制約充足問題，分散最適化，非協力ゲーム理論，ベイジアンゲーム，混雑ゲーム，提携ゲーム理論
  • Information Media and Tourism
    開講年度 : 2021
    課程区分 : 修士課程
    開講学部 : 国際広報メディア・観光学院
    キーワード : 情報メディア、観光、観光情報学、Web2.0、デジタルマーケティング、ビッグデータ、人工知能（AI）、ソーシャルメディア、サービスイノベーション、地図
  • Information Media and Tourism
    開講年度 : 2021
    課程区分 : 修士課程
    開講学部 : 国際広報メディア・観光学院
    キーワード : 情報メディア、観光、観光情報学、Web2.0、デジタルマーケティング、ビッグデータ、人工知能（AI）、ソーシャルメディア、サービスイノベーション、地図
  • Harmonious Systems Engineering
    開講年度 : 2021
    課程区分 : 博士後期課程
    開講学部 : 情報科学研究科
    キーワード : マルチエージェントシステム，分散制約充足問題，分散最適化，非協力ゲーム理論，ベイジアンゲーム，混雑ゲーム，提携ゲーム理論
  • Harmonious Systems Engineering
    開講年度 : 2021
    課程区分 : 博士後期課程
    開講学部 : 情報科学院
    キーワード : マルチエージェントシステム，分散制約充足問題，分散最適化，非協力ゲーム理論，ベイジアンゲーム，混雑ゲーム，提携ゲーム理論
  • Exercise in Computer Science and Information Technology IV
    開講年度 : 2021
    課程区分 : 学士課程
    開講学部 : 工学部
    キーワード : 人工知能、探索アルゴリズム、ニューラルネットワーク、ディープラーニング、機械学習、遺伝的アルゴリズム、回帰分析、サポートベクトルマシン
  • Artificial Intelligence
    開講年度 : 2021
    課程区分 : 学士課程
    開講学部 : 工学部
    キーワード : 人工知能、探索アルゴリズム、ニューラルネットワーク、ディープラーニング、機械学習、遺伝的アルゴリズム
  • Computer Programming Ⅰ
    開講年度 : 2021
    課程区分 : 学士課程
    開講学部 : 工学部
    キーワード : Unix, C言語, ファイル入出力, 数値計算
  • Exercise in Computer Programming
    開講年度 : 2021
    課程区分 : 学士課程
    開講学部 : 工学部
    キーワード : Unix, C言語, ファイル入出力, 数値計算
  • Freshman Seminar
    開講年度 : 2021
    課程区分 : 学士課程
    開講学部 : 全学教育
    キーワード : 創造工学、グループ実験、プレゼンテーション

Social Contribution

Social Contribution

Social Contribution

  • AI俳句の俳句コンテンツ提供
    Date (from-to) : 2019/10-Today
    Role : Informant
    Sponser, Organizer, Publisher  : 有限会社マルコボ．コム
    Event, Program, Title : 俳句の缶づめ（年4回発行の季刊誌）
  • 川村秀憲のなるほどAI
    Date (from-to) : 2022/07-2024/03
    Role : Contribution
    Sponser, Organizer, Publisher  : 日経MJ
  • Sapporo AI Connect 2024 ～JDLA×札幌AI道場～（「札幌AI道場」成果発表会のクロストークセッション及びクロージング）
    Date (from-to) : 2024/02/26
    Role : Panelist
    Sponser, Organizer, Publisher  : 札幌市，日本ディープラーニング協会等
  • ＡＩ時代の学校教育／未来を生きるための能力：ＡＩに取って代われない人間の価値
    Date (from-to) : 2024/01
    Role : Contribution
    Sponser, Organizer, Publisher  : 日本教育評価研究会
    Event, Program, Title : 機関誌「指導と評価」（2024年1月号）
  • ChatGPTの先にある世界 ― AIがもたらす転換期に立って（サイエンスカフェ）
    Date (from-to) : 2023/12/03
    Role : Lecturer
    Sponser, Organizer, Publisher  : 北海道大学 CoSTEP
    Event, Program, Title : 第133回サイエンス・カフェ札幌
  • チャットGPTのインパクト─ 我々はどう向き合い、どう活用すべきか ─（講師）
    Date (from-to) : 2023/11/10
    Role : Lecturer
    Sponser, Organizer, Publisher  : 一般社団法人 学士会
    Event, Program, Title : 十一月夕食会
  • AIが変えるミライとセカイ ～サッポロミライナイトmeets TOKYO #2～（クロストーク）
    Date (from-to) : 2023/08/31
    Role : Panelist
    Sponser, Organizer, Publisher  : Venture Café Tokyo、STARTUP CITY SAPPORO事務局
    Event, Program, Title : Sapporo Hokkaido Startup Night 北海道のイノベーションエコシステムの進化を目撃せよ
  • 北海道におけるスタートアップ経営支援の可能性（パネルディスカッション）
    Date (from-to) : 2023/07/12
    Role : Panelist
    Sponser, Organizer, Publisher  : 一般社団法人AMA terrace
    Event, Program, Title : 北海道スタートアップコミュニケーション2023
  • 「ChatGPT」AIの進化と教育の未来
    Date (from-to) : 2023/07/01
    Role : Contribution
    Sponser, Organizer, Publisher  : 株式会社日本金融通信社
    Event, Program, Title : 月刊金融ジャーナル（2023年7月号）
  • 「『ChatGPT』との付き合い方 ～生成AI興隆の今、考えたいこと～」（講師）
    Date (from-to) : 2023/06/26
    Role : Lecturer
    Sponser, Organizer, Publisher  : Sapporo AI Lab
    Event, Program, Title : 「札幌AI道場・第二期」開設式
  • 人工知能の未来 ChatGPTを超えて（講師）
    Date (from-to) : 2023/04/25
    Role : Lecturer
    Sponser, Organizer, Publisher  : モノづくり日本会議（日刊工業新聞）
    Event, Program, Title : モノづくり日本会議 ウェブセミナー
  • AIの発展と未来
    Date (from-to) : 2023/04/24
    Role : Contribution
    Sponser, Organizer, Publisher  : 北海道経済同友会
    Event, Program, Title : 北海道デジタル推進委員会報告書 「道内産業のデジタル化推進に向けて～デジタルの動向を知り道内産業のデジタル化を進めるためのポイントを探る～」
  • 道内市町村職員向け「まちづくり交流会」（講師）
    Date (from-to) : 2023/02/15
    Role : Lecturer
    Sponser, Organizer, Publisher  : 北海道建設部建設政策局「北の住まいるタウン」
  • 北大・川村教授に聞く ＡＩを知ろう
    Date (from-to) : 2021/11/06-2022/12/10
    Role : Contribution
    Sponser, Organizer, Publisher  : 道新こども新聞
    Event, Program, Title : 週間まなぶん
  • スタートアップ・エコシステム拠点都市報告会（パネルディスカッション）
    Date (from-to) : 2022/08/24
    Role : Panelist
    Sponser, Organizer, Publisher  : 内閣府
  • 「AI vs 人」の俳句対決 川村教授が説く 「AIは芸術家になれるのか」
    Date (from-to) : 2022/06/23
    Role : Contribution
    Sponser, Organizer, Publisher  : ビジネス＋IT
  • ICTキャンパス「企業と連携してAI研究 成果を社会に還元する」
    Date (from-to) : 2022/06/06
    Role : Contribution
    Sponser, Organizer, Publisher  : 教育家庭新聞社
    Event, Program, Title : 月刊 教育家庭新聞 教育マルチメディア号
  • 培養した脳細胞にコンピューター接続 卓球ゲーム プレイ可能に
    Date (from-to) : 2022/03/15
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • ＡＩ技術者採用 スタートアップが有利
    Date (from-to) : 2022/02/15
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • 「人工知能」とは何か 抽象的目的に沿う情報処理
    Date (from-to) : 2022/01/18
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • 米フェイスブック、社名変更 仮想世界の覇権に挑む
    Date (from-to) : 2021/12/21
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • 昔思い描いた未来の入り口 技術の融合「革新」生む
    Date (from-to) : 2021/10/26
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • いかに「人」とすみ分けるべきか ＡＩで手が回らないこと担う
    Date (from-to) : 2021/09/28
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • プログラムつくる、再定義
    Date (from-to) : 2021/08/31
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • ＡＩ導入、２つの秘訣
    Date (from-to) : 2021/08/03
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • 無形資産―スピルオーバーで利益得る
    Date (from-to) : 2021/07/06
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • 「かわいい」など感性数値化
    Date (from-to) : 2021/06/08
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • 婚活サービスにＡＩ活用
    Date (from-to) : 2021/05/11
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • 人と見紛う文章力 高評価
    Date (from-to) : 2021/04/13
    Role : Contribution
    Sponser, Organizer, Publisher  : 日刊工業新聞
    Event, Program, Title : 次代をつくる
  • AI俳句の俳句コンテンツ提供
    Date (from-to) : 2021/04/05
    Role : Informant
    Sponser, Organizer, Publisher  : 日本テレビ
    Event, Program, Title : しゃべくり007
  • AI俳句の俳句コンテンツ提供
    Date (from-to) : 2021/04
    Role : Informant
    Sponser, Organizer, Publisher  : 浜島書店
    Event, Program, Title : 国語の学習3（中学校教材, 2021年版）
  • AI一茶くんによる俳句コンテンツを提供
    Date (from-to) : 2020/12
    Role : Others
    Sponser, Organizer, Publisher  : 東京法令出版株式会社
    Event, Program, Title : 「見る，解く，納得！公民資料2021」(「公民」の中学校副教材）
  • AI俳句の俳句コンテンツ提供
    Date (from-to) : 2020/11/29
    Role : Informant
    Sponser, Organizer, Publisher  : BSフジ
    Event, Program, Title : タイプライターズ～物書きの世界～
  • バングラデシュICT人材採用・活用フォーラム（モデレーター）
    Date (from-to) : 2020/10/02
    Role : Presenter
    Sponser, Organizer, Publisher  : JICA北海道
  • 北海道学習センター面接授業（非常勤講師）
    Date (from-to) : 2020/04/01-2020/09/30
    Role : Lecturer
    Sponser, Organizer, Publisher  : 放送大学
  • AI川柳の川柳コンテンツ提供
    Date (from-to) : 2019/04/12-2020/03/27
    Role : Informant
    Sponser, Organizer, Publisher  : NHK総合
    Event, Program, Title : ニュース シブ5時
  • AI俳句「AI一茶くん」による俳句コンテンツ提供
    Date (from-to) : 2019/09/14
    Role : Organizing member
    Event, Program, Title : 第２９回芭蕉祭山中温泉全国俳句大会
  • 大阪府 商工労働常任委員会 行政視察対応
    Date (from-to) : 2019/08/26
    Role : Others
    Sponser, Organizer, Publisher  : 北海道大学情報科学研究院
  • AI川柳の川柳コンテンツ提供
    Date (from-to) : 2019/03/13-2019/03/27
    Role : Informant
    Sponser, Organizer, Publisher  : NHK総合
    Event, Program, Title : ニュースチェック11
  • AI俳句「AI一茶くん」による俳句コンテンツ提供
    Date (from-to) : 2019/02/02-2019/03/24
    Role : Organizing member
    Sponser, Organizer, Publisher  : 北海道立文学館
    Event, Program, Title : 北海道立文学館特別展「北海道の俳句～どこから来て、どこへ行くのか」
  • AI俳句の俳句コンテンツ提供
    Date (from-to) : 2019/03/08-2019/03/17
    Role : Informant
    Sponser, Organizer, Publisher  : SXSW社
    Event, Program, Title : South by Southwest (SXSW) 2019
  • AI俳句「AI一茶くん」による俳句コンテンツ提供
    Date (from-to) : 2018/10/10-2018/10/14
    Role : Organizing member
    Sponser, Organizer, Publisher  : No Maps実行委員会
    Event, Program, Title : Sapporo Creative Convention NoMaps～AIラボブース
  • S-NET（スペース・ニューエコノミー創造ネットワーク）北海道セミナー ～共に創る豊かな大地～」（パネルディスカッション）
    Date (from-to) : 2017/07/21
    Role : Panelist
    Sponser, Organizer, Publisher  : 経済産業省
  • 2045年:人工知能の旅「人工知能をビジネスに結びつけるには」（パネルディスカッション）
    Date (from-to) : 2016/10/16
    Role : Panelist
    Event, Program, Title : NoMaps

Media Coverage

  • マイ！Biz 著者に聞く（出演、著書『10年後のハローワーク これからなくなる仕事、伸びる仕事、なくなっても残る人』についてのインタビュー）
    Date : 2024/05/10
    Publisher, broadcasting station: NHKラジオ
    Program, newspaper magazine: 「マイあさ！」
    Media report
  • 特集：AIから探る人間の知性 AIに俳句の良さはわかるのか？（「AI一茶くん」の解説・取材協力）
    Date : 2024/04/25
    Program, newspaper magazine: 日経サイエンス2024年6月号
  • AIに俳句の良さはわかるのか？ 「AI一茶くん」の挑戦（「AI一茶くん」の解説・取材協力）
    Date : 2024/04/24
    Publisher, broadcasting station: 日本経済新聞 電子版
    Paper
  • クローズアップ北海道 ～半導体で変わる未来～（出演、人工知能・AI俳句・10年後の仕事についてのインタビュー）
    Date : 2024/04/13
    Publisher, broadcasting station: HBCラジオ
  • 10年後｢生き残る仕事｣｢なくなる仕事｣の境界線 今後においてもAIにできないことは何か？（著書「10年後のハローワーク これからなくなる仕事、伸びる仕事、なくなっても残る人」解説）
    Date : 2024/04/12
    Publisher, broadcasting station: 東洋経済オンライン
  • 小林一茶の故郷に「AI一茶くん」登場 心情でなくデータ元に生成（「AI一茶くん」紹介展示について掲載）
    Date : 2024/04/05
    Program, newspaper magazine: 朝日新聞
  • 【毎日書評】10年後になくなる仕事、生き残る仕事…どんな人なら必要とされるのか？（著書『「10年後のハローワーク これからなくなる仕事、伸びる仕事、なくなっても残る人』書評）
    Date : 2024/04/04
    Program, newspaper magazine: ライフハッカー・ジャパン
    Internet
  • チャットGPTのインパクト─ 我々はどう向き合い、どう活用すべきか ─(十一月夕食会講演の内容を掲載）
    Date : 2024/03/01
    Publisher, broadcasting station: 一般社団法人 学士会
    Program, newspaper magazine: 學士會会報No.965
    Pr
  • ＡＩで課題解決 企業の事例紹介 札幌で２６日催し（登壇するイベント「Sapporo AI Connect 2024」の開催について掲載）
    Date : 2024/02/15
    Program, newspaper magazine: 北海道新聞
    Paper
  • 見くびるな恋愛アプリ AIの提案、金融に生かす術 金融×AI⑥恋愛アプリ（エール・ゴエン）（インタビューを掲載）
    Date : 2024/02/01
    Program, newspaper magazine: NIKKEI Financial（日経フィナンシャル）
    Internet
  • 生成ＡＩ活用 西胆振の自治体で差 登別市 導入し業務削減／室蘭、伊達市 情報流出懸念（自治体の生成AI活用に関するコメントを掲載）
    Date : 2024/01/30
    Program, newspaper magazine: 北海道新聞
    Paper
  • 課題解決に向けて、ビジネスにどう生かすか 生成AIと創る札幌の未来（札幌商工会議所会頭 岩田 圭剛 氏との新春対談を掲載）
    Date : 2024/01/10
    Publisher, broadcasting station: 札幌商工会議所
    Program, newspaper magazine: 広報誌「さっぽろ経済」
    Pr
  • 北大発AWL、調和技研と提携 AI活用を共同提案（創業に関わる両社の業務提携について掲載）
    Date : 2023/12/27
    Program, newspaper magazine: 日本経済新聞（35面）
    Paper
  • ＜日胆 はなし抄＞人間の独創性、意思決定重要に 北大大学院情報科学研究院教授・川村秀憲さん（講演「ＡＩの未来 ＣｈａｔＧＰＴの先に待っている世界」について掲載）
    Date : 2023/12/25
    Program, newspaper magazine: 北海道新聞
    Paper
  • 日本のソフトパワーが生きる特化型ＡＩ デジタルクローンが代理で働く時代に（特化型AIについてコメントを掲載）
    Date : 2023/12/04
    Publisher, broadcasting station: 日経BP
    Program, newspaper magazine: 日経トレンディ2024年1月号
    特集「テクノロジーの最新動向からニッポンの未来を読み解く2024-2030 大予測」 Paper
  • 「対話型ＡＩ進化加速」 道新苫小牧政経懇 北大院・川村教授講演（講演「ＡＩの未来 ＣｈａｔＧＰＴの先に待っている世界」について掲載）
    Date : 2023/11/29
    Program, newspaper magazine: 北海道新聞
    Paper
  • AIもたらすパラダイムシフト「ゲームチェンジャーになろう」（起業支援やエコシステムの構築についてインタビューを掲載）
    Date : 2023/11/24
    Publisher, broadcasting station: 株式会社ディープコア
    Program, newspaper magazine: 「DEEPCORE」公式note
    Internet
  • #207 ChatGPTはいかにして人と“対話”するか〜AIをテーマにサイエンス・カフェを開催〜（ゲスト登壇したサイエンスカフェの紹介）
    Date : 2023/11/23
    Publisher, broadcasting station: 北海道大学 大学院教育推進機構 オープンエデュケーションセンター 科学技術コミュニケーション教育研究部門（CoSTEP）
    Program, newspaper magazine: いいね！Hokudai
    Internet
  • 北海道とNTT東日本、札幌でDX・AIテーマにフォーラム（基調講演「人工知能の未来 ChatGPTを超えて」について掲載）
    Date : 2023/11/02
    Program, newspaper magazine: 日本経済新聞
    Paper
  • 国内AIの旗手、北海道大学の川村秀憲教授が川村研究所を設立されました（川村研究所の発足に伴う研究発表会について掲載）
    Date : 2023/11/01
    Program, newspaper magazine: リージョナルキャリア地域情報ブログ
    Internet
  • JTB山北社長が語ったグループ戦略と未来、サステナビリティ経営から進化するAIへの対応まで聞いてきた（基調講演「人工知能の未来 ChatGPTの先に待っている世界」について掲載）
    Date : 2023/10/31
    Program, newspaper magazine: トラベルボイス
    Internet
  • 人工知能の未来をテーマに講演 札幌日経懇話会（講演「人工知能の未来 ChatGPTの先に待っている世界」について掲載）
    Date : 2023/10/31
    Program, newspaper magazine: 日本経済新聞
    Paper
  • 業務に生成ＡＩ 札幌市がガイドライン作成へ ２３年度中にも試行導入（自治体の生成AI導入に関するコメントを掲載）
    Date : 2023/10/27
    Program, newspaper magazine: 北海道新聞
    Paper
  • 聞く語る 汎用的な能力はAIに任せ、ニッチな分野にこそ人の役割（AIの普及と社会変化について、インタビュー記事を掲載）
    Date : 2023/10/25
    Program, newspaper magazine: 北海道新聞
    6面 Paper
  • 生成AI リスクを抱え進化（AIの普及とリスクについて、コメントを掲載）
    Date : 2023/09/25
    Program, newspaper magazine: 北海道新聞
    3面 Paper
  • 生成ＡＩが北海道に与える影響は コールセンター・ＩＴに大きな打撃も 北大・川村教授に聞く＜デジタル発＞（生成AIに関するインタビューを掲載・後編）
    Date : 2023/09/01
    Program, newspaper magazine: 北海道新聞
    Paper
  • ＡＩ時代は「さかなクン」を目指せ チャットＧＰＴとの向き合い方 北大・川村教授に聞く＜デジタル発＞（生成AIに関するインタビューを掲載・前編）
    Date : 2023/08/31
    Program, newspaper magazine: 北海道新聞
    Paper
  • 人工知能が俳句を評価する？（栗林浩氏による論考）
    Date : 2023/08/01
    Program, newspaper magazine: 「現代俳句」８月号
    Pr
  • 生成ＡＩ活用探る自治体 当別町はチャットＧＰＴ実証実験 業務改善図り実用化へ＜フォーカス＞（自治体のAI活用に関するコメントを掲載）
    Date : 2023/07/22
    Program, newspaper magazine: 北海道新聞
    Paper
  • 北のビジネス最前線「安全・安心な通信を目指して－最新技術でつくるサイバーセキュリティの未来－ ～株式会社 網屋～」（共同研究に関する川村教授のコメントを紹介）
    Date : 2023/07/18
    Publisher, broadcasting station: 北海道放送
    Media report
  • スタートアップ支援の重要性考える 札幌で企業交流イベント（登壇したパネルディスカッションについて掲載）
    Date : 2023/07/12
    Program, newspaper magazine: 北海道新聞
    Paper
  • 特集「飛躍する『AI×芸術』」（インタビュー）
    Date : 2023/07/01
    Publisher, broadcasting station: みずほリサーチ＆テクノロジーズ株式会社
    Program, newspaper magazine: Fole2023年7月号
    Pr
  • 俳句の楽しみ方を変える? 人工知能「AI一茶くん」の実力とは（俳句評論家 栗林 浩氏のインタビュー記事による「AI一茶くん」の紹介）
    Date : 2023/06/26
    Program, newspaper magazine: 毎日新聞
    Paper
  • 「チャットＧＰＴ」どう活用 札幌ＡＩ道場 第２期開設式で講演 （「札幌AI道場」第2期開設式の基調講演について掲載）
    Date : 2023/06/26
    Program, newspaper magazine: 北海道新聞
    Paper
  • 社員100人以上に育った北海道大学教授（九州工業大学の井上 創造 教授との対談）
    Date : 2023/05/31
    Publisher, broadcasting station: 一般社団法人 情報処理学会
    Program, newspaper magazine: 情処ラジオ
    Internet
  • AI研究会「人工知能の未来 ChatGPTを超えて」（講演内容の抄録）
    Date : 2023/05/22
    Program, newspaper magazine: 日刊工業新聞
    10面 Paper
  • ＴＶｈ道新ニュース「５時ナビ」【なるほどくらし情報部】対話型AI「チャットGPT」って何？道内の企業でも活用広がる（出演、AIの使用に関するコメント）
    Date : 2023/05/18
    Publisher, broadcasting station: テレビ北海道
    Media report
  • Spotlight on Research: Issa-kun, the artificial intelligence haiku poet
    Date : 2023/05/18
    Publisher, broadcasting station: 北海道大学ウェブサイト 英語版
    Internet
  • 【そもそも解説】ChatGPTの可能性 近づく「人間を超える日」（AIや「シンギュラリティ」に関するコメント）
    Date : 2023/05/18
    Program, newspaper magazine: 朝日新聞
    朝刊紙面 Paper
  • 明日をキヅク（出演、AIやChatGPTに関するコメント）
    Date : 2023/05/14
    Publisher, broadcasting station: 北海道放送HBCラジオ
    Media report
  • 牧野蘭太郎とAI一茶くんの植物俳句対決（「AI一茶くん」の紹介）
    Date : 2023/05/08
    Program, newspaper magazine: 牧野蘭太郎YouTube
    Internet
  • 一茶くんと句会を楽しみました（「AI一茶くん」の紹介、栗林浩氏による寄稿文）
    Date : 2023/04/25
    Publisher, broadcasting station: 角川文化振興財団
    Program, newspaper magazine: 「俳句」5月号
    Paper
  • 話題のAIサービス「チャットGPTって？」（出演、ChatGPTに関するコメントを掲載）
    Date : 2023/04/18
    Publisher, broadcasting station: 北海道放送
    Program, newspaper magazine: 情報報道番組「今日ドキッ！」
    Media report
  • （時時刻刻）生成ＡＩ、アートもデータ 対価なく模倣「道義に反する」（ChatGPTに関するコメントを掲載）
    Date : 2023/04/13
    Publisher, broadcasting station: 朝日新聞
    朝刊2面 Paper
  • 対話ＡＩ、大学が注意喚起 チャットＧＰＴ 論文利用に指針も 誤情報や思考力低下懸念（対話型ＡＩに関するコメントを掲載）
    Date : 2023/04/12
    Publisher, broadcasting station: 北海道新聞
    26面 Paper
  • 【そもそも解説】ChatGPT、驚きの会話力がもたらす未来と死角（ChatGPTとAIに関するコメントを掲載）
    Date : 2023/04/12
    Publisher, broadcasting station: 朝日新聞
    Paper
  • チャットGPT禁止の大学も 一部では授業導入の動き（ChatGPTの使用と今後の大学教育に関するコメントを掲載）
    Date : 2023/04/12
    Publisher, broadcasting station: 信濃毎日新聞
    Paper
  • 対話型ＡＩ 大学が規制 論文利用警告、在り方模索（ChatGPTの使用と今後の大学教育に関するコメントを掲載）
    Date : 2023/04/12
    Publisher, broadcasting station: 静岡新聞
    28面 Paper
  • 人間の仕事 なくならない（「AIが人間に取って代わる未来は来るのか」について回答）
    Date : 2023/03/10
    Publisher, broadcasting station: 読売中高生新聞
    3面 Paper
  • 特集「温故創DX 俳句編『俳人、AIが作った俳句と競う』」（鼎談、「AI一茶くん」の紹介）
    Date : 2023/03
    Publisher, broadcasting station: 旭化成株式会社ウェブサイト
    Internet
  • 「即答」ChatGPTの利用急拡大、ただし過信は禁物…教育現場「正確さに懸念」（ChatGPTに関するコメントを掲載）
    Date : 2023/02/14
    Program, newspaper magazine: 読売新聞
    Paper
  • AI人材育て 課題解決（「札幌AI道場」の成果発表会、およびコメントを掲載）
    Date : 2023/02/09
    Program, newspaper magazine: 北海道新聞
    Paper
  • 人はなぜ俳句を詠むのか 俳句生成人工知能は俳句をどこへ向かわせるか（『AI研究者と俳人 人はなぜ俳句を詠むのか』書評）
    Date : 2022/12/23
    Program, newspaper magazine: 週刊読書人
    Paper
  • ソウミラ ～相対的未来情報発信番組～（ゲスト出演、解説）
    Date : 2022/12/22
    Publisher, broadcasting station: ラジオNIKKEI
    Media report
  • 新企画 AIが作ったものはどれ？
    Date : 2022/11/24
    Publisher, broadcasting station: 日本テレビ
    Program, newspaper magazine: 「ぐるぐるナインティナイン」
    Media report
  • 北海道農業、新興企業がけん引 クラウド飼育情報管理
    Date : 2022/11/15
    Program, newspaper magazine: 日本経済新聞
    Paper
  • AIと共作俳句高評価（「AI一茶くん」について掲載）
    Date : 2022/11/07
    Program, newspaper magazine: 北海道新聞
    Paper
  • 俳句を作ったのはヒト!? 「見分けられない」京大実験で判明（「AI一茶くん」について掲載）
    Date : 2022/11/03
    Program, newspaper magazine: 毎日新聞
    Paper
  • AIとヒトの未来議論 札幌でノーマップス開幕
    Date : 2022/10/20
    Program, newspaper magazine: 北海道新聞
    Paper
  • エウレカ！北大 AI深層学習で俳句 （インタビュー記事を掲載）
    Date : 2022/10/05
    Publisher, broadcasting station: 読売新聞
    Paper
  • SAPPORO AI LAB
    Date : 2022/09/19
    Publisher, broadcasting station: テレビ北海道
    Program, newspaper magazine: 「シン・経営2.0 ―経営支援プラットフォーム最前線―」
    Media report
  • 「AI人材『道場』で育成産官学連携 市内に開設」（札幌AI道場の開設、および基調講演について掲載）
    Date : 2022/08/05
    Program, newspaper magazine: 北海道新聞
    Paper
  • 「AI人材育成 産官学で『道場』『サッポロバレー」復活めざす』 （札幌AI道場の開設、および基調講演について掲載）
    Date : 2022/08/05
    Program, newspaper magazine: 朝日新聞
    Paper
  • 【芭蕉vs.AI】感情を持たないAIが俳句を詠む『奇妙さ』がまた面白い（『ＡＩ研究者と俳人 人はなぜ俳句を詠むのか』書評)
    Date : 2022/08/01
    Publisher, broadcasting station: 日刊ゲンダイDEGITAL
    Program, newspaper magazine: 『熟読乱読 世相斬り』
    Internet
  • 「AIと創作の未来」（AI俳句についての解説が掲載）
    Date : 2022/07/07
    Program, newspaper magazine: 朝日新聞
    Paper
  • 『謎多き全貌』に光（『AI研究者と俳人 人はなぜ俳句を詠むのか』書評）
    Date : 2022/06/26
    Program, newspaper magazine: 朝日新聞
    俳句時評 Paper
  • 絵画と俳句 これまで、今、そしてこれから 「バンクシーとAI俳句」
    Date : 2022/06
    Publisher, broadcasting station: 現代俳句協会
    Program, newspaper magazine: 現代俳句
    Paper
  • 調和技研×AIの旗手 #1 ：川村 秀憲教授（北海道大学）
    Date : 2022/06
    https://www.chowagiken.co.jp/news/20220615-2/ Internet
  • 『ＡＩ研究者と俳人 人はなぜ俳句を詠むのか』の書評を掲載
    Date : 2022/05/22
    Program, newspaper magazine: 北海道新聞
    ＜書評＞ＡＩ研究者と俳人 人はなぜ俳句を詠むのか Paper
  • 「（サンキュータツオの「語る本」を読む）川村秀憲、大塚凱著『ＡＩ研究者と俳人 人はなぜ俳句を詠むのか』」（『ＡＩ研究者と俳人 人はなぜ俳句を詠むのか』書評）
    Date : 2022/05/21
    Program, newspaper magazine: 朝日新聞
    Paper
  • 『ＡＩ研究者と俳人 人はなぜ俳句を詠むのか』の書評を掲載
    Date : 2022/04/28
    Publisher, broadcasting station: 思潮社
    Program, newspaper magazine: 現代詩手帖5月号
    連載「対話はつづく」 Paper
  • 「顧客ニーズAIが提案」にAIのビジネス活用について掲載
    Date : 2022/04/19
    Program, newspaper magazine: 北海道新聞
    Paper
  • 「農業とAIを考える」にて人と人工知能の調和についてのインタビュー記事を掲載
    Date : 2022/03/02
    Publisher, broadcasting station: 農林中央金庫運営ウェブサイト
    Program, newspaper magazine: AgriweB
    Internet
  • 「東大・松尾研、起業熱再び 22年は10社前後が創業へ」に調和系工学研究室発のベンチャー企業について掲載
    Date : 2021/12/29
    Program, newspaper magazine: 日本経済新聞
    Paper
  • 「最優秀句は『香水を深めて…』恋の俳句王、AIの力作に驚きの声」に人工知能による俳句生成を掲載
    Date : 2021/11/07
    Program, newspaper magazine: 朝日新聞
    Paper
  • 「俳句チャンピオン決定戦 恋の選句王大会2 ～AIは恋の俳句が詠めるのか？～」において人工知能による俳句生成を紹介
    Date : 2021/11/07
    Publisher, broadcasting station: NHK
    Program, newspaper magazine: 愛媛県のニュース
    Media report
  • 調和系工学研究室発ベンチャーの取り組みを掲載
    Date : 2021/11
    Publisher, broadcasting station: 北海道大学
    Program, newspaper magazine: サステナビリティレポート2021
    Pr
  • 「フルポン村上の俳句修行・番外編 AIが作った俳句の価値は（座談会）」にてAI一茶くんにより生成された俳句コンテンツを掲載
    Date : 2021/10/15
    Publisher, broadcasting station: 朝日新聞社運営ウェブサイト
    Program, newspaper magazine: 好書好日
    Internet
  • 『人工知能が俳句を詠む AI一茶くんの挑戦』の書評を掲載
    Date : 2021/09/22
    Program, newspaper magazine: 週刊文春
    文春図書館「著者は語る」 Paper
  • 「フルポン村上の俳句修行・番外編 人工知能「AI一茶くん」と三番勝負！」にてAI一茶くんにより生成された俳句コンテンツを掲載
    Date : 2021/09/10
    Publisher, broadcasting station: 朝日新聞社運営ウェブサイト
    Program, newspaper magazine: 好書好日
    Internet
  • 「道内文学 俳句 AI一茶くん驚きの進化」にAI俳句の研究を掲載
    Date : 2021/08/21
    Program, newspaper magazine: 北海道新聞
    Paper
  • 『人工知能が俳句を詠む AI一茶くんの挑戦』の書評を掲載
    Date : 2021/08/09
    Program, newspaper magazine: 日刊工業新聞
    新刊 Paper
  • AI俳句の生成，画像認識によるロードヒーティングの制御をはじめとする調和系工学研究室のAI開発・利活用の取り組みを掲載
    Date : 2021/08/04
    Publisher, broadcasting station: 総務省
    Program, newspaper magazine: AIネットワーク社会推進会議「報告書2021」
    Others
  • 「人工知能が俳句を詠む 句会に参加する日は来るか」に『人工知能が俳句を詠む AI一茶くんの挑戦』の書評を掲載
    Date : 2021/07/30
    Program, newspaper magazine: 日本経済新聞
    Paper
  • 「北大人図鑑No.9」に人と機械の調和についてのインタビュー動画を掲載
    Date : 2021/06/09
    Publisher, broadcasting station: 北海道大学 大学院教育推進機構 オープンエデュケーションセンター 科学技術コミュニケーション教育研究部門（CoSTEP）運営ウェブサイト
    Program, newspaper magazine: いいね！Hokudai
    Internet
  • AI一茶くんによる俳句コンテンツを提供
    Date : 2021/05/30
    Publisher, broadcasting station: 札幌テレビ放送
    Program, newspaper magazine: ブギウギ専務
    Media report
  • AI俳句の紹介記事を掲載
    Date : 2021/05/19
    Publisher, broadcasting station: 株式会社学研ホールディングス運営ウェブサイト
    Program, newspaper magazine: マナビスタ
    Internet
  • 「テクノロジーと人との調和 人工知能最前線」と題した講演を掲載
    Date : 2021/04/09
    Publisher, broadcasting station: 日本経済新聞
    札幌日経懇話会、AI普及拡大へ 川村教授が講演 Paper
  • AI俳句の俳句コンテンツ提供
    Date : 2021/04/05
    Publisher, broadcasting station: 日本テレビ
    Program, newspaper magazine: しゃべくり007
    Media report
  • AI一茶くんによる俳句生成の取り組みを掲載
    Date : 2021/04/01
    Publisher, broadcasting station: 北海道大学生活協同組合
    Program, newspaper magazine: きぼうの虹 第393号
    Pr
  • AI一茶くんによる俳句生成の取り組みを掲載
    Date : 2021/03/14
    Publisher, broadcasting station: 朝日新聞社運営ウェブサイト
    Program, newspaper magazine: 好書好日
    Internet
  • 調和系工学研究室の取り組みを紹介
    Date : 2021/02/14
    Publisher, broadcasting station: 北海道放送
    Program, newspaper magazine: 北のフロンティア 人に寄り添うＡＩ 北海道大学調和系工学研究室
    Media report
  • 料理レシピを構造化するAIの研究を掲載
    Date : 2021/02
    Publisher, broadcasting station: 株式会社ニチレイ運営ウェブサイト
    Program, newspaper magazine: このみる研究所
    Internet
  • 「デジタルVS ＡＩ紡ぐ芸術、続々と」にAI俳句の研究を掲載
    Date : 2020/12/21
    Program, newspaper magazine: 毎日新聞
    Paper
  • 「芸術に挑戦してこそ進歩に貢献『AI映画』来年公開へ」にAI俳句の研究を掲載
    Date : 2020/12/09
    Program, newspaper magazine: 毎日新聞ウェブ版
    Internet
  • 「公民」の中学校副教材にAI一茶くんによる俳句コンテンツを提供
    Date : 2020/12
    Publisher, broadcasting station: 東京法令出版株式会社
    Program, newspaper magazine: 「見る，解く，納得！公民資料2021」
    Others
  • AI一茶くんによる俳句コンテンツを提供
    Date : 2020/11/29
    Publisher, broadcasting station: BSフジ
    Program, newspaper magazine: タイプライターズ～物書きの世界～
    Media report
  • 「3社対談で解き明かす『コロナ禍における産学連携のススメ』」にてインタビュー記事を掲載
    Date : 2020/11/24
    Publisher, broadcasting station: eiicon company運営ウェブサイト
    Program, newspaper magazine: TOMORUBA
    Internet
  • 人工知能による俳句生成を紹介
    Date : 2020/10/15
    Publisher, broadcasting station: テレビ東京
    Program, newspaper magazine: 探求の階段
    Media report
  • AI一茶くんによる俳句コンテンツを提供
    Date : 2020/08/05
    Publisher, broadcasting station: 日本テレビ
    Program, newspaper magazine: 1億人の大質問！？笑ってコラえて！
    Media report
  • 「スタートアップ経営者ら座談会 人・カネの壁 ITで挑む」に座談会記事を掲載
    Date : 2020/07/31
    Program, newspaper magazine: 日本経済新聞
    Paper
  • 「文化時評 人工知能に『文学の批評」は可能か』」にAI俳句の研究を掲載)
    Date : 2020/07/26
    Program, newspaper magazine: 日本経済新聞
    Paper
  • インタビュー記事を掲載
    Date : 2020/05/15
    Program, newspaper magazine: 財界さっぽろ6月号
    《北海道応援企画》激動の2020年を突き進め“北海道の底力”AI専門家集団として民間との共同研究を推進 Paper
  • 「暮らしのAI」においてファッションを理解する人工知能を紹介
    Date : 2020/04/23
    Publisher, broadcasting station: テレビ北海道
    Program, newspaper magazine: ゆうがたサテライト道新ニュース
    Media report
  • AI一茶くんによる俳句コンテンツを提供
    Date : 2020/04/12
    Publisher, broadcasting station: 日本テレビ
    Program, newspaper magazine: 人間 VS AI
    Media report
  • 「『適正価格』AIが判断」にオークションメカニズムの研究を掲載
    Date : 2020/04/06
    Program, newspaper magazine: 北海道新聞
    Paper
  • 「俳句遊びノススメ AI一茶くん」にAI俳句の研究を掲載
    Date : 2020/04/06
    Program, newspaper magazine: 西日本新聞
    Paper
  • 人工知能による俳句生成の意義や生成の仕組みを掲載
    Date : 2020/02/17
    Publisher, broadcasting station: Newton別冊
    Program, newspaper magazine: ゼロからわかる人工知能 増補第２版
    Paper
  • 「意思なき想像最後は人」に国語・美術分野での人工知能の活用の一例としてAI一茶くんの取り組みを掲載
    Date : 2020/01/03
    Program, newspaper magazine: 日本経済新聞
    Paper
  • 「本物そっくりAIモデル 俳句でも素人超」にAI俳句の研究を掲載
    Date : 2020/01/03
    Program, newspaper magazine: 日本経済新聞
    Paper
  • 「ＡＩで省エネ融雪 カメラが積雪判断、燃料費４割削減 北ガスと北大開発 ２０年度にも販売」に人工知能によるによるロードヒーティングの制御の研究を掲載
    Date : 2020/01/03
    Program, newspaper magazine: 北海道新聞
    Paper
  • 「人間とAIの協働こそが社会課題の解決に直結する」と題した解説記事が掲載
    Date : 2019/12/12
    Publisher, broadcasting station: 日経ムック
    Program, newspaper magazine: AIフロンティア
    Paper
  • 人工知能による俳句の取り組みやその周辺の紹介
    Date : 2019/12/05
    Program, newspaper magazine: 鷹 第五六巻第一二号
    俳句時評 人工知能が俳句を作るということ Paper
  • 人工知能による俳句の現状としてAI一茶くんにより生成された俳句と生成の仕組みを掲載
    Date : 2019/11/25
    Program, newspaper magazine: 月刊俳句界二〇一九年十二月号
    AIと作句の戦い Paper
  • 「AI俳人・歌人 人の感性を詠む」にAI俳句の研究を掲載
    Date : 2019/11/11
    Program, newspaper magazine: 日本経済新聞
    Paper
  • AI俳句の研究の過程や背景について掲載
    Date : 2019/10/30
    Publisher, broadcasting station: 岩波新書
    Program, newspaper magazine: 「日曜俳句入門」(吉竹純著)
    Others
  • ＡＩ俳人が芭蕉ゆかりの俳句大会に、結果は？
    Date : 2019/09/18
    Program, newspaper magazine: 朝日新聞
    Paper
  • 「AIが風景写真から俳句を詠む」において人工知能による俳句生成を紹介
    Date : 2019/09/17
    Publisher, broadcasting station: NHK総合
    Program, newspaper magazine: かがのとイブニング
    Media report
  • 「AI一茶くんに辛口評」に人工知能による俳句生成を掲載
    Date : 2019/09/16
    Program, newspaper magazine: 北陸中日新聞
    Paper
  • 山中の風景でＡＩが作句 芭蕉祭全国大会で世界初「吟行」
    Date : 2019/09/15
    Program, newspaper magazine: 北国新聞
    Paper
  • 「俳句AIチーム山中温泉を視察」に人工知能による俳句生成を掲載
    Date : 2019/09/03
    Program, newspaper magazine: 北國新聞
    Paper
  • 人工知能による俳句生成を掲載
    Date : 2019/08/28
    Program, newspaper magazine: 旅行読売
    芭蕉祭山中温泉全国俳句大会AIも参加する吟行句会 Paper
  • 「『ＡＩ俳句』研究」に人工知能による俳句生成を掲載
    Date : 2019/08/22
    Program, newspaper magazine: 日刊工業新聞
    Paper
  • 「AIの俳句批評願います」に AI俳句協会の結成とホームページの開設について掲載
    Date : 2019/08/20
    Program, newspaper magazine: 読売新聞
    Paper
  • 「AIが恋の俳句 愛媛の俳人の評価は？」において人工知能による俳句生成を紹介
    Date : 2019/08/09
    Publisher, broadcasting station: NHK
    Program, newspaper magazine: おはよう日本
    Media report
  • 人工知能による俳句生成の発展状況としてAI一茶くんの生成した俳句を掲載
    Date : 2019/07/25
    Publisher, broadcasting station: 現代俳句協会
    Program, newspaper magazine: 現代俳句令和元年八月号
    解説- AI俳句とその周辺 Paper
  • 人工知能による俳句生成とファッションを理解する人工知能を紹介
    Date : 2019/07/23
    Publisher, broadcasting station: 北海道テレビ
    Program, newspaper magazine: onちゃんキャンパスライフ 工学部編
    Paper
  • 「ＡＩに俳句が分かる感性を 道内研究者が協会 評価データを蓄積」に人工知能による俳句生成を掲載
    Date : 2019/07/20
    Program, newspaper magazine: 北海道新聞
    Paper
  • 「AIが読んだ俳句を紹介 金沢の『奥の細道サミット』」に人工知能による俳句生成を紹介
    Date : 2019/07/13
    Publisher, broadcasting station: ヤフー株式会社運営ウェブサイト
    Program, newspaper magazine: Yahoo!ニュース
    Internet
  • 「AIの一茶くん『奥の細道サミット』で俳句詠む」に人工知能による俳句生成を掲載
    Date : 2019/07/13
    Program, newspaper magazine: 毎日新聞
    Paper
  • 「ＡＩが詠んだ俳句を紹介 金沢の『奥の細道サミット』」に人工知能による俳句生成を掲載
    Date : 2019/07/13
    Program, newspaper magazine: 東京新聞
    Paper
  • 「AIが詠む恋秀句は」に人工知能による俳句生成を掲載
    Date : 2019/07/07
    Program, newspaper magazine: 愛媛新聞
    Paper
  • 「AIに俳句が分かる感性を」に人工知能による俳句生成を掲載
    Date : 2019/07/03
    Program, newspaper magazine: 北海道新聞
    Paper
  • 俳句チャンピオン決定戦 恋の選句王大会2019～ＡＩ一茶君に恋は詠めるのか！プロジェクト～
    Date : 2019/07/01
    Publisher, broadcasting station: 愛媛県域ＮＨＫ
    Program, newspaper magazine: ひめポン！645
    Media report
  • 雑記帳 俳句を学習させたＡＩ（人工知能）「一茶君」が詠んだ恋の俳句から…
    Date : 2019/06/30
    Program, newspaper magazine: 毎日新聞
    Paper
  • 「恋」詠んだＡＩの７８００句 人間が選句対決
    Date : 2019/06/30
    Program, newspaper magazine: 朝日新聞
    Paper
  • 俳句チャンピオン決定戦 恋の選句王大会2019～ＡＩ一茶君に恋は詠めるのか！プロジェクト～
    Date : 2019/06/29
    Publisher, broadcasting station: 愛媛県域ＮＨＫ
    Program, newspaper magazine: ひめポン！645
    Media report
  • 「AI、表現力も人以上？」に人工知能による俳句生成を掲載
    Date : 2019/06/23
    Program, newspaper magazine: 日本経済新聞
    Paper
  • 「俳句チャンピオン決定戦 恋の選句王大会2019～ＡＩ一茶君に恋は詠めるのか！プロジェクト～」の様子がYouTubeに公開
    Date : 2019/06
    Publisher, broadcasting station: 愛媛CATV
    Program, newspaper magazine: たうんニュース2019年6月
    Media report
  • 身近な科学技術の成果の一例として人工知能俳句の意義や俳句の生成の仕組みを掲載
    Date : 2019/06
    Publisher, broadcasting station: 文部科学省
    Program, newspaper magazine: 令和元年度版 科学技術白書
    Others
  • ファッション画像の印象推定に関する研究成果を掲載
    Date : 2019/05/20
    Publisher, broadcasting station: 日経BP社
    Program, newspaper magazine: 日経クロストレンド
    洋服のかわいい度をAIが診断 ファッション業界向け新ツール Internet
  • 人工知能による俳句生成の現状としてAI一茶くんの取り組みを紹介
    Date : 2019/05/14
    Publisher, broadcasting station: 本阿弥書店
    Program, newspaper magazine: 俳壇二〇一九年六月号
    特別企画「どう思う？AI俳句」 Paper
  • 「詠み人おらず 俳人チームに善戦したのは・・・かなしみの片手ひらいて渡り鳥」に人工知能による俳句生成を掲載
    Date : 2018/12/05
    Program, newspaper magazine: 朝日新聞
    Paper
  • 「AIが人に挑んで五・七・五 北大育ち『一茶くん』愛媛の俳人に苦杯」に人工知能による俳句生成を掲載
    Date : 2018/12/05
    Program, newspaper magazine: 朝日新聞
    Paper
  • 「AIが五感に挑む五七五 北大研究 愛媛の俳人と対決」に人工知能による俳句生成を掲載
    Date : 2018/12/03
    Program, newspaper magazine: 朝日新聞
    Paper
  • 競輪界にＡＩ予想が初登場…チャリロトが北大と共同研究
    Date : 2018/10/17
    Program, newspaper magazine: スポーツ報知
    Paper
  • 「AIとの対局 文芸の意味問う」に人工知能による俳句生成を掲載
    Date : 2018/08/21
    Program, newspaper magazine: 北海道新聞
    Paper
  • 「俳句でAIと人類対決」に人工知能による俳句生成を掲載
    Date : 2018/07/27
    Program, newspaper magazine: 北海道新聞
    Paper
  • 「AIは文豪を超える？ 小説や詩の創作にも進出」に人工知能による俳句生成を掲載
    Date : 2018/07/14
    Program, newspaper magazine: 東愛知新聞
    Paper
  • 「AIは文豪を超える？ 画像認識し作句/文学賞選考を追加」に人工知能による俳句生成を掲載
    Date : 2018/07/13
    Program, newspaper magazine: 福井新聞
    Paper
  • 「AIは文豪を超える？ 小説や詩の創作にも進出」に人工知能による俳句生成を掲載
    Date : 2018/07/10
    Program, newspaper magazine: 徳島新聞
    Paper
  • 「AIは文豪を超える？ 小説や詩の創作にも進出」に人工知能による俳句生成を掲載
    Date : 2018/07/08
    Program, newspaper magazine: 福島民報
    Paper
  • 「AIは文豪を超えるか」に人工知能による俳句生成を掲載
    Date : 2018/07/07
    Program, newspaper magazine: 北日本新聞
    Paper
  • 「AIは文豪を超える？ 小説や詩の創作にも進出」に人工知能による俳句生成を掲載
    Date : 2018/07/03
    Program, newspaper magazine: 苫小牧民法
    Paper
  • 「AIは文豪を超える？ 小説や詩の創作にも進出」に人工知能による俳句生成を掲載
    Date : 2018/07/01
    Program, newspaper magazine: 岩手日報
    Paper
  • 「AIは文豪を超える？ 小説や詩の創作にも進出」に人工知能による俳句生成を掲載
    Date : 2018/06/30
    Program, newspaper magazine: 陸奥新聞
    Paper
  • 「写真から 学ぶAI 一句詠む」に人工知能による俳句生成を掲載
    Date : 2018/06/02
    Program, newspaper magazine: 読売新聞大阪版
    Paper
  • 「AI 一句読みます 一句選びます 一茶や子規五万句お手本」にAI一茶くんの取り組みとAI一茶くんにより生成した俳句を掲載
    Date : 2018/06/02
    Program, newspaper magazine: 読売新聞東京版
    Paper
  • 「写真から 句を詠むAI 一茶くん」にAI一茶くんの取り組みとAI一茶くんにより生成した俳句を掲載
    Date : 2018/05/02
    Program, newspaper magazine: 信濃毎日新聞
    Paper
  • AI一茶くんの研究過程およびAI一茶くんにより生成された俳句コンテンツを提供
    Date : 2018/02/26
    Publisher, broadcasting station: 日本放送協会
    Program, newspaper magazine: 超絶 凄ワザ！
    Media report
  • 「道内文学 俳句 AI一茶くん驚きの進化」にAI俳句の研究を掲載
    Date : 2011/08/11
    Program, newspaper magazine: 北海道新聞
    Paper
  • 人工知能による俳句生成の取り組みとAI一茶くんによる生成された俳句コンテンツを掲載
    Program, newspaper magazine: 朝日新聞
    天声人語 Paper

Academic Contribution

  • 株式会社Aill 取締役(非常勤)
    Date (from-to) :2020/04/01-Today
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社Aill
  • 株式会社インターパーク 取締役（非常勤）
    Date (from-to) :2019/05/01-Today
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社インターパーク
  • 株式会社フュージョン（社外取締役）
    Date (from-to) :2016/08/08-Today
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社フュージョン
  • 株式会社調和技研（取締役）
    Date (from-to) :2010/04-Today
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社調和技研
  • 株式会社HBA（アドバイザー）
    Date (from-to) :2024/04/01-2025/03/31
    Role: Others
  • みらいコンサルティング株式会社（顧問）
    Date (from-to) :2024/04/01-2025/03/31
    Role: Others
  • アチーブメント株式会社（顧問）
    Date (from-to) :2024/01/01-2025/03/31
    Role: Others
    Organizer, responsible person: アチーブメント株式会社
  • 株式会社マイクロネット（技術顧問）
    Date (from-to) :2023/04/01-2025/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社マイクロネット
  • ザ・サン・ストラテジック・ソリューションズ株式会社（顧問）
    Date (from-to) :2023/04/01-2025/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: ザ・サン・ストラテジック・ソリューションズ株式会社
  • アイシン・ソフトウェア株式会社（技術顧問）
    Date (from-to) :2023/01/01-2025/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: アイシン・ソフトウェア株式会社
  • 株式会社グッドフェローズ（技術顧問）
    Date (from-to) :2022/10/24-2025/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社グッドフェローズ
  • AWL株式会社（技術顧問）
    Date (from-to) :2022/06/09-2025/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: AWL株式会社
  • 株式会社イノベーションプラス（アドバイザー）
    Date (from-to) :2021/07/01-2025/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社イノベーションプラス
  • 株式会社ニッコー（AI研究アドバイザー）
    Date (from-to) :2021/04/01-2025/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社ニッコー
  • 株式会社サンクレエ（顧問）
    Date (from-to) :2021/04/01-2025/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社サンクレエ
  • 株式会社ジャパンテクニカルソフトウェア（AIアドバイザー）
    Date (from-to) :2021/01/19-2025/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社ジャパンテクニカルソフトウェア
  • 株式会社クレスコ（情報科学/人工知能（AI）研究者）
    Date (from-to) :2024/04/01-2024/09/30
    Role: Others
    Organizer, responsible person: 株式会社クレスコ
  • 北海道デジタル推進委員会（アドバイザー）
    Date (from-to) :2023/10/01-2024/09/30
    Role: Others
    Organizer, responsible person: 北海道経済同友会
  • 株式会社ディープコア（顧問）
    Date (from-to) :2023/08/01-2024/09/30
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社ディープコア
  • バリュエンステクノロジーズ株式会社（顧問）
    Date (from-to) :2020/04/01-2024/08/31
    Role: Others
    Type: Review
    Organizer, responsible person: バリュエンステクノロジーズ株式会社
  • 2023 年度中小企業技術活性化助成事業（選考委員）
    Date (from-to) :2023/09-2024/03/31
    Role: Review
    Organizer, responsible person: 公益財団法人 北海道銀行中小企業人材育成基金
  • 2023年度ものづくり開発・グリーン成長分野推進事業（審査委員）
    Date (from-to) :2023/04/10-2024/03/31
    Role: Review
    Organizer, responsible person: ノーステック財団
  • GMOサイバーセキュリティbyイエラエ株式会社（技術アドバイザー）
    Date (from-to) :2023/04/01-2024/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: GMOサイバーセキュリティbyイエラエ株式会社
  • 穴吹興産株式会社（AI研究アドバイザー）
    Date (from-to) :2023/04/01-2024/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 穴吹興産株式会社
  • ノザキ製菓株式会社（顧問）
    Date (from-to) :2023/04/01-2024/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: ノザキ製菓株式会社
  • 株式会社Innovation BASE 北海道（技術顧問）
    Date (from-to) :2023/04/01-2024/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社Innovation BASE 北海道
  • 株式会社スクリエ（顧問）
    Date (from-to) :2021/10/01-2024/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社スクリエ
  • 株式会社クレスコ（情報科学/人工知能（AI）研究者）
    Date (from-to) :2021/04/01-2024/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社クレスコ
  • 株式会社ニッセイコム（技術顧問）
    Date (from-to) :2022/07/01-2024/03/29
    Role: Others
    Organizer, responsible person: 株式会社ニッセイコム
  • X-Tech Innovation 2023最終選考会（審査委員）
    Date (from-to) :2023/12/06
    Role: Review
    Organizer, responsible person: 株式会社北海道銀行
  • 2022 年度中小企業技術活性化助成事業（選考委員）
    Date (from-to) :2022/08/16-2023/03/31
    Role: Review
    Organizer, responsible person: 公益財団法人 北海道銀行中小企業人材育成基金
  • 札幌型ものづくり開発推進事業（審査委員）
    Date (from-to) :2022/04/20-2023/03/31
    Role: Review
    Organizer, responsible person: ノーステック財団
  • 株式会社ビッグ（顧問）
    Date (from-to) :2021/04/01-2023/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社ビッグ
  • X-Tech Innovation 2022最終選考会（審査委員）
    Date (from-to) :2022/12/08
    Role: Review
    Organizer, responsible person: 株式会社 北海道銀行
  • 北海道・大学等発スタートアップ育成プラットフォームにおけるDemo Day（審査委員）
    Date (from-to) :2022/01/06-2022/03/31
    Role: Review
    Organizer, responsible person: ノーステック財団
  • 2021 年度中小企業技術活性化助成事業（選考委員）
    Date (from-to) :2021/08/30-2022/03/31
    Role: Review
    Organizer, responsible person: 公益社団法人北海道銀行中小企業人材育成基金
  • QUALITY HOKKAIDO一般社団法人（アドバイザー）
    Date (from-to) :2021/07/07-2022/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: QUALITY HOKKAIDO 一般社団法人
  • アズミー株式会社（顧問）
    Date (from-to) :2021/06/01-2022/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: アズミー株式会社
  • SCORE研究開発課題審査委員会（審査委員）
    Date (from-to) :2021/05/17-2022/03/31
    Role: Review
    Organizer, responsible person: 公益財団法人 北海道科学技術総合振興センター (ノーステック財団)
  • ザ・サン・ストラテジック・ソリューションズ株式会社（顧問）
    Date (from-to) :2021/04/01-2022/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: ザ・サン・ストラテジック・ソリューションズ株式会社
  • 札幌型ものづくり開発推進事業（審査委員）
    Date (from-to) :2021/04-2022/03/31
    Role: Review
    Organizer, responsible person: ノーステック財団
  • INSIGHT LAB株式会社（顧問）
    Date (from-to) :2019/01/01-2022/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: INSIGHT LAB株式会社
  • X-Tech Innovetion 2021最終選考会（審査委員）
    Date (from-to) :2021/12/09
    Role: Review
    Organizer, responsible person: 北海道銀行
  • ヤマト運輸株式会社（アドバイザー）
    Date (from-to) :2021/01/15-2021/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: ヤマト運輸株式会社
  • 学内審査委員会（外部有識者）
    Date (from-to) :2020/11/01-2021/03/31
    Role: Review
    Organizer, responsible person: 長崎県立大学
  • ビッグデータ・AIコンペティション（審査員）
    Date (from-to) :2020/06/01-2021/03/31
    Role: Review
    Organizer, responsible person: NoMaps実行委員会
  • 札幌型ものづくり開発推進事業（審査委員）
    Date (from-to) :2020/04/16-2021/03/31
    Role: Review
    Organizer, responsible person: ノーステック財団
  • トヨタ自動車北海道株式会社（アドバイザー）
    Date (from-to) :2019/10/15-2021/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: トヨタ自動車北海道株式会社
  • 株式会社スペックホルダー（アドバイザー）
    Date (from-to) :2019/06/01-2021/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社スペックホルダー
  • 株式会社スーパーホテル（顧問）
    Date (from-to) :2019/06/01-2021/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社スーパーホテル
  • 株式会社クレスコ（アドバイザー）
    Date (from-to) :2018/07/01-2021/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社クレスコ
  • 社団法人さっぽろイノベーションラボ（顧問）
    Date (from-to) :2020/03/16-2021/03/15
    Role: Others
    Type: Review
    Organizer, responsible person: 社団法人さっぽろイノベーションラボ
  • X-Tech Innovetion 2020最終選考会（審査委員）
    Date (from-to) :2020/12/17
    Role: Review
    Organizer, responsible person: 北海道銀行
  • 株式会社SOU Technologies（顧問）
    Date (from-to) :2019/11/01-2020/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社SOU Technologies
  • 札幌型ものづくり開発推進事業（審査委員）
    Date (from-to) :2019/04/15-2020/03/31
    Role: Review
    Organizer, responsible person: ノーステック財団
  • 株式会社サンクレエ（顧問）
    Date (from-to) :2016/09/01-2020/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社サンクレエ
  • 株式会社ニッコー（アドバイザー）
    Date (from-to) :2019/03/01-2020/02/29
    Role: Others
    Type: Competition etc
    Organizer, responsible person: 株式会社ニッコー
  • 株式会社ビッグ（顧問）
    Date (from-to) :2017/12/21-2019/12/20
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社ビッグ
  • X-Tech Innovetion 2019最終選考会（審査委員）
    Date (from-to) :2019/12/11
    Role: Review
    Organizer, responsible person: 北海道銀行
  • 穴吹興産株式会社（アドバイザー）
    Date (from-to) :2018/12/01-2019/11/30
    Role: Others
    Type: Review
    Organizer, responsible person: 穴吹興産株式会社
  • 平岸ハイヤー株式会社（アドバイザー）
    Date (from-to) :2018/11/01-2019/10/31
    Role: Others
    Type: Review
    Organizer, responsible person: 平岸ハイヤー株式会社
  • 株式会社サングリン太陽園内スマート農業共同体（顧問）
    Date (from-to) :2018/11/26-2019/09/30
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社サングリン太陽園内スマート農業共同体
  • AI TOKYO LAB株式会社（顧問）
    Date (from-to) :2016/07/01-2019/06/30
    Role: Others
    Type: Review
    Organizer, responsible person: AI TOKYO LAB株式会社
  • ザ・サン・ストラテジック・ソリューションズ株式会社（顧問）
    Date (from-to) :2018/06/01-2019/05/31
    Role: Others
    Type: Review
    Organizer, responsible person: ザ・サン・ストラテジック・ソリューションズ株式会社
  • 小仕事株式会社（アドバイザー）
    Date (from-to) :2018/11/01-2019/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 小仕事株式会社
  • 札幌型ものづくり開発推進事業（審査委員）
    Date (from-to) :2018/04/19-2019/03/31
    Role: Review
    Organizer, responsible person: ノーステック財団
  • 株式会社アイウェイズコンサルティング（技術顧問）
    Date (from-to) :2018/01/01-2018/12/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社アイウェイズコンサルティング
  • X-Tech Innovetion 2018最終選考会（審査委員）
    Date (from-to) :2018/12/06
    Role: Review
    Organizer, responsible person: 北海道銀行
  • 株式会社道銀地域総合研究所（テーマ評価分析アドバイザー）
    Date (from-to) :2017/12/20-2018/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社道銀地域総合研究所
  • HOKKAIDO学生アプリコンテスト 審査委員会（委員）
    Date (from-to) :2017/06-2018/03/31
    Role: Review
    Organizer, responsible person: 一般社団法人北海道モバイルコンテンツ・ビジネス協議会
  • 札幌型ものづくり開発推進事業（審査委員）
    Date (from-to) :2017/04/19-2018/03/31
    Role: Review
    Organizer, responsible person: ノーステック財団
  • クリプトン・フューチャー・メディア株式会社（顧問）
    Date (from-to) :2016/12/01-2018/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: クリプトン・フューチャー・メディア株式会社
  • 一般社団法人北海道オープンデータ推進協議会（技術顧問）
    Date (from-to) :2016/12-2018/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 一般社団法人北海道オープンデータ推進協議会
  • 株式会社ネイン（顧問）
    Date (from-to) :2017/03/01-2018/02/28
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社ネイン
  • X-Tech Innovetion 2017最終選考会（審査委員）
    Date (from-to) :2018/01/30
    Role: Review
    Organizer, responsible person: 北海道銀行
  • ザ・サン・ストラテジック・ソリューションズ株式会社（顧問）
    Date (from-to) :2016/11/01-2017/10/31
    Role: Others
    Type: Review
    Organizer, responsible person: ザ・サン・ストラテジック・ソリューションズ株式会社
  • SAPPORO AWARD 2017 審査委員会（審査委員）
    Date (from-to) :2017/07/05-2017/09/25
    Role: Review
    Organizer, responsible person: 一般社団法人札幌青年会議所
  • 株式会社インターパーク（顧問）
    Date (from-to) :2017/03/01-2017/04/30
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社インターパーク
  • 株式会社澪標アナリティクス（技術顧問）
    Date (from-to) :2017/02/08-2017/03/31
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社澪標アナリティクス
  • ITイノベーション人材育成モデルプロジェクト支援補助金審査委員会（委員）
    Date (from-to) :2016/08/29-2017/03/31
    Role: Review
    Organizer, responsible person: 札幌市
  • HOKKAIDO学生アプリコンテスト 審査委員会（委員）
    Date (from-to) :2016/06-2017/03/31
    Role: Review
    Organizer, responsible person: 北海道モバイルコンテンツ・ビジネス協議会
  • X-Tech Innovetion 2016最終選考会（審査委員）
    Date (from-to) :2017/02/24
    Role: Review
    Organizer, responsible person: 北海道銀行
  • HOKKAIDO学生アプリコンテスト 審査委員会（委員）
    Date (from-to) :2015/06-2016/03
    Role: Review
    Organizer, responsible person: 北海道モバイルコンテンツ・ビジネス協議会
  • 株式会社ABEJA（技術顧問）
    Date (from-to) :2013/07-2014/06
    Role: Others
    Type: Review
    Organizer, responsible person: 株式会社ABEJA

Others

  • 2021 - Today 人工知能により生成した俳句・川柳によるデータベースを一般公開
    人工知能により生成した俳句・川柳によるデータベースを作成し，AI俳句・川柳を検索するシステムを一般に公開 ・AI俳句：https://ai-issa.jp ・AI川柳：http://ai-issa.mydns.jp:43546/

Copyright © MEDIA FUSION Co.,Ltd. All rights reserved.