2024年08月, 計測自動制御学会, 著述賞　　　　　　　　　　　　　　　

2022年09月, 計測自動制御学会, 著述賞　　　　　　　　　　　　　　　

2021年03月, 電気通信普及財団, テレコムシステム技術賞　　　　　　　　　　　　　　　

2021年01月, 計測自動制御学会 中部支部, 支部賞　　　　　　　　　　　　　　　

2020年06月, 日本毒性学会, 学術年会 優秀研究発表賞　　　　　　　　　　　　　　　

2018年11月, 計測自動制御学会, システム・情報部門 学術講演会 2018 優秀発表賞　　　　　　　　　　　　　　　
藤原 幸一

2018年11月, 計測自動制御学会, システム・情報部門 学術講演会 2018 優秀論文賞　　　　　　　　　　　　　　　
藤原 幸一

2018年11月, 人工知能学会, 全国大会優秀賞　　　　　　　　　　　　　　　

2017年12月, Beyond Next Ventures, BRAVE 2017 Winter 優秀賞　　　　　　　　　　　　　　　
藤原 幸一

2017年11月, 計測自動制御学会, システム・情報部門 学術講演会 2017 最優秀論文賞　　　　　　　　　　　　　　　
藤原 幸一

2017年09月, リバネス, バイオテックグランプリ・サントリー賞　　　　　　　　　　　　　　　
藤原 幸一

2017年09月, 計測自動制御学会, 論文賞　　　　　　　　　　　　　　　
藤原 幸一

2017年04月, 新技術開発財団, 市村学術賞 功績賞　　　　　　　　　　　　　　　
藤原 幸一

2016年09月, 計測自動制御学会, 技術賞　　　　　　　　　　　　　　　
藤原 幸一

2015年11月, 計測自動制御学会, システム・情報部門 学術講演会 2015 優秀論文賞　　　　　　　　　　　　　　　
藤原 幸一

2015年03月, 計測自動制御学会, 第1回制御部門マルチシンポジウム 部門大会賞　　　　　　　　　　　　　　　
藤原 幸一

2014年11月, 計測自動制御学会, システム・情報部門 学術講演会 2014 奨励賞　　　　　　　　　　　　　　　
藤原 幸一

2014年11月, 計測自動制御学会, システム・情報部門 学術講演会 2014 優秀論文賞　　　　　　　　　　　　　　　
藤原 幸一

2012年10月, 計測自動制御学会関西支部, 奨励賞　　　　　　　　　　　　　　　
藤原 幸一

In-hospital evaluation of an app-based seizure detection system in dogs: timely detection of generalized tonic–clonic seizures
Junya Hirashima, Miyoko Saito, Daisuke Hasegawa, Rikako Asada, Masato Kitagawa, Daisuke Ito, Shinichi Kanazono, Koichi Fujiwara
Frontiers in Veterinary Science, 12, Frontiers Media SA, 2025年04月29日, ［査読有り］
英語, 研究論文（学術雑誌）, The seizure detection system (SDS) is a wearable device developed by us to detect generalized tonic–clonic seizures (GTCSs) in dogs with epilepsy. In our previous study, a feasibility test was conducted for the SDS, which demonstrated its ability to correctly identify three GTCSs in one dog. To enhance user accessibility and facilitate real-time monitoring of epileptic seizures in dogs, we integrated the system into a smartphone application. This study aimed to evaluate the performance of the app-based SDS in a clinical setting involving a larger number of dogs. Initially, the app-based SDS was tested on a laboratory dog with no history of seizures, and a drug-induced GTCS was accurately detected. Subsequently, an in-hospital evaluation was conducted. A total of 12 dogs were included, comprising 10 dogs with epilepsy, either hospitalized or temporarily housed at participating veterinary hospitals, and two laboratory dogs with epilepsy. In total, 34 GTCSs occurred in four of the 12 dogs, and the app-based SDS correctly detected 25 of the 34 GTCSs. Including the preliminary test results, the overall sensitivity of the app-based SDS was 74.3% (26 out of 35 GTCSs). Two false positives were observed in both in one dog. The false-positive rate and positive predictive value of the app-based SDS for detection of GTCS were 0.018 events/day and 92.6%, respectively. The median detection latency from the onset of a GTCS was 11 s. This study demonstrates that the app-based SDS is effective for detecting GTCSs in hospitalized dogs in clinical settings.

IoT-Based Atrial Fibrillation Screening System, Development and Prospective Study
Koichi Fujiwara, Tetsuma Kawaji, Shota Saeda, Toshitaka Yamakawa, Masashi Kato, Takanori Aizawa, Takafumi Yokomatsu, Shinji Miki
IEEE Internet of Things Journal, 1, 1, Institute of Electrical and Electronics Engineers (IEEE), 2025年01月, ［査読有り］, ［筆頭著者, 責任著者］
英語, 研究論文（学術雑誌）

Adaptive soft-sensor update by Latest Sample Targeting Frustratingly Easy Domain Adaptation
Kaito Katayama, Kazuki Yamamoto, Koichi Fujiwara
Chemometrics and Intelligent Laboratory Systems, 105246, 105246, Elsevier BV, 2024年10月, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）

Blunted tachycardia and cardiac sympathetic denervation in isolated rapid eye movement sleep behavior disorder
Shota Saeda, Yukiyoshi Sumi, Koichi Fujiwara, Hiroshi Kadotani
BMC Neurology, 24, 1, 317, Springer Science and Business Media LLC, 2024年09月04日, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）, 45251782

Polysomnographic features prior to dream enactment behaviors in isolated rapid eye movement sleep behavior disorder.
Shumpei Date, Yukiyoshi Sumi, Koichi Fujiwara, Makoto Imai, Keiko Ogawa, Hiroshi Kadotani
Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology, 166, 74, 86, 2024年07月31日, ［査読有り］, ［責任著者］, ［国際誌］
英語, 研究論文（学術雑誌）, OBJECTIVE: This study aimed to identify electroencephalogram correlates of dream enactment behaviors (DEBs) and elucidate their cortical dynamics in patients with isolated/idiopathic rapid eye movement (REM) sleep behavior disorder (iRBD). METHODS: This cross-sectional study included 15 patients with iRBD. Two REM sleep periods in routine polysomnography were compared: the 60 s preceding the DEBs ("pre-representative behavior" [preR]), and the 60 s with the least submental electromyogram activity ("background" [BG]). Six EEG frequency bands and electrooculogram were analyzed; power spectra, coherence and phase-locking values in four 15-s periods were examined to assess trends. These indices were also compared between preR and BG. RESULTS: Compared with BG, significantly higher delta power in the F3 channel and gamma power in the F4 and O2 channels were observed during preR. For functional connectivity, the widespread beta-band connectivity was significantly increased during preR than BG. CONCLUSION: Before notable REM sleep behaviors, uneven distributed higher EEG spectral power in both very low and high frequencies, and increased wide-range beta band functional connectivity, were observed over 60 s, suggesting cortical correlates to subsequent DEBs. SIGNIFICANCE: This study may shed light on the pathological mechanisms underlies RBD through the routine vPSG analysis, leading to detection of DEBs.

Special Issue on Advanced Technologies for Augmenting Canine–Human Communication
Kazunori Ohno, Miho Nagasawa, Takatomi Kubo, Koichi Fujiwara, Toshitaka Yamakawa, Miiamaaria Kujala
Advanced Robotics, 38, 14, 907, 907, Informa UK Limited, 2024年07月17日, ［査読有り］, ［招待有り］
英語, 研究論文（学術雑誌）

Heart rate variability-based Model for estimating the severity of orthostatic hypotension in patients with REM sleep behavior disorder.
Shota Saeda, Koichi Fujiwara, Yukiyoshi Sumi, Hiroshi Kadotani
Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2024, 1, 4, 2024年07月, ［国際誌］
英語, 研究論文（学術雑誌）, BACKGROUND: Orthostatic hypotension (OH) is a typical autonomic dysfunction in patients with idiopathic REM sleep behavior disorder (iRBD). The Schellong test is a well-known method to evaluate the presence of OH; however, it is burdensome for both patients and the medical staff from the viewpoint of ensuring patient safety. In this study, we developed a machine learning (ML) model to discriminate the presence or absence of OH based on heart rate variability (HRV) in the supine position. METHODS: We recruited elderly healthy participants (HC) and iRBD patients and measured participants' R-R interval (RRI) during the Schellong test. The HRV features were calculated from the RRIs and were used as inputs for the ML model. We trained an ML model that combines two binary classifiers. The first model classifies HC and iRBD, and the second model discriminates the classified patients with iRBD between OH(-) and OH(+). RESULTS: The macro average classification performance was accuracy of 81%, recall of 73%, precision of 82%, and F-measure of 68%. In addition, the sensitivity for OH(+)iRBD was 100%. CONCLUSION: Utilizing this ML model will help to reduce the burden of the Schellong test.

Development and Validation of a Prediction Model for Acute Hypotensive Events in Intensive Care Unit Patients
Toshiyuki Nakanishi, Tatsuya Tsuji, Tetsuya Tamura, Koichi Fujiwara, Kazuya Sobue
Journal of Clinical Medicine, 2024年05月09日, ［査読有り］
英語, 研究論文（学術雑誌）

Beacon-based sleep-wake monitoring in dogs.
Takefumi Kikusui, Mizuho Yagisawa, Kahori Koyama, Yuma Shishikura, Kana Miyamoto, Koichi Fujiwara, Kazuhiko Kume, Kensaku Nomoto, Miho Nagasawa
The Journal of veterinary medical science, 2024年04月29日, ［査読有り］, ［国内誌］
英語, 研究論文（学術雑誌）, The sleep-wake cycle represents a crucial physiological process essential for maintaining homeostasis and promoting individual growth. In dogs, alterations in sleep patterns associated with age and dog's correlation with temperament factors, such as nervousness, have been reported, and there is an increasing demand for precise monitoring of sleep and physical activity in dogs. The present study aims to develop an analysis method for measuring sleep-wake patterns and physical activity in dogs by utilizing an accelerometer and a smartphone. By analyzing time series data collected from the accelerometer attached to the dog's collar, a comprehensive sleep and activity analysis model was constructed. This model classified the activity level into seven classes and effectively highlighted the variations in sleep-activity patterns. Two classes with lower activity levels were considered as sleep, while other five levels were regarded as wake based on the rate of occurrence. This protocol of data acquisition and analysis provides a methodology that enables accurate and extended evaluation of both sleep and physical activity in dogs.

Predictive Modeling for Hospital Readmissions for Patients With Heart Disease: An Updated Review From 2012–2023
Wei Zhang, Weihan Cheng, Koichi Fujiwara, Richard Evans, Chengyan Zhu
IEEE Journal of Biomedical and Health Informatics, 2024年04月, ［査読有り］
英語, 研究論文（学術雑誌）

Frustration control during driving using auditory false heart rate feedback
Koshi Ota, Koichi Fujiwara, Toshihiro Hiraoka
Transportation Research Part F: Traffic Psychology and Behaviour, 101, 375, 386, Elsevier BV, 2024年02月, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）

Association between postinduction hypotension and postoperative mortality: a single-centre retrospective cohort study
Nakanishi, T., Tsuji, T., Sento, Y., Hashimoto, H., Fujiwara, K., Sobue, K.
Canadian Journal of Anesthesia, 71, 3, 2024年, ［査読有り］
英語, 研究論文（学術雑誌）

Heat illness detection with heart rate variability analysis and anomaly detection algorithm
Koichi Fujiwara, Koshi Ota, Shota Saeda, Toshitaka Yamakawa, Takatomi Kubo, Aozora Yamamoto, Yuki Maruno, Manabu Kano
Biomedical Signal Processing and Control, 87, 105520, 105520, Elsevier BV, 2024年01月, ［査読有り］, ［筆頭著者, 責任著者］
英語, 研究論文（学術雑誌）, 13226379

Association entre hypotension post-induction et mortalité postopératoire : une étude de cohorte rétrospective monocentrique
Toshiyuki Nakanishi, Tatsuya Tsuji, Yoshiki Sento, Hiroya Hashimoto, Koichi Fujiwara, Kazuya Sobue
Canadian Journal of Anesthesia/Journal canadien d'anesthésie, Springer Science and Business Media LLC, 2023年11月21日, ［査読有り］
英語, 研究論文（学術雑誌）

Prediction Model of Postoperative Pain Exacerbation Using a Wearable Electrocardiogram Sensor
Toshiyuki Nakanishi, Koichi Fujiwara, Kazuya Sobue
2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), IEEE, 2023年10月31日
研究論文（国際会議プロシーディングス）

FexSplice: A LightGBM-Based Model for Predicting the Splicing Effect of a Single Nucleotide Variant Affecting the First Nucleotide G of an Exon
Atefeh Joudaki, Jun-ichi Takeda, Akio Masuda, Rikumo Ode, Koichi Fujiwara, Kinji Ohno
Genes, 14, 9, 1765, 1765, MDPI AG, 2023年09月06日, ［査読有り］
研究論文（学術雑誌）, Single nucleotide variants (SNVs) affecting the first nucleotide G of an exon (Fex-SNVs) identified in various diseases are mostly recognized as missense or nonsense variants. Their effect on pre-mRNA splicing has been seldom analyzed, and no curated database is available. We previously reported that Fex-SNVs affect splicing when the length of the polypyrimidine tract is short or degenerate. However, we cannot readily predict the splicing effects of Fex-SNVs. We here scrutinized the available literature and identified 106 splicing-affecting Fex-SNVs based on experimental evidence. We similarly identified 106 neutral Fex-SNVs in the dbSNP database with a global minor allele frequency (MAF) of more than 0.01 and less than 0.50. We extracted 115 features representing the strength of splicing cis-elements and developed machine-learning models with support vector machine, random forest, and gradient boosting to discriminate splicing-affecting and neutral Fex-SNVs. Gradient boosting-based LightGBM outperformed the other two models, and the length and nucleotide compositions of the polypyrimidine tract played critical roles in the discrimination. Recursive feature elimination showed that the LightGBM model using 15 features achieved the best performance with an accuracy of 0.80 ± 0.12 (mean and SD), a Matthews Correlation Coefficient (MCC) of 0.57 ± 0.15, an area under the curve of the receiver operating characteristics curve (AUROC) of 0.86 ± 0.08, and an area under the curve of the precision–recall curve (AUPRC) of 0.87 ± 0.09 using a 10-fold cross-validation. We developed a web service program, named FexSplice that accepts a genomic coordinate either on GRCh37/hg19 or GRCh38/hg38 and returns a predicted probability of aberrant splicing of A, C, and T variants.

医工連携によるRBD病態解明の取り組み 立ち上がる数分前に起立性低血圧を予測できるか?レム睡眠行動障害患者への心拍変動解析の応用例　　　　　　　　　　　　　　　
角 幸頼, 小枝 正汰, 藤原 幸一, 尾関 祐二, 角谷 寛
日本睡眠学会定期学術集会・日本時間生物学会学術大会合同大会プログラム・抄録集, 45回・30回, 141, 141, 日本睡眠学会・日本時間生物学会, 2023年09月
日本語

医工連携によるRBD病態解明の取り組み 心拍変動に着目したレム睡眠行動障害患者における起立性低血圧の有無を判定する機械学習モデル　　　　　　　　　　　　　　　
藤原 幸一, 小枝 正汰, 角 幸頼, 今井 眞, 角谷 寛
日本睡眠学会定期学術集会・日本時間生物学会学術大会合同大会プログラム・抄録集, 45回・30回, 141, 141, 日本睡眠学会・日本時間生物学会, 2023年09月
日本語

医工連携によるRBD病態解明の取り組み 立ち上がる数分前に起立性低血圧を予測できるか?レム睡眠行動障害患者への心拍変動解析の応用例　　　　　　　　　　　　　　　
角 幸頼, 小枝 正汰, 藤原 幸一, 尾関 祐二, 角谷 寛
日本睡眠学会定期学術集会・日本時間生物学会学術大会合同大会プログラム・抄録集, 45回・30回, 141, 141, 日本睡眠学会・日本時間生物学会, 2023年09月
日本語

医工連携によるRBD病態解明の取り組み 心拍変動に着目したレム睡眠行動障害患者における起立性低血圧の有無を判定する機械学習モデル　　　　　　　　　　　　　　　
藤原 幸一, 小枝 正汰, 角 幸頼, 今井 眞, 角谷 寛
日本睡眠学会定期学術集会・日本時間生物学会学術大会合同大会プログラム・抄録集, 45回・30回, 141, 141, 日本睡眠学会・日本時間生物学会, 2023年09月
日本語

Heat Illness Detection with Heart Rate Variability Analysis and Anomaly Detection Algorithm
K. Fujiwara, K. Ota, S. Saeda, T. Yamakawa, T. Kubo, A. Yamamoto, Y. Maruno, M. Kano
Biomedical Signal Processing and Control, 2023年09月, ［査読有り］, ［筆頭著者, 責任著者］
英語, 研究論文（学術雑誌）, 13226379

Association between post-induction hypotension and postoperative mortality: A single-center retrospective cohort study　　　　　　　　　　　　　　　
T. Nakanishi, T. Tsuji, Y. Sento, H. Hashimoto, K. Fujiwara, K. Sobue
Canadian Journal of Anesthesia, 2023年08月, ［査読有り］
英語, 研究論文（学術雑誌）

Driver Drowsiness Detection Using R-R Interval of Electrocardiogram and Self-Attention Autoencoder
Koichi Fujiwara, Hiroki Iwamoto, Kentaro Hori, Manabu Kano
IEEE Transactions on Intelligent Vehicles, 1, 10, Institute of Electrical and Electronics Engineers (IEEE), 2023年08月, ［査読有り］, ［筆頭著者, 責任著者］
英語, 研究論文（学術雑誌）

Learning curve of i-gel insertion in novices using a cumulative sum analysis
Toshiyuki Nakanishi, Seishi Sakamoto, Manabu Yoshimura, Koichi Fujiwara, Takashi Toriumi
Scientific Reports, 13, 1, 7121, Springer Science and Business Media LLC, 2023年05月02日, ［査読有り］
英語, 研究論文（学術雑誌）, Abstract

The i-gel, a popular second-generation supraglottic airway device, has been used in a variety of airway management situations, including as an alternative to tracheal intubation for general anesthesia, rescue in difficult airway settings, and out-of-hospital cardiac arrest resuscitation. We aimed to investigate the number of experiences needed to achieve a rapid, highly successful first attempt i-gel insertion in novices with a cumulative sum analysis. We also looked at how learning affected success rates, insertion time, and bleeding and reflex (limb movement, frowning face, or coughing) incidences. This prospective observational study included 15 novice residents from March 2017 to February 2018 in a tertiary teaching hospital. Finally, 13 residents with 35 [30–42] (median [interquartile range]) cases of i-gel insertion were analyzed. The cumulative sum analysis showed that 11 of 13 participants had an acceptable failure rate after 15 [8–20] cases. With increasing experience, success rate (P = 0.004), insertion time (P < 0.001), and incidence of bleeding (P = 0.006) all improved. However, the incidence of reflex did not change (P = 0.43). Based on our results, we suggest that 20 cases are preferable for novices to develop skills in using the i-gel in airway management.

Development of an epileptic seizure prediction algorithm using R–R intervals with self-attentive autoencoder
R. Ode, K. Fujiwara, M. Miyajima, T. Yamakawa, M. Kano, K. Jin, N. Nakasato, Y. Sawai, T. Hoshida, M. Iwasaki, Y. Murata, S. Watanabe, Y. Watanabe, Y. Suzuki, M. Inaji, N. Kunii, S. Oshino, H. M. Khoo, H. Kishima, T. Maehara
Artificial Life and Robotics, 28, 403, 409, Springer Science and Business Media LLC, 2023年05月, ［査読有り］, ［招待有り］, ［責任著者］
英語, 研究論文（学術雑誌）, Abstract

Epilepsy is a neurological disorder that may affect the autonomic nervous system (ANS) from 15 to 20 min before seizure onset, and disturbances of ANS affect R–R intervals (RRI) on an electrocardiogram (ECG). This study aims to develop a machine learning algorithm for predicting focal epileptic seizures by monitoring R–R interval (RRI) data in real time. The developed algorithm adopts a self-attentive autoencoder (SA-AE), which is a neural network for time-series data. The results of applying the developed seizure prediction algorithm to clinical data demonstrated that it functioned well in most patients; however, false positives (FPs) occurred in specific participants. In a future work, we will investigate the causes of FPs and optimize the developing seizure prediction algorithm to further improve performance using newly added clinical data., 31776990

Causal analysis of nitrogen oxides emissions process in coal-fired power plant with LiNGAM
Tatsuki Saito, Koichi Fujiwara
Frontiers in Analytical Science, 3, Frontiers Media SA, 2023年02月16日, ［査読有り］, ［招待有り］, ［責任著者］
英語, 研究論文（学術雑誌）, Coal has been an important energy source worldwide; however, it is the largest source of nitrogen oxide (NOx) emissions because the amount of nitrogen in coal is larger than that of other fossil fuels. Precise control of NOx emissions is required in operations of coal-fired power plants from the viewpoint of air pollution control. Although theoretical analyses of NOx generation from a coal-fired power plant have been conducted, it is difficult to precisely predict NOx generation in an actual plant. NOx generation is affected by various factors, such as furnace design and operating conditions, and there are complicated relationships among them. Thus, it is necessary to identify important operating factors that affect NOx generation in actual coal-fired power plants. A linear non-Gaussian acyclic model (LiNGAM) is an exploratory causal analysis method that identifies a causal ordering of variables and their connection strengths without any prior knowledge of causal relationships among variables. In this study, we analyzed real operation data collected from a coal-fired power plant using LiNGAM to identify factors of NOx generation. The causal relationship between process variables and NOx generation was estimated by means of LiNGAM, and the connectional strengths of the variables on NOx generation were derived. The analysis results agreed with previous reports on NOx generation mechanisms, such as combustion air temperature, steam temperature on a specific side of the furnace, and air flow rate of forced draft fans. In addition, we found the steam flow rate and the furnace pressure as new candidate factors of NOx generation through causal analysis using LiNGAM, which heretofore has not been suggested. Our analysis result should contribute to reducing NOx emissions from coal-fired power plants in the future.

Editorial: Data science and digital service delivery in healthcare
Fujiwara, K.
Frontiers in Computer Science, 4, 2023年
研究論文（学術雑誌）

心拍変動解析とニューラルネットワークを用いた睡眠時無呼吸症候群スクリーニングAIの開発
角 幸頼, 藤原 幸一, 岩崎 絢子, 尾関 祐二, 角谷 寛
人工知能学会全国大会論文集, JSAI2023, 1L4OS18a04, 1L4OS18a04, 一般社団法人 人工知能学会, 2023年
日本語, 睡眠時無呼吸症候群 (sleep apnea syndrome: SAS) は、睡眠中の無呼吸または低呼吸など呼吸イベントにより、眠気や倦怠感が引き起こされる疾患である。SASは、冠動脈疾患（狭心症・心筋梗塞）や心房細動、脳卒中など危険因子である。SASの有病率は成人の2-7% とされるが、自覚症状の乏しい患者はさらに多いと見積もられている。 SAS は一般的には、睡眠専門機関における検査(睡眠ポリグラフ, PSG)で診断される。PSG は限られた施設でしか行われておらず、本疾患のスクリーニング法の開発が必要であった。 そこで、呼吸イベントに関連した心拍変動に着目し、心拍変動解析とニューラルネットワークを用いた睡眠時無呼吸症候群スクリーニング手法を開発した。 大規模な PSG データセット (N = 938) を対象に、心拍データに対して長期・短期記憶を用い、SAS の検出を試みた。 重症 SAS の検出は、area under the curve (AUC) 0.92、感度 0.80、特異度 0.84 で検出できた。 今後、SAS 患者の早期発見のため、ウェアラブルデバイスを用いた簡易なスクリーニング手法の開発を目指している。

ウェアラブル心電計と経静脈的患者自己調節鎮痛法を用いた手術後の痛み増強を予測するAIの開発
中西 俊之, 藤原 幸一, 仙頭 佳起, 祖父江 和哉
人工知能学会全国大会論文集, JSAI2023, 1L5OS18b02, 1L5OS18b02, 一般社団法人 人工知能学会, 2023年
日本語, 痛みは主観的な感覚であるため，自己評価スケールで評価されてきた．しかし，自己評価スケールは時間的に連続評価ができず，意識レベル低下時や小児では実施が難しい．そのため，熱や電気刺激に対する生体信号の変化を痛みの正解データとして用いることで，痛みの客観化が試みられてきた．しかし，実験環境での解析結果をそのまま実際の患者に適応できるかどうかは明らかでない．我々は，患者自身が痛みの増強時に鎮痛剤を投与する経静脈的患者自己調節鎮痛法（IV-PCA）の使用記録から痛みの経時変化を推定できると考えた．本研究の目的は，ウェアラブル心電計とIV-PCAを用い，生体信号と機械学習により術後の痛みを連続的に評価し，その増強を予測することである．時系列性を考慮した異常検知モデルである自己注意機構付きオートエンコーダ（SA-AE）を採用し，心拍変動指標を入力特徴量に用いて痛み増強を予測するAIを構築した．IV-PCAの使用を痛みの増強と定義し，8人の術後患者において痛み増強の15分前にTPR 54%，FPR 1.76 回/hの性能で予測できた．今後，データを蓄積してモデルの性能を改善する．

Nearest Neighbor Search-Based Modification of RRI Data with Premature Atrial Contraction and Premature Ventricular Contraction
Sifeng Chen, Shota Kato, Koichi Fujiwara, Manabu Kano
2023 SICE INTERNATIONAL SYMPOSIUM ON CONTROL SYSTEMS, SICE ISCS, 53, 57, IEEE, 2023年
英語, 研究論文（国際会議プロシーディングス）, Heart rate variability (HRV) analysis plays an essential role in healthcare. HRV features cannot be extracted accurately from the R-R interval (RRI) when RRI data contains artifacts. Previous research for modifying RRI data with artifacts considered premature atrial contraction (PAC) and premature ventricular contraction (PVC), which are the most common types of extrasystoles occurring every day in healthy persons. This research proposed three new RRI modification algorithms for PAC and PVC using nearest neighbor search (NNS) algorithms: k-nearest neighbors (KNN), clustering-KNN (CKNN), and approximate nearest neighbors (ANN). The present work demonstrated that the ANN-based RRI modification (ANN-RM) algorithm achieved lower root mean squared errors (RMSEs) than the CKNN-based RRI modification algorithm and the highest computational speed. The RMSEs of ANN-RM for PAC and PVC were 23.0 ms and 26.2 ms, respectively.

Interactive system for optimal position selection of a patch-type R–R interval telemeter
Noguchi, A., Takano, T., Fujiwara, K., Miyajima, M., Yamakawa, T.
Artificial Life and Robotics, 28, 1, Springer Science and Business Media LLC, 2023年, ［査読有り］, ［招待有り］
英語, 研究論文（学術雑誌）

Auditory Feedback of False Heart Rate for Video Game Experience Improvement
Sayaka Ogawa, Koichi Fujiwara, Manabu Kano
IEEE Transactions on Affective Computing, 14, 1, 487, 497, Institute of Electrical and Electronics Engineers (IEEE), 2023年01月01日, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）

Causal Plot: Causal-Based Fault Diagnosis Method Based on Causal Analysis
Uchida, Y., Fujiwara, K., Saito, T., Osaka, T.
Processes, 10, 11, 2269, 2022年11月03日, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）

Effects of pleasant sound on overnight sleep condition: A crossover randomized study
Shota Saeda, Koichi Fujiwara, Takafumi Kinoshita, Yukiyoshi Sumi, Masahiro Matsuo, Kiyoshi Yamaki, Takahiro Kawashima, Hiroshi Kadotani
Frontiers in Sleep, 1, Frontiers Media SA, 2022年10月18日, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）, It is desirable to improve sleep quality since poor sleep results in decreases in work productivity and increases in risks of lifestyle-related diseases. Sleep spindles in sleep EEG are waveforms that characterize non-REM sleep Stage 2 (Stage N2). Music therapy has been adopted as a non-pharmacological therapy for sleep quality improvement; however, few studies mention the relationship between music during sleep and spindles. We conducted a crossover randomized study to investigate music's effects on spindles and sleep parameters. Polysomnography (PSG) was performed on 12 adult males with sleep difficulties over three nights, during which they were exposed to three different acoustic environments–silent, white noise, and pleasant sounds–throughout the night, in a crossover randomized setting. Half of the participants with large WASO were defined as the sleep maintenance difficulty group. We investigated whether pleasant sounds shortened sleep onset latency (SOL) and increased the number of spindles (SN) and spindle density (SD) compared to white noise, using silent as the reference. The spindles were detected using the previously reported automatic spindle detection algorithm. After one patient was excluded due to data corruption, a total of 11 participants, including the sleep maintenance difficulty group (n = 5), were analyzed. For all participants, SOL was not significantly shorter with pleasant sound than with white noise (p = 0.683); for the sleep maintenance difficulty group, SOL tended to be shorter with pleasant sound than with white noise (p = 0.060). Compared to white noise, the SN increased in pleasant sound for 7 of 11 (4 of 5 in the sleep maintenance difficulty group), and SD increased for 5 of 11 (3 of 5 in the sleep maintenance difficulty group). The results suggest that all-night background sound exposure may affect SN and SD. Future research should investigate whether background sound exposure reduces sleep-related distress, achieves sound sleep, or improves daytime psychomotor function., 12628475

Sleep-EEG-based Parameters for Discriminating Fatigue and Sleepiness
Koichi Fujiwara, Yuki Goto, Yukiyoshi Sumi, Manabu Kano, Hiroshi Kadotani
Frontiers in Sleep, 1, 975415, 975415, 2022年10月10日, ［査読有り］, ［筆頭著者, 責任著者］
英語, 研究論文（学術雑誌）

Wearable sensor device-based detection of decreased heart rate variability in Parkinson's disease.
Masashi Suzuki, Tomohiko Nakamura, Masaaki Hirayama, Masamichi Ueda, Mai Hatanaka, Yumiko Harada, Masahiro Nakatochi, Daisuke Nakatsubo, Satoshi Maesawa, Ryuta Saito, Koichi Fujiwara, Masahisa Katsuno
Journal of neural transmission (Vienna, Austria : 1996), 129, 10, 1299, 1306, 2022年10月, ［国際誌］
英語, 研究論文（学術雑誌）, The evidence that heart rate variability (HRV) decreases during early Parkinson's disease (PD) largely depends on electrocardiogram data. In this study, we examined HRV in PD using wearable sensors and assessed various evaluation methods for detecting disease-related alterations. We evaluated 27 patients with PD and 23 disease controls. The wearable sensors POLAR V800 HR and POLAR H10 were used for the HRV measurements. The participants wore the two sensors for approximately 24 h, and long-term HRV data were acquired. We analyzed the standard deviation of normal R-R intervals (SDNN) and coefficient of variation of R-R intervals (CVRR) for every 100 consecutive beats. Focusing on the fluctuation of SDNN and CVRR, we extracted the minimum, first decile, first quartile, and median values of SDNN and CVRR. The area under the receiver operating characteristic curve (AUC) for each HRV parameter was calculated to differentiate PD from the disease controls. The minimum values of SDNN and CVRR had the highest AUC (SDNN: AUC 0.90, 95% confidence interval [CI] 0.78-0.96; CVRR: AUC 0.90, CI 0.76-0.96) among the evaluation methods tested. The minimum values of SDNN and CVRR were significantly decreased in PD (SDNN: 9.5 ± 4.0 ms vs. 4.4 ± 2.0 ms, p < 0.0001; CVRR: 1.15 ± 0.33% vs. 0.65 ± 0.24%, p < 0.0001). We detected decreased HRV in PD using wearable sensors. Analyzing the minimum values of the HRV parameter in long-term recordings appears to be appropriate for detecting the decrease in HRV in PD.

麻酔・集中治療領域における医学と工学の異分野融合研究の経験　　　　　　　　　　　　　　　
中西 俊之, 祖父江 和哉, 藤原 幸一
麻酔科学サマーセミナー, 18回, 44, 44, 麻酔科学サマーセミナー事務局, 2022年07月
日本語

R-R interval-based sleep apnea screening by a recurrent neural network in a large clinical polysomnography dataset
Ayako Iwasaki, Koichi Fujiwara, Chikao Nakayama, Yukiyoshi Sumi, Manabu Kano, Tetsuharu Nagamoto, Hiroshi Kadotani
Clinical Neurophysiology, 139, 80, 89, Elsevier BV, 2022年04月, ［責任著者］
研究論文（学術雑誌）

Medical checkup data analysis method based on LiNGAM and its application to nonalcoholic fatty liver disease
Tsuyoshi Uchida, Koichi Fujiwara, Kenichi Nishioji, Masao Kobayashi, Manabu Kano, Yuya Seko, Kanji Yamaguchi, Yoshito Itoh, Hiroshi Kadotani
Artificial Intelligence in Medicine, 128, 102310, 102310, Elsevier BV, 2022年04月, ［責任著者］, ［国際誌］
英語, 研究論文（学術雑誌）, Although medical checkup data would be useful for identifying unknown factors of disease progression, a causal relationship between checkup items should be taken into account for precise analysis. Missing values in medical checkup data must be appropriately imputed because checkup items vary from person to person, and items that have not been tested include missing values. In addition, the patients with target diseases or disorders are small in comparison with the total number of persons recorded in the data, which means medical checkup data is an imbalanced data analysis. We propose a new method for analyzing the causal relationship in medical checkup data to discover disease progression factors based on a linear non-Gaussian acyclic model (LiNGAM), a machine learning technique for causal inference. In the proposed method, specific regression coefficients calculated through LiNGAM were compared to estimate the causal strength of the checkup items on disease progression, which is referred to as LiNGAM-beta. We also propose an analysis framework consisting of LiNGAM-beta, collaborative filtering (CF), and a sampling approach for causal inference of medical checkup data. CF and the sampling approach are useful for missing value imputation and balancing of the data distribution. We applied the proposed analysis framework to medical checkup data for identifying factors of Nonalcoholic fatty liver disease (NAFLD) development. The checkup items related to metabolic syndrome and age showed high causal effects on NAFLD severity. The level of blood urea nitrogen (BUN) would have a negative effect on NAFLD severity. Snoring frequency, which is associated with obstructive sleep apnea, affected NAFLD severity, particularly in the male group. Sleep duration also affected NAFLD severity in persons over fifty years old. These analysis results are consistent with previous reports about the causes of NAFLD; for example, NAFLD and metabolic syndrome are mutual and bi-directionally related, and BUN has a negative effect on NAFLD progression. Thus, our analysis result is plausible. The proposed analysis framework including LiNGAM-beta can be applied to various medical checkup data and will contribute to discovering unknown disease factors.

Prediction of GABA receptor antagonist-induced convulsion in cynomolgus monkeys by combining machine learning and heart rate variability analysis
Nagata, S., Fujiwara, K., Kuga, K., Ozaki, H.
Journal of Pharmacological and Toxicological Methods, 112, 107127, 2021年10月, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）

Sympathetic hyperactivity, hypertension, and tachycardia induced by stimulation of the ponto-medullary junction in humans.
Tadashi Hamasaki, Toshitaka Yamakawa, Koichi Fujiwara, Haruki Harashima, Kota Nakamura, Yoshihiro Ikuta, Tatsuo Yamamoto, Yu Hasegawa, Tatsuya Takezaki, Akitake Mukasa
Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology, 132, 6, 1264, 1273, 2021年06月, ［査読有り］, ［国際誌］
英語, 研究論文（学術雑誌）, OBJECTIVE: The purpose of this study is to investigate changes in autonomic activities and systemic circulation generated by surgical manipulation or electrical stimulation to the human brain stem. METHODS: We constructed a system that simultaneously recorded microsurgical field videos and heart rate variability (HRV) that represent autonomic activities. In 20 brain stem surgeries recorded, HRV features and sites of surgical manipulation were analyzed in 19 hypertensive epochs, defined as the periods with transient increases in the blood pressure. We analyzed the period during electrical stimulation to the ponto-medullary junction, performed for the purpose of monitoring a cranial nerve function. RESULTS: In the hypertensive epoch, HRV analysis showed that sympathetic activity predominated over the parasympathetic activity. The hypertensive epoch was more associated with surgical manipulation of the area in the caudal pons or the rostral medulla oblongata compared to controls. During the period of electrical stimulation, there were significant increases in blood pressures and heart rates, accompanied by sympathetic overdrive. CONCLUSIONS: Our results provide physiological evidence that there is an important autonomic center located adjacent to the ponto-medullary junction. SIGNIFICANCE: A large study would reveal a candidate target of neuromodulation for disorders with autonomic imbalances such as drug-resistant hypertension.

Development of Game-Like System Using Active Behavior Input for Wakefulness-Keeping Support in Driving
Tatsuro Ibe, Koichi Fujiwara, Toshihiro Hiraoka, Erika Abe, Toshitaka Yamakawa
IEEE Transactions on Intelligent Vehicles, 6, 2, 323, 332, Institute of Electrical and Electronics Engineers (IEEE), 2021年06月, ［責任著者］
研究論文（学術雑誌）

Autoencoder-Based Extrasystole Detection and Modification of RRI Data for Precise Heart Rate Variability Analysis
Koichi Fujiwara, Shota Miyatani, Asuka Goda, Miho Miyajima, Tetsuo Sasano, Manabu Kano
Sensors, 21, 9, 3235, 3235, MDPI AG, 2021年05月07日, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）, Heart rate variability, which is the fluctuation of the R-R interval (RRI) in electrocardiograms (ECG), has been widely adopted for autonomous evaluation. Since the HRV features that are extracted from RRI data easily fluctuate when arrhythmia occurs, RRI data with arrhythmia need to be modified appropriately before HRV analysis. In this study, we consider two types of extrasystoles—premature ventricular contraction (PVC) and premature atrial contraction (PAC)—which are types of extrasystoles that occur every day, even in healthy persons who have no cardiovascular diseases. A unified framework for ectopic RRI detection and a modification algorithm that utilizes an autoencoder (AE) type of neural network is proposed. The proposed framework consists of extrasystole occurrence detection from the RRI data and modification, whose targets are PVC and PAC. The RRI data are monitored by means of the AE in real time in the detection phase, and a denoising autoencoder (DAE) modifies the ectopic RRI caused by the detected extrasystole. These are referred to as AE-based extrasystole detection (AED) and DAE-based extrasystole modification (DAEM), respectively. The proposed framework was applied to real RRI data with PVC and PAC. The result showed that AED achieved a sensitivity of 93% and a false positive rate of 0.08 times per hour. The root mean squared error of the modified RRI decreased to 31% in PVC and 73% in PAC from the original RRI data by DAEM. In addition, the proposed framework was validated through application to a clinical epileptic seizure problem, which showed that it correctly suppressed the false positives caused by PVC. Thus, the proposed framework can contribute to realizing accurate HRV-based health monitoring and medical sensing systems., 31776990

Sympathetic hyperactivity, hypertension, and tachycardia induced by stimulation of the ponto-medullary junction in humans　　　　　　　　　　　　　　　
T. Hamasaki, T. Yamakawa, K. Fujiwara, H. Harashima, K. Nakamura, Y. Ikuta, T. Yamamoto, Y. Hasegawa, T. Takezaki, A. Mukasa
Clinical Neurophysiology, 2021年03月, ［査読有り］
英語, 研究論文（学術雑誌）

Work habit-related sleep debt; insights from factor identification analysis of actigraphy data
Yuki Goto, Koichi Fujiwara, Yukiyoshi Sumi, Masahiro Matsuo, Manabu Kano, Hiroshi Kadotani
Frontiers in Public Health, 10, 630640, 630640, 2021年02月, ［査読有り］, ［招待有り］, ［責任著者］, ［国際誌］
英語, 研究論文（学術雑誌）, The present study investigates the factors of "Weekday sleep debt (WSD)" by comparing activity data collected from persons with and without WSD. Since it has been reported that the amount of sleep debt as well the difference between the social clock and the biological clock is associated with WSD, specifying the factors of WSD other than chronotype may contribute to sleep debt prevention. We recruited 324 healthy male employees working at the same company and collected their one-week wrist actigraphy data and answers to questionnaires. Because 106 participants were excluded due to measurement failure of the actigraphy data, the remaining 218 participants were included in the analysis. All participants were classified into WSD or non-WSD groups, in which persons had WDS if the difference between their weekend sleep duration and the mean weekday sleep duration was more than 120 min. We evaluated multiple measurements derived from the collected actigraphy data and trained a classifier that predicts the presence of WSD using these measurements. A support vector machine (SVM) was adopted as the classifier. In addition, to evaluate the contribution of each indicator to WSD, permutation feature importance was calculated based on the trained classifier. Our analysis results showed significant importance of the following three out of the tested 32 factors: 1) WSD was significantly related to persons with evening tendency. 2) Daily activity rhythms and sleep were less stable in the WSD group than in the non-WSD group. 3) A specific day of the week had the highest importance in our data, suggesting that work habit contributes to WSD. These findings indicate some WSD factors: evening chronotype, instability of the daily activity rhythm, and differences in work habits on the specific day of the week. Thus, it is necessary to evaluate the rhythms of diurnal activities as well as sleep conditions to identify the WSD factors. In particular, the diurnal activity rhythm influences WSD. It is suggested that proper management of activity rhythm may contribute to the prevention of sleep debt., 12628475

Screening of sleep apnea based on heart rate variability and long short-term memory
Ayako Iwasaki, Chikao Nakayama, Koichi Fujiwara, Yukiyoshi Sumi, Masahiro Matsuo, Manabu Kano, Hiroshi Kadotani
Sleep and Breathing, Springer Science and Business Media LLC, 2021年01月10日, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）,

Sleep apnea syndrome (SAS) is a prevalent sleep disorder in which apnea and hypopnea occur frequently during sleep and result in increase of the risk of lifestyle-related disease development as well as daytime sleepiness. Although SAS is a common sleep disorder, most patients remain undiagnosed because the gold standard test polysomnography (PSG), is high-cost and unavailable in many hospitals. Thus, an SAS screening system that can be used easily at home is needed.




Apnea during sleep affects changes in the autonomic nervous function, which causes fluctuation of the heart rate. In this study, we propose a new SAS screening method that combines heart rate measurement and long short-term memory (LSTM) which is a type of recurrent neural network (RNN). We analyzed the data of intervals between adjacent R waves (R-R interval; RRI) on the electrocardiogram (ECG) records, and used an LSTM model whose inputs are the RRI data is trained to discriminate the respiratory condition during sleep.




The application of the proposed method to clinical data showed that it distinguished between patients with moderate-to-severe SAS with a sensitivity of 100% and specificity of 100%, results which are superior to any other existing SAS screening methods.




Since the RRI data can be easily measured by means of wearable heart rate sensors, our method may prove to be useful as an SAS screening system at home.


, 12628475

スポーツ中の熱中症予防を目的とした飲水の心拍変動への影響評価
山本 青空, 久保 孝富, 藤原 幸一, 山川 俊貴, 奥村 七彩, 丸野 由希
生体医工学, Annual59, Abstract, 381, 381, 公益社団法人 日本生体医工学会, 2021年
日本語, スポーツ中の熱中症予防の為、暑さ指数（WBGT）に基づいて休息、水分補給を行うよう運動指針が示されている。しかし、熱中症の発症要因は環境面に限らず個人の身体的な要因も関連しており、WBGTのみの考慮では十分でない可能性もあると考えられる。運動指針が提案されて以降も熱中症患者数は減少傾向を示していない。個人の生理的な要因を考慮した熱中症予防の確立に向け、本研究では水分補給と心拍変動（HRV）の関係性に着目し、スポーツ活動中の飲水がHRVに与える影響の解明に向けた計測実験を行った。マラソンクラブチームに所属する20~70代の男女40名を被験者とし、ウェアラブル心拍測定デバイスを用いて、ランニング時の心拍データ（RRI）および加速度を計測した。被験者は心拍測定デバイスと連動しているスマートフォンアプリを用いて休憩や水分補給、体調変化等の申告を行った。RRIは飲水前後で値の変化は見られなかったが、調査した4つのHRV指標（NN50、pNN50、HF、LF/HF）全てで変化が見られた。HRV指標のうち副交感神経関連の指標（NN50、pNN50、HF）では飲水後1~5分後に値が増加し、20分後まで影響が持続している可能性があることが示された。交感神経系の指標であるLF/HFは飲水時の前後のみ値が増加しており、飲水の1分後には影響がほとんど消失していると考えられた。本研究の結果、飲水の交感神経系への効果は速やかに現れ、副交感神経への影響は持続する可能性が示唆された。

Preliminary Study Using Autoencoder for Early Detection of Heat Illness from Heart Rate Variability Obtained with Wearable Device.
Nao Inatsu, Aoi Noguchi, Koshi Ota, Koichi Fujiwara, Takatomi Kubo, Toshitaka Yamakawa
APSIPA ASC, 1348, 1352, 2021年
研究論文（国際会議プロシーディングス）

Resting Heart Rate Variability Is Associated With Subsequent Orthostatic Hypotension: Comparison Between Healthy Older People and Patients With Rapid Eye Movement Sleep Behavior Disorder
Y. Sumi, C. Nakayama, H. Kadotani, M. Matsuo, Y. Ozeki, T. Kinoshita, Y. Goto, M. Kano, T. Yamakawa, M. Ohira, K. Ogawa, K. Fujiwara
Frontiers in Neurology, 11, 567984, Frontiers Media SA, 2020年11月, ［査読有り］, ［最終著者］
英語, 研究論文（学術雑誌）, Background: Orthostatic hypotension (OH) caused by autonomic dysfunction is a common symptom in older people and patients with idiopathic rapid eye movement sleep behavior disorder (iRBD). The orthostatic challenge test is a standard autonomic function test that measures a decrease of blood pressure during a postural change from supine to standing positions. Although previous studies have reported that changes in heart rate variability (HRV) are associated with autonomic dysfunction, no study has investigated the relationship between HRV before standing and the occurrence of OH in an orthostatic challenge test. This study aims to examine the connection between HRV in the supine position and the occurrence of OH in an orthostatic challenge test.

Methods: We measured the electrocardiograms of patients with iRBD and healthy older people during an orthostatic challenge test, in which the supine and standing positions were held for 15 min, respectively. The subjects were divided into three groups: healthy controls (HC), OH-negative iRBD [OH (–) iRBD], and OH-positive iRBD [OH (+) iRBD]. HRV measured in the supine position during the test were calculated by time-domain analysis and Poincaré plots to evaluate the autonomic dysfunction.

Results: Forty-two HC, 12 OH (–) iRBD, and nine OH (+) iRBD subjects were included. HRV indices in the OH (–) and the OH (+) iRBD groups were significantly smaller than those in the HC group. The multivariate logistic regression analysis for OH identification for the iRBD groups showed the model whose inputs were the HRV indices, i.e., standard deviation 2 (SD2) and the percentage of adjacent intervals that varied by more than 50 ms (pNN50), had a receiver operating characteristic curve with area under the curve of 0.840, the sensitivity to OH (+) of 1.000, and the specificity to OH (–) of 0.583 (p = 0.023).

Conclusions: This study showed the possibility that short-term HRV indices in the supine position would predict subsequent OH in iRBD patients. Our results are of clinical importance in terms of showing the possibility that OH can be predicted using only HRV in the supine position without an orthostatic challenge test, which would improve the efficiency and safety of testing., 12628475

Optimal Design of Neuroprotective Focal Brain Cooling Device Using Surrogate Model Approach
Takuto Abe, Koichi Fujiwara, Takao Inoue, Takatomi Kubo, Toshitaka Yamakawa, Sadahiro Nomura, Michiyasu Suzuki, Manabu Kano
IEEE Transactions on Medical Robotics and Bionics, 2, 4, 681, 691, Institute of Electrical and Electronics Engineers (IEEE), 2020年11月, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）

Evaluating Mental State of Drivers in Automated Driving Using Heart Rate Variability towards Feasible Request-to-Intervene
Felan Carlo Garcia, Takatomi Kubo, Chao-Ling Chang, Masafumi Hisada, Takashi Bando, Midori Kato, Masataka Mori, Kazuhito Takenaka, Toshitaka Yamakawa, Koichi Fujiwara, Kazushi Ikeda
Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, 2020-, 3454, 3459, Institute of Electrical and Electronics Engineers Inc., 2020年10月11日
英語, 研究論文（国際会議プロシーディングス）, As Intelligent Transport Systems (ITS) advances, more and more people will have the opportunities to drive vehicles with autonomous capabilities. This rise in number of semi-autonomous vehicles also gives rise to several challenges with regards on how human factors come into play in interacting with the vehicle's Automated Driving System (ADS). One important interaction of an ADS with Level 3 Conditional Automated Driving capabilities is Request-to-Intervene (RTI), which alerts drivers to takeover the vehicle during an automated driving session, however, the driver is not necessarily ready to receive the authority. To see whether an ADS can detect the readiness of the user for RTI, in this preliminary study we evaluated the mental states of ADS users in naturalistic driving conditions by comparing them with those of drivers and passengers. The mental states were evaluated by measuring their heart rate and by calculating specific features of Heart Rate Variability (HRV), specifically NN50 and pNN50 indices, during driving events (turning, lane changing, and stopping) and no-events. The results showed the NN50 and pNN50 values of manual driving were significantly different from those of ADS driving and passenger, suggesting that ADS driving has a higher level of relaxed state. In addition, events such as lane-changing in the ADS driving did not induce significantly different NN50 and pNN50 from nonevent situation, which may imply the participants did not pay attention to such events.

Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability
Toshitaka Yamakawa, Miho Miyajima, Koichi Fujiwara, Manabu Kano, Yoko Suzuki, Yutaka Watanabe, Satsuki Watanabe, Tohru Hoshida, Motoki Inaji, Taketoshi Maehara
Sensors, 20, 14, 3987, 3987, MDPI AG, 2020年07月17日, ［査読有り］
英語, 研究論文（学術雑誌）, A warning prior to seizure onset can help improve the quality of life for epilepsy patients. The feasibility of a wearable system for predicting epileptic seizures using anomaly detection based on machine learning is evaluated. An original telemeter is developed for continuous measurement of R-R intervals derived from an electrocardiogram. A bespoke smartphone app calculates the indices of heart rate variability in real time from the R-R intervals, and the indices are monitored using multivariate statistical process control by the smartphone app. The proposed system was evaluated on seven epilepsy patients. The accuracy and reliability of the R-R interval measurement, which was examined in comparison with the reference electrocardiogram, showed sufficient performance for heart rate variability analysis. The results obtained using the proposed system were compared with those obtained using the existing video and electroencephalogram assessments; it was noted that the proposed method has a sensitivity of 85.7% in detecting heart rate variability change prior to seizures. The false positive rate of 0.62 times/h was not significantly different from the healthy controls. The prediction performance and practical advantages of portability and real-time operation are demonstrated in this study.

Over- and Under-sampling Approach for Extremely Imbalanced and Small Minority Data Problem in Health Record Analysis
Koichi Fujiwara, Yukun Huang, Kentaro Hori, Kenichi Nishioji, Masao Kobayashi, Mai Kamaguchi, Manabu Kano
Frontiers in Public Health, 8, 178, 2020年05月19日, ［査読有り］, ［招待有り］, ［筆頭著者, 責任著者］
英語, 研究論文（学術雑誌）, © Copyright © 2020 Fujiwara, Huang, Hori, Nishioji, Kobayashi, Kamaguchi and Kano. A considerable amount of health record (HR) data has been stored due to recent advances in the digitalization of medical systems. However, it is not always easy to analyze HR data, particularly when the number of persons with a target disease is too small in comparison with the population. This situation is called the imbalanced data problem. Over-sampling and under-sampling are two approaches for redressing an imbalance between minority and majority examples, which can be combined into ensemble algorithms. However, these approaches do not function when the absolute number of minority examples is small, which is called the extremely imbalanced and small minority (EISM) data problem. The present work proposes a new algorithm called boosting combined with heuristic under-sampling and distribution-based sampling (HUSDOS-Boost) to solve the EISM data problem. To make an artificially balanced dataset from the original imbalanced datasets, HUSDOS-Boost uses both under-sampling and over-sampling to eliminate redundant majority examples based on prior boosting results and to generate artificial minority examples by following the minority class distribution. The performance and characteristics of HUSDOS-Boost were evaluated through application to eight imbalanced datasets. In addition, the algorithm was applied to original clinical HR data to detect patients with stomach cancer. These results showed that HUSDOS-Boost outperformed current imbalanced data handling methods, particularly when the data are EISM. Thus, the proposed HUSDOS-Boost is a useful methodology of HR data analysis.

Regression and independence based variable importance measure
Xinmin Zhang, Takuya Wada, Koichi Fujiwara, Manabu Kano
Computers and Chemical Engineering, 135, 6, 106757, 2020年04月, ［査読有り］, ［国際誌］
英語, 研究論文（学術雑誌）, © 2020 Elsevier Ltd Evaluating the importance of input (predictor) variables is of interest in many applications of statistical models. However, nonlinearity and correlation among variables make it difficult to measure variable importance accurately. In this work, a novel variable importance measure, called regression and independence based variable importance (RIVI), is proposed. RIVI is designed by integrating Gaussian process regression (GPR) and Hilbert-Schmidt independence criterion (HSIC) so that it is applicable to nonlinear systems. The results of two numerical examples demonstrate that RIVI is superior to several conventional measures including the Pearson correlation coefficient, PLS-β, PLS-VIP, Lasso, HSIC, and permutation importance with random forest in the variable identification accuracy.

Sleep Spindle Detection Using RUSBoost and Synchrosqueezed Wavelet Transform.
Takafumi Kinoshita, Koichi Fujiwara, Manabu Kano, Keiko Ogawa, Yukiyoshi Sumi, Masahiro Matsuo, Hiroshi Kadotani
IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society, 28, 2, 390, 398, 2020年02月, ［査読有り］, ［責任著者］, ［国際誌］
英語, 研究論文（学術雑誌）, Sleep spindles are important electroencephalographic (EEG) waveforms in sleep medicine; however, it is burdensome even for experts to detect spindles, so automatic spindle detection methodologies have been investigated. Conventional methods utilize waveforms template matching or machine learning for detecting spindles. In the former approach, it is necessary to tune thresholds for individual adaptation, while the latter approach has the problem of imbalanced data because the amount of sleep spindles is small compared with the entire EEG data. The present work proposes a sleep spindle detection method that combines wavelet synchrosqueezed transform (SST) and random under-sampling boosting (RUSBoost). SST is a time-frequency analysis method suitable for extracting features of spindle waveforms. RUSBoost is a framework for coping with the imbalanced data problem. The proposed SST-RUS can deal with the imbalanced data in spindle detection and does not require threshold tuning because RUSBoost uses majority voting of weak classifiers for discrimination. The performance of SST-RUS was validated using an open-access database called the Montreal archives of sleep studies cohort 1 (MASS-C1), which showed an F-measure of 0.70 with a sensitivity of 76.9% and a positive predictive value of 61.2%. The proposed method can reduce the burden of PSG scoring.

Application of wearable devices for the risk assessment and prevention of sudden unexpected death in epilepsy,てんかん突然死のリスク評価と予防におけるウェアラブルデバイスの有用性
Miyajima, M., Yamakawa, T., Fujiwara, K., Maehara, T.
Journal of the Japan Epilepsy Society, 38, 1, 2020年
研究論文（学術雑誌）

Trial of evaluation of emotions using heart rate variability in free moving dogs
MIKURU MURAYAMA, MIHO NAGASAWA, MAKI KATAYAMA, KAZUSHI IKEDA, TAKATOMI KUBO, TOSHITAKA YAMAKAWA, KOICHI FUJIWARA, TAKEFUMI KIKUSUI
Japanese Journal of Animal Psychology, 70, 1, 15, 18, Japanese Society of Animal Psychology, 2020年, ［査読有り］
研究論文（学術雑誌）

Obstructive sleep apnea screening by heart rate variability-based apnea/normal respiration discriminant model.
Chikao Nakayama, Koichi Fujiwara, Yukiyoshi Sumi, Masahiro Matsuo, Manabu Kano, Hiroshi Kadotani
Physiological measurement, 40, 12, 125001, 125001, 2019年12月20日, ［査読有り］, ［責任著者］, ［国際誌］
英語, 研究論文（学術雑誌）, OBJECTIVE: Obstructive sleep apnea (OSA) is a common sleep disorder; however, most patients are undiagnosed and untreated because it is difficult for patients themselves to notice OSA in daily living. Polysomnography (PSG), which is the gold standard test for sleep disorder diagnosis, cannot be performed in many hospitals. This fact motivates us to develop a simple system for screening OSA at home. APPROACH: The autonomic nervous system changes during apnea, and such changes affect heart rate variability (HRV). This work develops a new apnea screening method based on HRV analysis and machine learning technologies. An apnea/normal respiration (A/N) discriminant model is built for respiration condition estimation for every heart rate measurement, and an apnea/sleep ratio is introduced for final diagnosis. A random forest is adopted for the A/N discriminant model construction, which is trained with the PhysioNet apnea-ECG database. MAIN RESULTS: The screening performance of the proposed method was evaluated by applying it to clinical PSG data. Sensitivity and specificity achieved 76% and 92%, respectively, which are comparable to existing portable sleep monitoring devices used in sleep laboratories. SIGNIFICANCE: Since the proposed OSA screening method can be used more easily than existing devices, it will contribute to OSA treatment.

Views of patients with epilepsy on wearable seizure prediction system; impact of two different type of devices on sleep quality
M. Miyajima, T. Yamakawa, K. Fujiwara, T. Seki, T. ohno, M. Iimori, M. Inaji, H. Osoegawa, M. Kano, T. Maehara
Sleep Medicine, 64, Elsevier {BV}, 2019年12月
英語, 研究論文（学術雑誌）

医師患者関係のトラスト構築に向けたAI活用の可能性　　　　　　　　　　　　　　　
藤田 卓仙, 江間 有沙, 近藤 諭, 藤原 幸一, 中谷内 一也, 尾藤 誠司
医療情報学連合大会論文集, 39回, 126, 128, (一社)日本医療情報学会, 2019年11月
日本語

Development of a Sleep Apnea Detection Algorithm Using Long Short-Term Memory and Heart Rate Variability
Ayako Iwasaki, Chikao Nakayama, Koichi Fujiwara, Yukiyoshi Sumi, Masahiro Matsuo, Manabu Kano, Hiroshi Kadotani
Annu Int Conf IEEE Eng Med Biol Soc., 2019, 3964, 3967, 2019年07月, ［査読有り］, ［国際誌］
英語, 研究論文（学術雑誌）, Sleep apnea syndrome (SAS) is a prevalent disorder which causes daytime fatigue with the increased risk of lifestyle diseases. A large number of patients are undiagnosed and untreated partly because of the difficulty in performing its gold standard test, polysomnography (PSG). In this research, we propose a simple screening method utilizing heart rate variability (HRV) and long short-term memory (LSTM) which is a kind of neural network techniques. The result of applying this algorithm to clinical data demonstrates that it can discriminate between patients and healthy people with high sensitivity (100%) and specificity (100%).

Emotional Contagion From Humans to Dogs Is Facilitated by Duration of Ownership
M. Katayama, T. Kubo, T. Yamakawa, K. Fujiwara, K. Nomoto, K. Ikeda, K. Mogi, M. Nagasawa, T. Kikusui
Frontiers in Psychology, 10, 1678, 1678, 2019年07月, ［査読有り］, ［国際誌］
英語, 研究論文（学術雑誌）, Emotional contagion is a primitive form of empathy that does not need higher psychological functions. Recent studies reported that emotional contagion exists not only between humans but also among various animal species. The dog (Canis familiaris) is a unique animal and the oldest domesticated species. Dogs have coexisted with humans for more than 30,000 years and are woven into human society as partners bonding with humans. Dogs have acquired human-like communication skills and, likely as a result of the domestication process, the ability to read human emotions; therefore, it is feasible that there may be emotional contagion between human and dogs. However, the higher time-resolution of measurement of emotional contagion between them is yet to be conducted. We assessed the emotional reactions of dogs and humans by heart rate variability (HRV), which reflects emotion, under a psychological stress condition on the owners. The correlation coefficients of heart beat (R-R) intervals (RRI), the standard deviations of all RR intervals (SDNN), and the square root of the mean of the sum of the square of differences between adjacent RR intervals (RMSSD) between dogs and owners were positively correlated with the duration of dog ownership. Dogs' sex also influenced the correlation coefficients of the RRI, SDNN, and RMSSD in the control condition; female showed stronger values. These results suggest that emotional contagion from owner to dog can occur especially in females and the time sharing the same environment is the key factor in inducing the efficacy of emotional contagion.

Heart Rate Variability-Based Driver Drowsiness Detection and Its Validation With EEG.
Koichi Fujiwara, Erika Abe, Keisuke Kamata, Chikao Nakayama, Yoko Suzuki, Toshitaka Yamakawa, Toshihiro Hiraoka, Manabu Kano, Yukiyoshi Sumi, Fumi Masuda, Masahiro Matsuo, Hiroshi Kadotani
IEEE transactions on bio-medical engineering, 66, 6, 1769, 1778, 2019年06月, ［査読有り］, ［筆頭著者, 責任著者］, ［国際誌］
英語, 研究論文（学術雑誌）, OBJECTIVE: Driver drowsiness detection is a key technology that can prevent fatal car accidents caused by drowsy driving. The present work proposes a driver drowsiness detection algorithm based on heart rate variability (HRV) analysis and validates the proposed method by comparing with electroencephalography (EEG)-based sleep scoring. METHODS: Changes in sleep condition affect the autonomic nervous system and then HRV, which is defined as an RR interval (RRI) fluctuation on an electrocardiogram trace. Eight HRV features are monitored for detecting changes in HRV by using multivariate statistical process control, which is a well known anomaly detection method. RESULT: The performance of the proposed algorithm was evaluated through an experiment using a driving simulator. In this experiment, RRI data were measured from 34 participants during driving, and their sleep onsets were determined based on the EEG data by a sleep specialist. The validation result of the experimental data with the EEG data showed that drowsiness was detected in 12 out of 13 pre-N1 episodes prior to the sleep onsets, and the false positive rate was 1.7 times per hour. CONCLUSION: The present work also demonstrates the usefulness of the framework of HRV-based anomaly detection that was originally proposed for epileptic seizure prediction. SIGNIFICANCE: The proposed method can contribute to preventing accidents caused by drowsy driving.

Epileptic Seizure Suppression by Focal Brain Cooling with Recirculating Coolant Cooling System: Modeling and Simulation
Kei Hata, Koichi Fujiwara, Takao Inoue, Takuto Abe, Takatomi Kubo, Toshitaka Yamakawa, Sadahiro Nomura, Hirochika Imoto, Michiyasu Suzuki, Manabu Kano
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27, 2, 162, 171, 2019年02月, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）, © 2001-2011 IEEE. A focal brain cooling system for treatment of refractory epilepsy that is implantable and wearable may permit patients with this condition to lead normal daily lives. We have developed such a system for cooling of the epileptic focus by delivery of cold saline to a cooling device that is implanted cranially. The outflow is pumped for circulation and cooled by a Peltier device. Here, we describe the design of the system and evaluate its feasibility by simulation. Mathematical models were constructed based on equations of fluid dynamics and data from a cat model. Computational fluid dynamics simulations gave the following results: 1) a cooling device with a complex channel structure gives a more uniform temperature in the brain; 2) a cooling period of <10 min is required to reach an average temperature of 25.0°Cat 2 mm below the brain surface, which is the target temperature for seizure suppression. This time is short enough for cooling of the brain before seizure onset after seizure prediction by an intracranial electroencephalogram-based algorithm; and 3) battery charging would be required once every several days for most patients. These results suggest that the focal brain cooling system may be clinically applicable.

Missing RRI interpolation algorithm based on locally weighted partial least squares for precise heart rate variability analysis
Keisuke Kamata, Koichi Fujiwara, Takafumi Kinoshita, Manabu Kano
Sensors, 18, 11, 3870, 2018年11月10日, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）, © 2018 by the authors. Licensee MDPI, Basel, Switzerland. The R-R interval (RRI) fluctuation in electrocardiogram (ECG) is called heart rate variability (HRV), which reflects activities of the autonomic nervous system (ANS) and has been used for various health monitoring services. Accurate R wave detection is crucial for success in HRV-based health monitoring services; however, ECG artifacts often cause missing R waves and deteriorate the accuracy of HRV analysis. The present work proposes a new missing RRI interpolation technique based on Just-In-Time (JIT) modeling. In the JIT modeling framework, a local regression model is built by weighing samples stored in the database according to the distance from a query and output is estimated only when an estimate is requested. The proposed method builds a local model and estimates missing RRI only when an RRI detection error is detected. Locally weighted partial least squares (LWPLS) is adopted for local model construction. The proposed method is referred to as LWPLS-based RRI interpolation (LWPLS-RI). The performance of the proposed LWPLS-RI was evaluated through its application to RRI data with artificial missing RRIs. We used the MIT-BIH Normal Sinus Rhythm Database for nominal RRI dataset construction. Missing RRIs were artificially introduced and they were interpolated by the proposed LWPLS-RI. In addition, MEAN that replaces the missing RRI by a mean of the past RRI data was compared as a conventional method. The result showed that the proposed LWPLS-RI improved root mean squared error (RMSE) of RRI by about 70% in comparison with MEAN. In addition, the proposed method realized precise HRV analysis. The proposed method will contribute to the realization of precise HRV-based health monitoring services.

Deniosing Autoencoder-based Modification of RRI data with Premature Ventricular Contraction for Precise Heart Rate Variability Analysis
Shota Miyatani, Koichi Fujiwara, Manabu Kano
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2018-July, 5018, 5021, 2018年10月26日, ［査読有り］
研究論文（国際会議プロシーディングス）, © 2018 IEEE. The fluctuation of an RR interval (RRI) on an electrocardiogram (ECG) is called heart rate variability (HRV). HRV reflects the autonomic nerve activity, thus HRV analysis has been used for health monitoring such as stress estimation, drowsiness detection, epileptic seizure prediction, and cardiovascular disease diagnosis. However, RRI and HRV features are easily affected by arrhythmia, which deteriorates the health monitoring performance. Premature ventricular contraction (PVC) is common arrhythmia that many healthy persons have. Thus, a new methodology for dealing with RRI fluctuation disturbed by PVC needs to be developed for realizing precise health monitoring. To modify RRI data affected by PVC, the present work proposes a new method based on a denoising autoencoder (DAE), which reconstructs original input data from the noisy input data by using a neural network. The proposed method, referred to as DAE-based RRI modification (DAERM), aims to correct the disturbed RRI data by regarding PVC as artifacts. The present work demonstrated the usefulness of the proposed DAE-RM through its application to real RRI data with artificial PVC (PVC-RRI). The result showed that DAE-RM successfully modified PVC-RRI data. In fact, the root means squared error (RMSE) of the modified RRI was improved by 83.5% from the PVC-RRI. The proposed DAERM will contribute to realizing precise HRV-based health monitoring in the future.

Is hemifacial spasm affected by changes in the heart rate? A study using heart rate variability analysis.
Tadashi Hamasaki, Motohiro Morioka, Koichi Fujiwara, Chikao Nakayama, Miho Harada, Kiyohiko Sakata, Yu Hasegawa, Toshitaka Yamakawa, Kazumichi Yamada, Akitake Mukasa
Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology, 129, 10, 2205, 2214, 2018年10月, ［査読有り］, ［責任著者］, ［国際誌］
英語, 研究論文（学術雑誌）, OBJECTIVE: Hemifacial spasm (HFS) is caused by arterial conflict at the root exit zone of the facial nerve. As the offending artery is pulsatile in nature, this study investigated the association of heart rate fluctuation with HFS. METHODS: Twenty-four preoperative patients underwent simultaneous recordings of facial electromyogram and electrocardiogram overnight. Series of R-wave to R-wave intervals (RRIs) in the electrocardiogram were analyzed across subjects in relation to HFS. The degree of heart rate fluctuation was quantified by analyzing the heart rate variability (HRV). The sleep stage was evaluated during the period of HFS. RESULTS: A 0.1 Hz fluctuation in RRIs by 5% compared to the baseline preceded a few seconds the onset of the HFS, indicating that a significant increase in the heart rate coincided with HFS. HRV analysis demonstrated that fluctuations in the heart rate were significantly enhanced during HFS. Wake or light sleep stages were more often accompanied by HFS, suggesting an association with autonomic activities. CONCLUSION: Our findings suggest that the etiology of HFS is more than just a mechanical compression of the facial nerve and may involve changes in pulsatile frequency in offending arteries. SIGNIFICANCE: We propose the etiology of HFS from a unique standpoint.

Ischemic stroke detection by analyzing heart rate variability in rat middle cerebral artery occlusion model
Tomonobu Kodama, Keisuke Kamata, Koichi Fujiwara, Manabu Kano, Toshitaka Yamakawa, Ichiro Yuki, Yuichi Murayama
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26, 6, 1152, 1160, 2018年06月, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）, © 2001-2011 IEEE. Although early reperfusion therapy is effective for acute ischemic stroke, limited therapeutic time-window resulted in only 10% of patients receiving reperfusion therapy. A fast and reliable stroke detection method is desired so that patients can receive early reperfusion therapy. It has been reported that ischemic stroke affects heart rate variability (HRV), which reflects activities of the autonomic nervous function. Thus, ischemic stroke may be detected at an acute stage through monitoring HRV. This paper proposes an HRV-based ischemic stroke detection algorithm by using multivariate statistical process control (MSPC), which is a well-known anomaly detection algorithm. As a feasibility study before collecting a large amount of clinical data from human patients, this paper used the middle cerebral artery occlusion (MCAO) model in rats for collecting HRV data shortly after ischemic stroke onsets. The 11 MCAO-operated rats and 11 sham-operated rats were prepared, and HRV data of three sham-operated rats were used for model construction. The data on the other 19 rats were used for its validation. The experimental result showed that sensitivity and specificity of the proposed algorithm were 82% and 75%, respectively. Thus, the present work shows the possibility of realizing an HRV-based ischemic stroke detection system for human patients.

Nearest correlation-based input variable weighting for soft-sensor design
Fujiwara, K., Kano, M.
Frontiers in Chemistry, 6, MAY, 2018年05月, ［査読有り］, ［筆頭著者, 責任著者］
英語, 研究論文（学術雑誌）

Design of false heart rate feedback system for improving game experience
Sayaka Ogawa, Koichi Fujiwara, Toshitaka Yamakawa, Erika Abe, Manabu Kano
2018 IEEE International Conference on Consumer Electronics, ICCE 2018, 2018-January, 1, 4, 2018年03月26日, ［査読有り］
研究論文（国際会議プロシーディングス）, © 2018 IEEE. When players are excited by playing a video game, corresponding physiological responses such as sweating or changes in heart rate may appear. It is assumed that presenting physiological responses during game play to players in real-time alters their game experience even when they play the same game. Based on this assumption, this work investigated the effect of false heart rate (HR) feedback on game experience through experiments using a simple action game. Our experimental results indicated that false HR feedback not only prevented the players from becoming tired of the game but also enhanced players' experiences. In addition, a new game controller that can present HR information audibly and tactually was developed for realizing a game system based on false HR feedback.

CFD-Based Design of Focal Brain Cooling System for Suppressing Epileptic Seizures
Kei Hata, Takuto Abe, Takao Inoue, Koichi Fujiwara, Takatomi Kubo, Toshitaka Yamakawa, Sadahiro Nomura, Hirochika Imoto, Michiyasu Suzuki, Manabu Kano
Computer Aided Chemical Engineering, 44, 2089, 2094, 2018年01月01日, ［査読有り］
論文集(書籍)内論文, © 2018 Elsevier B.V. Epilepsy is a group of neurological disorders which is caused by excessive neuronal activities in cerebrum and characterized by recurrent seizures. A quarter of patients have intractable epilepsy and do not become seizure-free with medication. We are developing an implantable and wearable focal brain cooling system, which enables the patients to lead ordinary daily life. The system cools the epileptic focus, where the excessive neuronal activities begin, by delivering cold saline to a cranially implanted cooling device. In this research, we developed a whole system model through the first principles and animal experiments. The results of system design have shown that a cooling device with more complex channel structure achieves higher temperature uniformity in the brain with lower flow rate of saline. The optimal structure was derived by taking account of the trade-off between pressure drop and temperature uniformity. In addition, the results have demonstrated that the cooling duration is less than 10 minutes for the average temperature 2 mm below the cooling device (inside the brain) to reach 25 °C; it is short enough to cool the brain after seizure is predicted by existing electroencephalogram (EEG)-based algorithms. Moreover, the frequency of battery charging would be once in several days for most patients.

Validation of HRV-based drowsy-driving detection method with EEG sleep stage classification
T. Yamakawa, K. Fujiwara, T. Hiraoka, M. Kano, Y. Sumi, F. Masuda, M. Matsuo, H. Kadotani
Sleep Medicine (Proc. of World Sleep Congress), 40, e352, e352, Elsevier BV, 2017年12月, ［査読有り］
英語, 研究論文（国際会議プロシーディングス）

Seizure prediction in localization-related epilepsy by heart rate variability monitoring
Miyajima M, Fujiwara K, Toshitaka Y, Yoko S, Sasai-Sakuma T, Kano M, Maehara T, Watanabe Y, Watanabe S, Murata Y, Sasano T, Eisuke M
JOURNAL OF THE NEUROLOGICAL SCIENCES, 381, 554, 555, 2017年10月, ［査読有り］
英語

A new infarction detection method based on heart rate variability in rat middle cerebral artery occlusion model
Kodata T, Kamata K, Fujiwara K, Kano M, Yamakawa T, Yuki I, Murayama Y
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 3061, 3064, 2017年09月13日, ［査読有り］
英語, 研究論文（国際会議プロシーディングス）, © 2017 IEEE. Objective: The present study proposes a cerebral infarction detection algorithm based on heart rate variability (HRV). Methods: It has been reported that infarction affects HRV. Therefore, infarction could be detected at an acute stage by monitoring HRV. This study uses multivariate statistical process control (MSPC), which is a well-known anomaly monitoring method. HRV data shortly after infarction onsets are collected by using the middle cerebral artery occlusion (MCAO) model in rats. This study prepares 11 MCAO-operated rats and 11 sham-operated rats. Three sham-operated rats' data are used for model construction of MSPC, and the other 19 rats' data are used for its validation. Results: The sensitivity and specificity of the proposed algorithm were 82 % and 75 %, respectively. Conclusion: An infarction onset could be detected at an acute stage by monitoring HRV.

Design of focal brain cooling system for suppressing epileptic seizures
Kei Hata, Koichi Fujiwara, Manabu Kano, Takao Inoue, Sadahiro Nomura, Hirochika Imoto, Michiyasu Suzuki
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 283, 286, 2017年09月13日, ［査読有り］
英語, 研究論文（国際会議プロシーディングス）, ? 2017 IEEE. Epilepsy is a group of diseases caused by excessive neuronal activities, and one-quarter of the patients do not become seizure-free by the existing treatments. The potential treatments include focal brain cooling, which aims to cool the region where the excessive neuronal activities begin. We are developing a focal brain cooling system. The system delivers cold saline to a cranially implanted cooling device. The outflow is cooled by a Peltier device and pumped for circulation. The Peltier device and the pump are activated only when a seizure is predicted. In this research, the length of time for cooling the brain was calculated with a computational fluid dynamics (CFD)-based model of the focal brain cooling system. As a result, it takes less than 10 minutes for the average temperature 2 mm below the cooling device to reach 25.0 °C. It is much shorter than the time from seizure prediction to seizure onset when an existing algorithm for prediction is used.

Development of correlation-based process characteristics visualization method and its application to fault detection
Koichi Fujiwara, Manabu Kano
IEEE International Conference on Control and Automation, ICCA, 940, 945, 2017年08月04日, ［査読有り］
英語, 研究論文（国際会議プロシーディングス）, ? 2017 IEEE. Although process monitoring is important for maintaining safety and product quality, it is difficult to understand process characteristics particularly when they are changing. Since the correlation among variables changes due to changes in process characteristics, process data visualization based on the correlation among variables helps process characteristic understanding. In the present work, a new correlation-based data visualization method is proposed by integrating joint decorrelation (JD) and stochastic proximity embedding (SPE). JD is a blind source separation (BSS) method that can separates sample based on the correlation, and SPE is a self-organizing algorithm that can map high-dimensional data to a two-dimensional plane. The proposed method, referred to as JD-SPE, separates samples based on the correlation using JD and the separated samples are visualized in the two-dimensional plane by SPE. Correlation matrices have to be constructed before sample separation for JD; however how to construct them is not clear. The present work also proposes a correlation matrix construction method for JD by using nearest correlation spectral clustering (NCSC), which is a correlation-based clustering method. In addition, a new process monitoring method based on multivariate statistical process control (MSPC) which is a well-known process monitoring algorithm and JD-SPE. This monitoring method is referred to as JD-SPE-r 2 . The proposed JD-SPE-Γ 2 can detect a fault that can not detected by the conventional MSPC. The usefulness of the proposed methods is demonstrated through numerical examples.

運転中の能動的行為によるドライバの覚醒維持効果と運転安全性
伊部達郎, 平岡敏洋, 阿部恵里花, 藤原幸一, 山川俊貴
自動車技術会論文集, 48, 2, 463, 469, 2017年02月, ［査読有り］
日本語, 研究論文（学術雑誌）

Missing RRI interpolation for HRV analysis using locally-weighted partial least squares regression
Keisuke Kamata, Koichi Fujiwara, Toshiki Yamakawa, Manabu Kano
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2016-October, EMBC, 2386, 2389, 2016年10月13日, ［査読有り］
英語, 研究論文（国際会議プロシーディングス）, ? 2016 IEEE. The R-R interval (RRI) fluctuation in electrocardiogram (ECG) is called heart rate variability (HRV). Since HRV reflects autonomic nervous function, HRV-based health monitoring services, such as stress estimation, drowsy driving detection, and epileptic seizure prediction, have been proposed. In these HRV-based health monitoring services, precise R wave detection from ECG is required; however, R waves cannot always be detected due to ECG artifacts. Missing RRI data should be interpolated appropriately for HRV analysis. The present work proposes a missing RRI interpolation method by utilizing using just-in-time (JIT) modeling. The proposed method adopts locally weighted partial least squares (LW-PLS) for RRI interpolation, which is a well-known JIT modeling method used in the filed of process control. The usefulness of the proposed method was demonstrated through a case study of real RRI data collected from healthy persons. The proposed JIT-based interpolation method could improve the interpolation accuracy in comparison with a static interpolation method.

Epileptic Seizure Prediction Based on Multivariate Statistical Process Control of Heart Rate Variability Features
Koichi Fujiwara, Miho Miyajima, Toshitaka Yamakawa, Erika Abe, Yoko Suzuki, Yuriko Sawada, Manabu Kano, Taketoshi Maehara, Katsuya Ohta, Taeko Sasai-Sakuma, Tetsuo Sasano, Masato Matsuura, Eisuke Matsushima
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 63, 6, 1321, 1332, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2016年06月, ［査読有り］, ［筆頭著者, 責任著者］
英語, 研究論文（学術雑誌）, Objective: The present study proposes a new epileptic seizure prediction method through integrating heart rate variability (HRV) analysis and an anomaly monitoring technique. Methods: Because excessive neuronal activities in the preictal period of epilepsy affect the autonomic nervous systems and autonomic nervous function affects HRV, it is assumed that a seizure can be predicted through monitoring HRV. In the proposed method, eight HRV features are monitored for predicting seizures by using multivariate statistical process control, which is a well-known anomaly monitoring method. Results: We applied the proposed method to the clinical data collected from 14 patients. In the collected data, 8 patients had a total of 11 awakening preictal episodes and the total length of interictal episodes was about 57 h. The application results of the proposed method demonstrated that seizures in ten out of eleven awakening preictal episodes could be predicted prior to the seizure onset, that is, its sensitivity was 91%, and its false positive rate was about 0.7 times per hour. Conclusion: This study proposed a new HRV-based epileptic seizure prediction method, and the possibility of realizing an HRV-based epileptic seizure prediction system was shown. Significance: The proposed method can be used in daily life, because the heart rate can be measured easily by using a wearable sensor.

Evaluation of a Portable Two-channel Electroencephalogram Monitoring System to Analyze Sleep Stages
T. Kanemura, H. Kadotani, M. Matsuo, F. Masuda, K. Fujiwara, M. Ohira, N. Yamada
Journal of Oral and Sleep Medicine, 2, 2, 101, 108, (NPO)日本睡眠歯科学会, 2016年05月, ［査読有り］
英語, 研究論文（学術雑誌）

Variable Elimination-Based Contribution for Accurate Fault Identification
Satoyama Yusuke, Fujiwara Koichi, Kano Manabu
IFAC PAPERSONLINE, 49, 7, 383, 388, 2016年, ［査読有り］
英語, 研究論文（学術雑誌）, ? 2016 We propose a new fault identification method, which can describe the contribution of each process variable to a detected fault and identify a faulty variable more accurately than conventional methods. In the proposed method, in addition to a fault detection model that describes normal operating condition (NOC), multiple fault identification models that describe the same NOC are also constructed by eliminating one variable from all monitored variables at a time. After a fault is detected with the fault detection model, the fault detection index, e.g. a combined index of the T 2 and Q statistics, is calculated by using each of the fault identification models. When the faulty variable is eliminated, the index does not change before and after the fault occurs. On the other hand, when the normal variable is eliminated, the index is affected by the fault and increases after the fault occurs. Thus, the eliminated variable corresponding to the index that does not increase after the occurrence of the fault is identified as a faulty variable. In the proposed method, the ratio of the average index in NOC to the current index is used as a fault identification index or a contribution. To validate the proposed method, VEC was compared with the reconstruction-based contribution (RBC) through numerical examples. The results have demonstrated that VEC outperformed RBC in fault identification performance both in the linear case and in the nonlinear case.

Epileptic Seizure Prediction Based on Multivariate Statistical Process Control of Heart Rate Variability Features
Koichi Fujiwara, Miho Miyajima, Toshitaka Yamakawa, Erika Abe, Yoko Suzuki, Yuriko Sawada, Manabu Kano, Taketoshi Maehara, Katsuya Ohta, Taeko Sasai-Sakuma, Tetsuo Sasano, Masato Matsuura, Eisuke Matsushima
IEEE Transactions on Biomedical Engineering, 63, 6, 1321, 1332, 2016年, ［査読有り］
英語, 研究論文（学術雑誌）, ? 2015 IEEE.Objective: The present study proposes a new epileptic seizure prediction method through integrating heart rate variability (HRV) analysis and an anomaly monitoring technique. Methods: Because excessive neuronal activities in the preictal period of epilepsy affect the autonomic nervous systems and autonomic nervous function affects HRV, it is assumed that a seizure can be predicted through monitoring HRV. In the proposed method, eight HRV features are monitored for predicting seizures by using multivariate statistical process control, which is a well-known anomaly monitoring method. Results: We applied the proposed method to the clinical data collected from 14 patients. In the collected data, 8 patients had a total of 11 awakening preictal episodes and the total length of interictal episodes was about 57 h. The application results of the proposed method demonstrated that seizures in ten out of eleven awakening preictal episodes could be predicted prior to the seizure onset, that is, its sensitivity was 91%, and its false positive rate was about 0.7 times per hour. Conclusion: This study proposed a new HRV-based epileptic seizure prediction method, and the possibility of realizing an HRV-based epileptic seizure prediction system was shown. Significance: The proposed method can be used in daily life, because the heart rate can be measured easily by using a wearable sensor.

Canine Emotional States Assessment with Heart Rate Variability
Eri Nakahara, Yuki Maruno, Takatomi Kubo, Rina Ouchi, Maki Katayama, Koichi Fujiwara, Miho Nagasawa, Takefumi Kikusui, Kazushi Ikeda
2016 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), IEEE, 2016年, ［査読有り］
英語, 研究論文（国際会議プロシーディングス）, Emotions of a person affect the person's performance in a task and so do emotions of a rescue dog that works after disasters. Hence, estimating emotions of a rescue dog by the handler can improve its performance and welfare. Emotions also appear in physiological signals such as heart rate variability (HRV). In fact, HRV has information of emotions in both cases of human and dogs. To make emotion estimation more practical, we proposed a method for emotion estimation from HRV of dogs and evaluated its performance using real data. The method classified positive, negative, and neutral emotions with 88% accuracy within each subject and 72% over all subjects. These accuracies are high enough for practical use in rescue dogs.

Development of Drowsiness Detection Method by Integrating Heart Rate Variability Analysis and Multivariate Statistical Process Control
E. Abe, K. Fujiwara, T. Hiraoka, T. Yamakawa, M. Kano
SICE Journal of Control, Measurement, and System Integration, 9, 1, 10, 17, 公益社団法人 計測自動制御学会, 2016年01月, ［査読有り］, ［責任著者］
英語, 研究論文（学術雑誌）, Drowsy driving accidents can be prevented if predicted in advance. The present work aims to develop a new method for detecting driver drowsiness based on the fact that the autonomic nervous function affects heart rate variability (HRV), which is a fluctuation of the RR interval (RRI) obtained from an electrocardiogram (ECG). The proposed method uses eight HRV features derived through HRV analysis as input variables of multivariate statistical process control (MSPC), which is a well-known anomaly detection method in the field of process control. In the proposed method, only one principal component was adopted in MSPC and driver drowsiness was detected through monitoring the T2 statistic. Driving simulator experiments demonstrated that driver drowsiness was successfully detected in seven out of eight cases before accidents occurred. In addition, the proposed method was implemented in a smartphone app for on-vehicle use.

Comparisons of Portable Sleep Monitors of Different Modalities: Potential as Naturalistic Sleep Recorders.
Masahiro Matsuo, Fumi Masuda, Yukiyoshi Sumi, Masahiro Takahashi, Naoto Yamada, Masako Hasegawa Ohira, Koichi Fujiwara, Takashi Kanemura, Hiroshi Kadotani
Frontiers in neurology, 7, 110, 110, 2016年, ［査読有り］, ［国際誌］
英語, 研究論文（学術雑誌）, BACKGROUND: Humans spend more than one-fourth of their life sleeping, and sleep quality has been significantly linked to health. However, the objective examination of ambulatory sleep quality remains a challenge, since sleep is a state of unconsciousness, which limits the reliability of self-reports. Therefore, a non-invasive, continuous, and objective method for the recording and analysis of naturalistic sleep is required. OBJECTIVE: Portable sleep recording devices provide a suitable solution for the ambulatory analysis of sleep quality. In this study, the performance of two activity-based sleep monitors (Actiwatch and MTN-210) and a single-channel electroencephalography (EEG)-based sleep monitor (SleepScope) were compared in order to examine their reliability for the assessment of sleep quality. METHODS: Twenty healthy adults were recruited for this study. First, data from daily activity recorded by Actiwatch and MTN-210 were compared to determine whether MTN-210, a more affordable device, could yield data similar to Actiwatch, the de facto standard. In addition, sleep detection ability was examined using data obtained by polysomnography as reference. One simple analysis included comparing the sleep/wake detection ability of Actiwatch, MTN-210, and SleepScope. Furthermore, the fidelity of sleep stage determination was examined using SleepScope in finer time resolution. RESULTS: The results indicate that MTN-210 demonstrates an activity pattern comparable to that of Actiwatch, although their sensitivity preferences were not identical. Moreover, MTN-210 provides assessment of sleep duration comparable to that of the wrist-worn Actiwatch when MTN-210 was attached to the body. SleepScope featured superior overall sleep detection performance among the three methods tested. Furthermore, SleepScope was able to provide information regarding sleep architecture, although systemic bias was found. CONCLUSION: The present results suggest that single-channel EEG-based sleep monitors are the superior option for the examination of naturalistic sleep. The current results pave a possible future use for reliable portable sleep assessment methods in an ambulatory rather than a laboratory setting.

Efficient wavenumber selection based on spectral fluctuation dividing and correlation-based clustering for calibration modeling
Takuya Miyano, Koichi Fujiwara, Manabu Kano, Hideaki Tanabe, Hiroshi Nakagawa, Tomoyuki Watanabe, Hidemi Minami
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 148, 85, 94, ELSEVIER SCIENCE BV, 2015年11月, ［査読有り］
英語, 研究論文（学術雑誌）, This study proposes an efficient wavenumber selection method to develop calibration models based on near-infrared (NIR) spectroscopy. First, spectral fluctuation dividing (SFD) divides a whole NIR spectrum into multiple spectral intervals based on a spectral fluctuation profile, which consists of the standard deviation of spectral intensities at each wavenumber. Then, nearest correlation spectral clustering (NCSC) clusters those spectral intervals into spectral interval groups based on the correlation of the spectral intensities among the spectral intervals. Finally, the proposed method builds a partial least squares (PLS) model using the spectral intensities in each spectral interval group, and selects several spectral interval groups based on the estimation accuracy of each PLS model. This method was named SFD-NCSC-PLS. In developing calibration models to estimate water and drug contents in granules, SFD-NCSC-PLS achieved higher estimation accuracy than the commonly-used interval PLS, searching combination moving window PLS, and the methods using either SFD or NCSC The results show that SFD-NCSC-PLS can properly select wavenumbers that reflect the target response. In addition, SFD-NCSC-PLS took only less than half the computation time compared with the wavenumber selection methods using either SFD or NCSC Thus, the proposed SFD-NCSC-PLS is a promising wavenumber selection method. (C) 2015 Elsevier B.V. All rights reserved.

Efficient input variable selection for soft-senor design based on nearest correlation spectral clustering and group Lasso
Koichi Fujiwara, Manabu Kano
ISA TRANSACTIONS, 58, 9, 367, 379, ELSEVIER SCIENCE INC, 2015年09月, ［査読有り］, ［筆頭著者, 責任著者］
英語, 研究論文（学術雑誌）, Appropriate input variables have to be selected for building highly accurate soft sensor. A novel input variable selection method based on nearest correlation spectral clustering (NCSC) has been proposed, and it is referred to as NCSC-based variable selection (NCSC-VS). Although NCSC-VS can select appropriate input variables, a lot of parameters have to be tuned carefully for selecting proper variables. The present work proposes a new methodology for efficient input variable selection by integrating NCSC and group Lasso. The proposed NCSC-based group Lasso (NCSC-GL) can not only reduce the number of tuning parameters but also achieve almost the same performance as NCSC-VS. The usefulness of the proposed NCSC-GL is demonstrated through applications to soft sensor design for a pharmaceutical process and a chemical process. (C) 2015 ISA. Published by Elsevier Ltd. All rights reserved.

Heart Rate Monitoring by A Pulse Sensor Embedded Game Controller
Erika Abe, Hiroshi Chigira, Koichi Fujiwarai, Toshitaka Yamakawa, Manabu Kano
2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 1266, 1269, IEEE, 2015年, ［査読有り］
英語, 研究論文（国際会議プロシーディングス）, If player condition during video game playing could be measured in real time, it would become possible to develop a new game interaction system. Since heart rate (HR) has been used for various psychological state estimation, it can be used for player condition estimation. The present work consists of two parts: the development of a new game controller that can measure player HR naturally based on a photoplethysmogram (PPG), and simultaneous monitoring of player condition by using the newly developed game controller.
The experiment result demonstrated that the newly developed game controller could measure the player HR with sufficiently high accuracy. In addition, it showed that the correlation coefficient between HR and the game score varied according to player condition. This indicates that player condition during video game could be estimated by monitoring HR and the game score simultaneously.

Accuracy Comparison between Two Microcontroller-embedded R-wave Detection Methods for Heart-rate Variability Analysis
Toshitaka Yamakawa, Ryunosuke Kinoshita, Koichi Fujiwara, Manabu Kano, Miho Miyajima, Tadashi Sakata, Yuichi Ueda
2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 1010, 1013, IEEE, 2015年, ［査読有り］
英語, 研究論文（国際会議プロシーディングス）, Analysis of heart rate variability, which is calculated using the R-R intervals (RRI) of electrocardiogram (ECG), provides beneficial information for both clinical and healthcare diagnoses. To achieve the required accuracy for RRI measurement using the wearable telemetery system, two R-wave detection methods (one based on voltage threshold and another that adopts differential peak detection) were developed for implementation in a low-power microcontroller integrated into a wearable telemeter. Accuracy of these methods were compared using a clinical-grade ECG measurement system to evaluate the systematic errors of the proposed methods by correlation and Bland-Altman analyses.

Development of Stroke Detection Method by Heart Rate Variability Analysis and Support Vector Machine
Keisuke Kamata, Koichi Fujiwara, Tomonobu Kodama, Manabu Kano, Toshitaka Yamakawa, Norikata Kobayashi, Fuminori Shimizu
2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 1257, 1261, IEEE, 2015年
英語, 研究論文（国際会議プロシーディングス）, It is important to start stroke treatment as early as possible for patient prognosis. In particular, thrombolysis with the tissue plasminogen activator (tPA) that can dissolve blood clots is effective only when it is given within 4.5 hours from the symptom onset. Since it is sometimes difficult for patients to recognize their symptoms, an early stroke detection system is needed. It is possible that a stroke can be detected by monitoring heart rate variability (HRV) because a stroke affects the autonomic nervous system. In the present work, a stroke detection method was proposed by integrating HRV analysis and support vector machine (SVM). The sensitivity and the specificity of the proposed method were 100% and 80%, respectively. The possibility of realizing an HRV-based stroke detection system was shown.

Nearest correlation Louvain method for fast and good selection of input variables of statistical model
Taku Uchimaru, Koji Hazama, Koichi Fujiwara, Manabu Kano
IFAC Proceedings Volumes (IFAC-PapersOnline), 28, 8, 123, 128, 2015年, ［査読有り］
研究論文（学術雑誌）, © 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.In the present work, a new input variable selection method for building linear regression models is proposed. The proposed method is referred to as nearest correlation Louvain method based variable selection (NCLM-VS). NCLM-VS is a correlation-based group-wise method; it constructs an affinity matrix of input variables by the nearest correlation (NC) method, partitions the affinity matrix by the Louvain method (LM), consequently clusters input variables into multiple variable classes, and finally selects variable classes according to their contribution to estimates. LM is very fast and optimizes the number of classes automatically unlike spectral clustering (SC). The advantage of NCLM-VS over conventional methods including NCSC-VS is demonstrated through their applications to soft-sensor design for an industrial chemical process and calibration modeling based on near-infrared (NIR) spectra. In particular, it is confirmed that NCLM-VS is significantly faster than the recently proposed NCSC-VS while NCLM-VS can achieve as good estimation performance as NCSC-VS.

A Study on Heart Rate Monitoring in Daily Life by Using a Surface-Type Sensor
H. Chigira, A. Maeda, M. Kobayashi, K. Fujiwara, T. Hiraoka, A. Tanaka, T. Tanaka
SICE Journal of Control, Measurement, and System Integration, 8, 1, 74, 78, The Society of Instrument and Control Engineers, 2015年01月, ［査読有り］
英語, 研究論文（学術雑誌）, Heart rate monitoring has huge potential in disease prevention, stroke prediction, and mental stress/workload assessment. Although most conventional heart rate monitoring systems are wearable devices, such devices may be obtrusive and disturb our daily life. This work proposes a new large, thin and flat/curved surface-type heart rate sensor. Building the proposed sensor into the surfaces of daily devices, such as a steering wheel or a computer mouse, allows daily heart rate to be monitored unobtrusively, without changing the users behavior. Experiments on subjects evaluated the heart rate monitoring performances of flat, curved, and mouse-embedded prototypes. The results confirm PPG measurement accuracies equivalent to those of the conventional point sensor.

Development of Drowsy Driving Accident Prediction by Heart Rate Variability Analysis
Erika Abe, Koichi Fujiwara, Toshihiro Hiraoka, Toshitaka Yamakawa, Manabu Kano
2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), IEEE, 2014年
英語, 研究論文（国際会議プロシーディングス）, Drowsy driving accidents can be prevented if it can be predicted in advance. The present work aims to develop a new method for predicting a drowsy driving accident based on the fact that the autonomic nervous function affects heart rate variability (HRV), which is the fluctuation of the RR interval (RRI) obtained from an electrocardiogram (ECG). The proposed method uses HRV features derived through HRV analysis as input variables of multivariate statistical process control (MSPC), which is a well-known anomaly detection method in process control. Driving simulator experiments demonstrated that driver drowsiness was successfully predicted seven out of eight cases before drowsy driving accidents occur.

Epileptic seizure monitoring by using multivariate statistical process control
Hirotsugu Hashimoto, Koichi Fujiwara, Yoko Suzuki, Miho Miyajima, Toshitaka Yamakawa, Manabu Kano, Taketoshi Maehara, Katsuya Ohta, Tetsuo Sasano, Masato Matsuura, Eisuke Matsushima
IFAC Proceedings Volumes (IFAC-PapersOnline), 12, PART 1, 249, 254, 2013年, ［査読有り］
英語, 研究論文（国際会議プロシーディングス）, Although refractory epileptic patients suffer from uncontrolled seizures, their quality of life (QoL) may be improved if the seizure can be predicted in advance. In the preictal period, the excessive neuronal activity of epilepsy affects the autonomic nervous system. Since the fluctuation of the R-R interval (RRI) of an electrocardiogram (ECG), called heart rate variability (HRV), reflects the autonomic nervous function, an epileptic seizure may be predicted through monitoring RRI data. The present work proposes an HRV-based epileptic seizure monitoring method by utilizing multivariate statistical process control (MSPC) technology. Various HRV features are derived from the RRI data in both the interictal period and the preictal period recorded from epileptic patients, and an MSPC-based seizure prediction model is built from the interictal HRV features. The result of applying the proposed monitoring method to a clinical data demonstrates that seizures can be detected at least one minutes prior to the seizure onset. The possibility of realizing an HRV-based seizure monitoring system is shown. © IFAC.

Virtual sensing technology in process industries: Trends and challenges revealed by recent industrial applications
Manabu Kano, Koichi Fujiwara
Journal of Chemical Engineering of Japan, 46, 1, 1, 17, 2013年, ［査読有り］
英語, Virtual sensing technology is crucial for high product quality and productivity in any industry. This review aims to clarify the trend of research and application of virtual sensing technology in process industries. After a brief survey, practical issues are clarified by introducing recent questionnaire survey results: 1) changes in process characteristics and operating conditions, 2) individual difference of equipment, and 3) reliability of soft-sensors. Since input variable selection is crucial for high estimation performance, conventional methods and new group-wise variable selection methods are introduced, and the usefulness of the group-wise variable selection methods is demonstrated through industrial case studies. Just-in-time (JIT) modeling is dealt with as a promising virtual sensing technology that can cope with changes in process characteristics as well as nonlinearity. Recent developments leading to successful industrial applications are introduced: correlation-based JIT (CoJIT) modeling and locally weighted regression (LWR), especially LW-PLS, with modified similarity measures. Manufacturing processes in different industries are quite different in appearance, but they have very similar problems from the viewpoint of quality issue. There remain practical issues requiring further research efforts to realize high-performance, maintenance-free virtual sensing technology. © 2013 The Society of Chemical Engineers, Japan.

Input variable selection for PLS modeling using nearest correlation spectral clustering
Koichi Fujiwara, Hiroshi Sawada, Manabu Kano
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 118, 109, 119, ELSEVIER SCIENCE BV, 2012年08月, ［査読有り］, ［筆頭著者］
英語, 研究論文（学術雑誌）, Soft-sensors have been widely used for estimating product quality or other key variables, and partial least squares (PLS) regression is accepted as a useful technique for soft-sensor design. To achieve high estimation performance, it is important to select appropriate input or explanatory variables. The present work proposes a new systematic methodology to select input variables for PLS using nearest correlation spectral clustering (NCSC), which is a clustering method based on the correlation among variables. The proposed method, referred to as NCSC-based variable selection (NCSC-VS), clusters the variables into some variable classes by using NCSC, and selects a few variable classes according to their contribution to estimates. That is, the input variables are not selected individually but some variables that have similar correlation are selected together. The usefulness of the proposed NCSC-VS is demonstrated through an application to soft-sensor design for an industrial chemical process. (C) 2012 Elsevier B.V. All rights reserved.

Development of correlation-based pattern recognition algorithm and adaptive soft-sensor design
Koichi Fujiwara, Manabu Kano, Shinji Hasebe
CONTROL ENGINEERING PRACTICE, 20, 4, 371, 378, PERGAMON-ELSEVIER SCIENCE LTD, 2012年04月, ［査読有り］, ［筆頭著者］
英語, 研究論文（学術雑誌）, Although soft-sensors have been used for estimating product quality, they do not always function well due to not only changes in process characteristics but also the individual difference of production devices. Correlation-based Just-In-Time (CoJIT) modeling has been proposed to cope with such changes in process characteristics: however it cannot deal with the individual difference. In the present work, a new pattern recognition method, referred to as the nearest correlation (NC) method is proposed to cope with the individual difference. The proposed NC method is integrated with CoJIT modeling. The advantages of the proposed methods are demonstrated through a case study. (c) 2010 Elsevier Ltd. All rights reserved.

Correlation-based spectral clustering for flexible process monitoring
Koichi Fujiwara, Manabu Kano, Shinji Hasebe
JOURNAL OF PROCESS CONTROL, 21, 10, 1438, 1448, ELSEVIER SCI LTD, 2011年12月, ［査読有り］, ［筆頭著者］
英語, 研究論文（学術雑誌）, The individuality of production devices should be taken into account when statistical models are designed for parallelized devices. In the present work, a new clustering method, referred to as NC-spectral clustering, is proposed for discriminating the individuality of production devices. The key idea is to classify samples according to the differences of the correlation among measured variables, since the individuality of production devices is expressed by the correlation. In the proposed NC-spectral clustering, the nearest correlation (NC) method and spectral clustering are integrated. The NC method generates the weighted graph that expresses the correlation-based similarities between samples, and the constructed graph is partitioned by spectral clustering. A new statistical process monitoring method and a new soft-sensor design method are proposed on the basis of NC-spectral clustering. The usefulness of the proposed methods is demonstrated through a numerical example and a case study of parallelized batch processes. (C) 2011 Elsevier Ltd. All rights reserved.

Development of correlation-based clustering method and its application to software sensing
Koichi Fujiwara, Manabu Kano, Shinji Hasebe
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 101, 2, 130, 138, ELSEVIER SCIENCE BV, 2010年04月, ［査読有り］, ［筆頭著者］
英語, 研究論文（学術雑誌）, The individuality of production devices should be taken into account when soft-sensors are designed for parallelized devices. Since it is expressed as differences of the correlation among measured variables, it is useful to cluster samples on the basis of the correlation among variables for adopting a multi-model approach. In addition, changes in process characteristics can be coped with in the same way. In the present work, a new clustering method, referred to as NC-spectral clustering, is proposed by integrating the nearest correlation (NC) method and spectral clustering. Spectral clustering is a graph partitioning method that can be used for sample classification when an affinity matrix of a weighted graph is given. The NC method can detect samples that are similar to the query from the viewpoint of the correlation without a teacher signal. In the proposed method, the NC method is used for constructing the weighted graph that expresses the correlation-based similarities between samples and the constructed graph is partitioned by using spectral clustering. In addition, a new soft-sensor design method is proposed on the basis of the proposed NC-spectral clustering. The usefulness of the proposed methods is demonstrated through a numerical example and a case study of parallelized batch processes. The performance of the proposed correlation-based method is better than that of the conventional distance-based methods. (C) 2010 Elsevier B.V. All rights reserved.

Soft-Sensor Development Using Correlation-Based Just-in-Time Modeling
Koichi Fujiwara, Manabu Kano, Shinji Hasebe, Akitoshi Takinami
AICHE JOURNAL, 55, 7, 1754, 1765, JOHN WILEY & SONS INC, 2009年07月, ［査読有り］, ［筆頭著者］
英語, 研究論文（学術雑誌）, Soft-sensors have been widely used for estimating product quality or other key variables, but their estimation performance deteriorate when the process characteristics change. To cope with such changes, recursive PLS and Just-In-Time (JIT) modeling have been developed. However, recursive PLS does not always function well when process characteristics change abruptly and JIT modeling does not always achieve the high-estimation performance. In the present work, a new method for constructing soft-sensors based on a JIT modeling technique is proposed. In the proposed method, referred to as correlation-based JIT modeling (CoJIT), the samples used for local modeling are selected on the basis of the correlation among measured variables and the model can adapt to changes in process characteristics. The usefulness of the proposed method is demonstrated through a case study of a CSTR process, in which catalyst deactivation and recovery are taken into account. In addition, its industrial application to a cracked gasoline fractionator is reported. (C) 2009 American Institute of Chemical Engineers AIChE J, 55: 1754-1765, 2009

Development of correlation-based pattern recognition and its application to adaptive soft-sensor design
Koichi Fujiwara, Manabu Kano, Shinji Hasebe
ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings, 1990, 1995, 2009年, ［査読有り］
研究論文（国際会議プロシーディングス）, Although linear regression is a simple and useful method to build process models, they do not always function well in practice due to not only changes in process characteristics but differences of specifities between the equipments when multiple equipments are operated in parallel. To cope with them, the correlation between variables should be considered. In the present work, a new pattern recognition method, referred to as Nearest Correlation (NC) method that can select samples whose correlations are similar to the query point without supervised signal is proposed. The proposed procedures are as follows: 1) Subtract the query point from all the other samples. 2) Calculate the correlation coefficient between all pairs of arbitrary two subtracted samples, and the pairs whose correlation coefficients are close to -1 are selected. 4) Derive the subspace containing the query point from the selected samples. 4) The Q statistics between all samples and the derived subspace are calculated, and the samples whose Q statistic is small are selected as the similar samples to the query point. In addition, a new soft-sensor design method integrating the NC method and Just-In-Time (JIT) modeling is proposed. This method is referred to as Correlation-based JIT (C-JIT) modeling, and it cope with the changes in process characteristics and the differences of specifities between the equipments. The usefulness of the proposed NC method and C-JIT modeling are demonstrated through case studies of CSTR process. © 2009 SICE.

相関型 Just-In-Time モデリングによるソフトセンサの設計
藤原幸一, 加納学, 長谷部伸治
計測自動制御学会論文集, 44, 4, 317, 324, The Society of Instrument and Control Engineers, 2008年04月, ［査読有り］, ［筆頭著者］
日本語, Softsensors are widely used for estimating product quality or other key variables when on-line analyzers are not available. However, their estimation performance deteriorates when the process characteristics change. To cope with the changes in process characteristics and update the model, recursive methods such as recursive PLS and Just-In-Time (JIT) modeling have been developed. However, they do not always function well when process characteristics change abruptly. In the present work, a new method for constructing softsensors based on a JIT modeling technique is proposed. In the proposed method, referred to as correlation-based JIT modeling, the samples used for local modeling are selected on the basis of the correlation among variables. Q statistic is used as an index of the correlation. The proposed modeling procedure is as follows: 1) Divide samples stored in the database into some temporal datasets, 2) Apply Principal Component Analysis (PCA) to the datasets separately, 3) Calculate Q statistic of the query point against each dataset, 4) Select a dataset which provides the smallest Q statistic, and 5) Construct a temporary model from the selected dataset. The proposed method can adapt a model to changes in process characteristics even when operating condition is changed abruptly. It can also cope with process nonlinearity. The usefulness of the proposed method is demonstrated through a case study of a CSTR process whose catalyst deactivation and recovery are considered as changes in process characteristics.

Epitaxial supramolecular assembly of fullerenes formed by using a coronene template on a Au(111) surface in solution
Yoshimoto, S., Tsutsumi, E., Narita, R., Murata, Y., Murata, M., Fujiwara, K., Komatsu, K., Ito, O., Itaya, K.
Journal of the American Chemical Society, 129, 14, 2007年
研究論文（学術雑誌）

ウェーブレット解析を用いたバッチプロセス操作プロファイルの最適化
藤原幸一, 加納学, 長谷部伸治, 大野弘
計測自動制御学会論文集, 42, 10, 1143, 1149, The Society of Instrument and Control Engineers, 2006年10月, ［査読有り］, ［筆頭著者］
日本語, In the present work, a new regression method based on wavelet analysis and multivariate analysis is proposed. Referred to as wavelet coefficient regression (WCR), the proposed method can build a statistical model that relates operation profiles with product quality in a batch process. In WCR, selected wavelet coefficients of operation profiles are used as input variables of a statistical model, and thus time-related information such as timing of manipulation can be successfully modeled. In addition, by integrating multivariate analysis and wavelet analysis, WCR can cope with correlation of input variables. As a result, WCR enables us to build an accurate statistical model of a batch process. On the basis of WCR, a data-driven method for improving product quality in a batch process is also proposed. The proposed method can determine operation profiles that can achieve the desired product quality and optimize the operation profiles under a given performance index and various constraints. The usefulness of the proposed WCR and quality improvement method is demonstrated through a case study of lysine production based on a semi-batch fermentation process.

運転データに基づく品質改善のための定性的品質情報の定量化
加納学, 藤原幸一, 長谷部伸治, 大野弘
計測自動制御学会論文集, 42, 8, 902, 908, The Society of Instrument and Control Engineers, 2006年08月, ［査読有り］
日本語, The most important contribution of this work is to provide a new quantification method for product quality. A qualitative quality variable can be quantified by using a conventional method, e.g., good=1 and bad=0. However, this quantification method is useless for operating condition optimization, because the quantified variable does not have any physical meaning and thus the desired quality cannot be specified. On the other hand, the proposed method can relate operating condition to product yield by integrating principal component analysis (PCA) and liner discriminant analysis (LDA), and thus it enables us to specify the desired product quality and optimize the operating condition. In addition, a data-driven methodology for improving product quality and yield is proposed. Referred to as Data-Driven Quality Improvement (DDQI), the proposed method can cope with qualitative as well as quantitative quality variables, determine the operating conditions that can achieve the desired product quality, optimize the operating condition under various constraints, and thus can provide useful information to improve product quality. The usefulness of the proposed quantification method and DDQI is demonstrated through an illustrative case study.

運転データに基づく階層型品質改善システムの開発 : 品質制御のための操作変数選択
藤原幸一, 加納学, 長谷部伸治, 大野弘
計測自動制御学会論文集, 42, 8, 909, 915, The Society of Instrument and Control Engineers, 2006年08月, ［査読有り］, ［筆頭著者］
日本語, A new process control and monitoring system for quality imprgvement, referred to as hierarchical quality improvement system (HiQIS), is proposed. HiQIS consists of data-driven quality improvement (DDQI), Run-to-Run (R2R) control, local control, and multivariate statistical process control (MSPC). The main features of HiQIS are: 1) to build a statistical quality model, 2) to analyze the cause of quality variation, 3) to select a few variables to be manipulated, 4) to optimize the operating condition, and 5) to realize the desired quality even if there is modeling error and disturbances. A typical problem encountered in real applications is product quality variation, which occurs even if operators attempt to keep operating conditions at constant. In addition, from the practical viewpoint, it is difficult to change many operating condition variables simultaneously. Therefore, in the present work, quality variation analysis and manipulated variables selection are mainly focused on. The usefulness of HiQIS and the proposed methods are demonstrated through a case study.

Product quality improvement using multivariate data analysis
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno
IFAC Proceedings Volumes (IFAC-PapersOnline), 16, 175, 180, 2005年, ［査読有り］
研究論文（国際会議プロシーディングス）, A data-based methodology for improving product quality is proposed. Referred to as Data-Driven Quality Improvement (DDQI), the proposed method can cope with qualitative as well as quantitative variables, determine the operating conditions that can achieve the desired product quality, optimize operating condition under various constraints, and thus can provide useful information to improve product quality. This paper aims to formulate DDQI and demonstrate its usefulness with an case study of an industrial steel process. in addition, possible extensions and remaining problems are discussed based on the authors' experience of succeeding in improving product quality by applying DDQI to several industrial processes. Copyright © 2005 IFAC.

Data-driven quality improvement: Handling qualitative variables　　　　　　　　　　　　　　　
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno
IFAC Proceedings Volumes (IFAC-PapersOnline), 37, 9, 565, 570, IFAC Secretariat, 2004年
英語, 研究論文（国際会議プロシーディングス）, A data-based methodology for improving product quality is proposed. Referred to as Data-Driven Quality Improvement (DDQI), the proposed method can cope with qualitative as well as quantitative variables, determine the operating conditions that can achieve the desired product quality, optimize operating condition under constraints, and also evaluate the validity of the results. The desired yield is specified instead of the quality for a qualitative quality variable. This paper aims to formulate DDQI and demonstrate its usefulness with an illustrative example. In addition, possible extensions and remaining problems are discussed based on the authors' experience of suceeding in improving product quality by applying DDQI to several industrial processes.

Adlayers of C₆₀-C₆₀ and C₆₀-C ₇₀ Fullerene Dimers Formed on Au(111) in Benzene Solutions Studied by STM and LEED
Matsumoto, M., Inukai, J., Tsutsumi, E., Yoshimoto, S., Itaya, K., Ito, O., Fujiwara, K., Murata, M., Murata, Y., Komatsu, K.
Langmuir, 20, 4, 2004年
研究論文（学術雑誌）

Mechanochemical synthesis of a novel C₆₀ dimer connected by a silicon bridge and a single bond
Fujiwara, K., Komatsu, K.
Organic Letters, 4, 6, 2002年
研究論文（学術雑誌）

Structural analysis of C₆₀ trimers by direct observation with scanning tunneling microscopy
Kunitake, M., Uemura, S., Ito, O., Fujiwara, K., Murata, Y., Komatsu, K.
Angewandte Chemie - International Edition, 41, 6, 2002年
研究論文（学術雑誌）

Direct observation of localized excitation in the lowest excited triplet state of fullerene dimers C₁₂₀ and C₁₂₀O by means of time-resolved electron paramagnetic resonance
Yamauchi, S., Funayama, T., Ohba, Y., Paul, P., Reed, C.A., Fujiwara, K., Komatsu, K.
Chemical Physics Letters, 363, 3-4, 2002年
研究論文（学術雑誌）

Adlayers of fullerene monomer and [2 + 2]-type dimer on Au(111) in aqueous solution studied by in situ scanning tunneling microscopy
Yoshimoto, S., Narita, R., Tsutsumi, E., Matsumoto, M., Itaya, K., Ito, O., Fujiwara, K., Murata, Y., Komatsu, K.
Langmuir, 18, 22, 2002年
研究論文（学術雑誌）

Photophysical and photochemical properties of decakis-adduct of C₁₂₀ and related compounds
Fujitsuka, M., Fujiwara, K., Murata, Y., Ito, O., Komatsu, K.
Chemistry Letters, 5, 2002年
研究論文（学術雑誌）

A supramolecular oscillator composed of carbon nanocluster C₁₂₀ and a rhodium(III) porphyrin cyclic dimer
Tashiro, K., Hirabayashi, Y., Aida, T., Saigo, K., Fujiwara, K., Komatsu, K., Sakamoto, S., Yamaguchi, K.
Journal of the American Chemical Society, 124, 41, 2002年
研究論文（学術雑誌）

Properties of photoexcited states of C₁₈₀, a triangle trimer of C₆₀
Fujitsuka, M., Fujiwara, K., Murata, Y., Uemura, S., Kunitake, M., Ito, O., Komatsu, K.
Chemistry Letters, 5, 2001年
研究論文（学術雑誌）

First synthesis of a highly symmetrical decakis-adduct of fullerene dimer C₁₂₀
Fujiwara, K., Komatsu, K.
Chemical Communications, 1, 19, 2001年
研究論文（学術雑誌）

Positron lifetime in supramolecular gamma- and delta-cyclodextrin- C₆₀ and - C₇₀ compounds
S{\"u}vegh, K., Fujiwara, K., Komatsu, K., Marek, T., Ueda, T., V{\'e}rtes, A., Braun, T.
Chemical Physics Letters, 344, 3-4, 2001年
研究論文（学術雑誌）

Derivatization of fullerene dimer C₁₂₀by the Bingel reaction and a ³He NMR study of ³He@C₁₂₀ monoadducts
Fujiwara, K., Komatsu, K., Wang, G.-W., Tanaka, T., Hirata, K., Yamamoto, K., Saunders, M.
Journal of the American Chemical Society, 123, 43, 2001年
研究論文（学術雑誌）

The fullerene cross-dimer C₁₃₀: Synthesis and properties
Komatsu, K., Fujiwara, K., Murata, Y.
Chemical Communications, 17, 2000年
研究論文（学術雑誌）

The mechanochemical synthesis and properties of the fullerene trimer C₁₈₀
Komatsu, K., Fujiwara, K., Murata, Y.
Chemistry Letters, 9, 2000年
研究論文（学術雑誌）

Ultrafast energy relaxation dynamics of C₁₂₀, a [2+2]-bridged C₆₀ dimer
Cho, H.S., Kim, S.K., Kim, D., Fujiwara, K., Komatsu, K.
Journal of Physical Chemistry A, 104, 43, 2000年
研究論文（学術雑誌）

Fullerene dimer C₁₂₀ and related carbon allotropes
Komatsu, K., Fujiwara, K., Tanaka, T., Murata, Y.
Carbon, 38, 11, 2000年
研究論文（学術雑誌）

Solid-state mechanochemical reaction of fullerene C₆₀
Komatsu, K., Murata, Y., Wang, G.-W., Tanaka, T., Kato, N., Fujiwara, K.
Fullerene Science and Technology, 7, 4, 1999年
研究論文（学術雑誌）

Aqueous solubilization of crystalline fullerenes by supramolecular complexation with y-cyclodextrin and sulfocalix[8]arene under mechanochemical high-speed vibration milling
Komatsu, K., Fujiwara, K., Murata, Y., Braun, T.
Journal of the Chemical Society - Perkin Transactions 1, 20, 1999年
研究論文（学術雑誌）

Solid-state [4 + 2] cycloaddition of fullerene C₆₀ with condensed aromatics using a high-speed vibration milling technique
Murata, Y., Karo, N., Fujiwara, K., Komatsu, K.
Journal of Organic Chemistry, 64, 10, 1999年
研究論文（学術雑誌）

Mechanochemical synthesis and characterization of the fullerene dimer C₁₂₀
Komatsu, K., Wang, G.-W., Murata, Y., Tanaka, T., Fujiwara, K., Yamamoto, K., Saunders, M.
Journal of Organic Chemistry, 63, 25, 1998年
研究論文（学術雑誌）

Synthesis of a propargyl alcohol having a C₆₀ cage, its transformation into C₆₀ derivatives with polar functional groups, and the solubility measurements
Fujiwara, K., Murata, Y., Wan, T.S.M., Komatsu, K.
Tetrahedron, 54, 10, 1998年
研究論文（学術雑誌）

Sensitive Detection of Viral Antigens With A New Method, “Laser Magnet Immunoassay”
Mizutani, H., Suzuki, M., Mizutani, H., Fujiwara, K., Shibata, S., Arishima, K., Hoshino, M., Ushijima, H., Honma, H., KitamurA, T.
Microbiology and Immunology, 35, 9, 1991年
研究論文（学術雑誌）

Electron Microscopic Studies of Viruses Labeled with Magnetite
Mizutani, H., Mizutani, H., Nozaki, K., Fujiwara, K.
Microbiology and Immunology, 33, 7, 1989年
研究論文（学術雑誌）

Olfactory Response in the Yellowtail Seriola quinqueradiata
Kobayashi, H., Fujiwara, K.
NIPPON SUISAN GAKKAISHI, 53, 10, 1987年
研究論文（学術雑誌）

レム睡眠行動障害患者が有する起立性低血圧の重症度を心拍変動指標に基づいて分類する機械学習モデルの開発
小枝正汰, 藤原幸一, 角幸頼, 角谷寛, 日本生体医工学会大会プログラム・抄録集(Web), 63rd, 2024年

孤発性レム睡眠行動障害における起立時自律神経反応と長期予後の関連
角幸頼, 小枝正汰, 藤原幸一, 尾関祐二, 角谷寛, 日本睡眠学会定期学術集会プログラム・抄録集, 48th, 2024年

生体信号処理を活用した医療AI
藤原幸一, 中西俊之, 計測と制御, 63, 6, 342, 348, 2024年, ［招待有り］, ［筆頭著者, 責任著者］
日本語, 記事・総説・解説・論説等（学術雑誌）

レム睡眠行動障害におけるデルタ・ガンマ帯域パワー値の増大は夢内容行動化と関連する　　　　　　　　　　　　　　　
伊達 俊坪, 藤原 幸一, 角 幸頼, 角谷 寛, 今井 眞, 小川 景子, 日本睡眠学会定期学術集会プログラム・抄録集, 47回, 241, 241, 2022年06月
(一社)日本睡眠学会, 日本語

埋込サイボーグ技術の社会実装に係る技術・ 社会的課題
藤原幸一, 藤田卓仙, 山川俊貴, 久保孝富, 日永田智絵, 桐山瑶子, 川島浩誉, 川治徹真, 野田隼人, 田畑淳, 人工知能, 36, 6, 674, 683, 2021年11月, ［招待有り］, ［筆頭著者, 責任著者］
日本語, 31644670

睡眠脳波に基づく日中の疲労と眠気の鑑別に関する調査　　　　　　　　　　　　　　　
藤原 幸一, 後藤 有貴, 角 幸頼, 加納 学, 角谷 寛, 日本睡眠学会定期学術集会プログラム・抄録集, 46回, 211, 211, 2021年09月
(一社)日本睡眠学会, 日本語

SST-RUSを用いた睡眠脳波解析による異なる音環境下でのスピンドル出現の評価　　　　　　　　　　　　　　　
小枝 正汰, 藤原 幸一, 木下 貴文, 角 幸頼, 角谷 寛, 山木 清志, 森島 守人, 川嶋 隆宏, 日本睡眠学会定期学術集会プログラム・抄録集, 46回, 214, 214, 2021年09月
(一社)日本睡眠学会, 日本語

畳み込みニューラルネットワークを用いた睡眠時無呼吸症候群スクリーニング　　　　　　　　　　　　　　　
王 歩雲, 岩崎 絢子, 藤原 幸一, 永元 哲治, 角 幸頼, 加納 学, 井関 邦敏, 名嘉村 博, 角谷 寛, 日本睡眠学会定期学術集会プログラム・抄録集, 46回, 221, 221, 2021年09月
(一社)日本睡眠学会, 日本語

心拍変動のAI解析に基づく焦点起始両側強直間代発作検知アルゴリズムの検討
芹野 真郷, 宮島 美穂, 藤原 幸一, 鈴木 陽子, 加納 学, 稲次 基希, 橋本 聡華, 中里 信和, 神 一敬, 星田 徹, 澤井 康子, 渡辺 裕貴, 山本 信二, 岩崎 真樹, 前原 健寿, てんかん研究, 39, 2, 399, 399, 2021年07月
(一社)日本てんかん学会, 日本語

レム睡眠行動障害研究の進歩 レム睡眠行動障害の自律神経障害
角 幸頼, 松尾 雅博, 尾関 祐二, 仲山 千佳夫, 藤原 幸一, 角谷 寛, 臨床神経生理学, 48, 5, 401, 401, 2020年10月
(一社)日本臨床神経生理学会, 日本語

レム睡眠行動障害研究の進歩 レム睡眠行動障害の自律神経障害
角 幸頼, 松尾 雅博, 尾関 祐二, 仲山 千佳夫, 藤原 幸一, 角谷 寛, 臨床神経生理学, 48, 5, 401, 401, 2020年10月
(一社)日本臨床神経生理学会, 日本語

シンクロスクイージングウェーブレット変換とRUSBoostの融合による睡眠紡錘波検出アルゴリズムの開発
藤原幸一, 木下貴文, 角幸頼, 松尾雅博, 小川景子, 加納学, 角谷寛, 人工知能学会全国大会(Web), 34th, 0, 1M4GS1301, 1M4GS1301, 2020年

睡眠紡錘波（スピンドル）は，睡眠医学における重要な脳波（EEG）波形であるが，目視でスピンドルを検出することは専門技師でも労力を要するため，自動化が求められている．これまでスピンドル波形との類似度によるテンプレートマッチングや，機械学習を用いた手法が提案されている．前者は個人ごとに類似度の閾値を調整する必要があり，後者はEEGデータ全体と比較しスピンドルが少ないため，学習データが不均衡となる．そこで本研究では，ウェーブレットシンクロスクイズド変換（SST）とRUSBoostを組み合わせたスピンドル検出方法を提案する．SSTはスピンドル波形の特徴を抽出するのに適した時間周波数解析手法で，RUSBoostは不均衡データに対処するための機械学習手法である．提案するSST-RUSは，RUSBoostによって不均衡データの問題に対応でき，識別に弱分類器の多数決を使用するため閾値調整が必要ない．提案法をオーブンデータを用いて検証したところ，感度77.8%，陽性的中率73.5%を達成した．提案するSST-RUSは技師の目視によるスピンドル検出の負担を軽減できる可能性がある．

, 一般社団法人 人工知能学会, 日本語

心拍変動解析を用いたCPAPの自律神経活動への短期的効果の検証　　　　　　　　　　　　　　　
仲山 千佳夫, 藤原 幸一, 松尾 雅博, 加納 学, 角谷 寛, 日本睡眠学会定期学術集会プログラム・抄録集, 44回, 220, 220, 2019年06月
(一社)日本睡眠学会, 日本語

ウェーブレット・シンクロスクイージング変換とランダムアンダーサンプリングによる高精度睡眠紡錘波検出アルゴリズムの開発　　　　　　　　　　　　　　　
藤原 幸一, 木下 貴文, 角 幸頼, 松尾 雅博, 角谷 寛, 加納 学, 日本睡眠学会定期学術集会プログラム・抄録集, 44回, 279, 279, 2019年06月
(一社)日本睡眠学会, 日本語

サポートベクターマシンに基づいた変数重要度による手首アクチグラフによる週末の寝だめ有無の推定および要因検討　　　　　　　　　　　　　　　
後藤 有貴, 藤原 幸一, 角 幸頼, 松尾 雅博, 加納 学, 角谷 寛, 日本睡眠学会定期学術集会プログラム・抄録集, 44回, 284, 284, 2019年06月
(一社)日本睡眠学会, 日本語

てんかん発作検知・予知に関する最新の研究動向　　　　　　　　　　　　　　　
宮島 美穂, 藤原 幸一, 山川 俊貴, クリニシアン, 66, 637, 40, 45, 2019年05月, ［査読有り］
日本語

Analysis of VNS Effect on EEG Connectivity with Granger Causality and Graph Theory
Tsuyoshi Uchida, Koichi Fujiwara, Takao Inoue, Yuichi Maruta, Manabu Kano, Michiyasu Suzuki, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings, 861, 864, 2019年03月04日, ［査読有り］
© 2018 APSIPA organization. Vagus Nerve Stimulation (VNS) is treatment of refractory epilepsy; however, its physiological mechanism has not been fully understood. The effectiveness of VNS for each patient cannot be predicted preoperatively. Thus, the mechanism of VNS needs to be investigated in order to avoid ineffective operations. Because an epileptic seizure is caused by the spread of excessive discharge from neurons in the cerebrum, analyzing effects of VNS on electroencephalogram (EEG) would be useful for VNS mechanism investigation. In the present work, the EEG data of epileptic patients with VNS were analyzed by using Granger Causality (GC) and the graph theory. Since GC is an index which expresses the intensity of a causal relation between two time series, it may illustrate information interactions between EEG channels. In addition, a directed graph constructed from those GC values would express neural connection. The analysis was carried out with the EEG data of two patients with frontal lobe epilepsy receiving the VNS therapy. The result supported the existing hypothesis indicating the bilateral asymmetry of the VNS effect on the brain, and furthermore, it suggested that VNS would increase neural connection between the frontal lobe and other brain regions, and that should control epileptic seizures by keeping patients awake.

長期短期記憶と心拍変動に基づく睡眠時無呼吸症候群のスクリーニング
岩崎 絢子, 仲山 千佳夫, 藤原 幸一, 角 幸頼, 松尾 雅博, 加納 学, 角谷 寛, 人工知能学会全国大会論文集, 2019, 0, 1H4J1303, 1H4J1303, 2019年

睡眠時無呼吸症候群 (SAS) は, 睡眠中に呼吸の停止あるいは呼吸量の減少が頻回に起こる疾患であり, 日中の眠気などの症状を引き起こすほか, 心血管系の合併症のリスクを高める. しかし, 自覚症状に乏しいケースも存在することから, 診断および治療に至っていない患者が多く存在すると考えられている. SAS の診断には終夜睡眠ポリグラフ検査 (PSG) が用いられるが, PSG を実施できる施設が少ないことが問題となっていた. そこで本研究では, 心拍変動解析と長期短期記憶を組み合わせた簡便なスクリーニング手法を提案する. SAS 患者および健常者計 59 名のデータに対して提案法を適用したところ, 感度 100%, 特異度 100% で SAS のスクリーニングが可能であることが判明した.

, 一般社団法人 人工知能学会, 日本語

睡眠時無呼吸症候群患者における多変量統計的プロセス管理と心拍変動解析を用いた持続陽圧呼吸療法の自律神経活動への短期的効果の検証　　　　　　　　　　　　　　　
仲山 千佳夫, 藤原 幸一, 松尾 雅博, 角谷 寛, 加納 学, 日本睡眠学会定期学術集会プログラム・抄録集, 43回, 200, 200, 2018年07月
(一社)日本睡眠学会, 日本語

Causal analysis based on non-time-series kernel Granger causality in a steelmaking process
Sato R, Fujiwara K, Tani M, Mori J, Ise J, Harada K, Kano M, 2017 Asian Control Conference, ASCC 2017, 2018-January, 1778, 1782, 2018年02月07日, ［査読有り］
© 2017 IEEE. In the manufacturing industry, it is extremely important to identify variables that affect product quality. Identifying variables which affect quality variables is called causal analysis. In batch processes, time-series data of process variables and the corresponding data of quality variables are generally acquired. Since causal analysis using the raw data needs a large computation load, it is often performed after compressing time-series process variables data into non-time-series feature variables data. Various causal analysis methods using such data have been developed, however, none have shown effective results in actual plants. In the present work, non-time-series kernel Granger causality (NTS-KGC) is proposed for causal analysis with non-time-series data of batch processes. This is a method that kernel Granger causality [1], which is used for causal analysis with time-series data in nonlinear systems, is expanded for causal analysis with non-time-series data. The validity of the proposed method is demonstrated through a numerical example of a nonlinear batch process. In addition, we conducted a case study of applying NTS-KGC to data obtained from a real steelmaking process. The results demonstrate that NTS-KGC is superior to other existing methods using the following indexes, i.e. variable influence on projection (VIP) of partial least squares (PLS), regression coefficients of PLS, and variable importance of Random Forest., 英語

心拍数変動解析と多変量統計的プロセス管理を用いたウェアラブルてんかん発作予知システムの開発
山川 俊貴, 宮島 美穂, 藤原 幸一, 加納 学, 鈴木 陽子, 渡辺 裕貴, 渡邊 さつき, 村田 佳子, 星田 徹, 前原 健寿, てんかん研究, 35, 3, 730, 730, 2018年01月, ［査読有り］
(一社)日本てんかん学会, 日本語

ウェアラブルデバイスとスマートフォンを用いたてんかん発作予知技術
藤原 幸一, 宮島 美穂, 山川 俊貴, Epilepsy: てんかんの総合学術誌, 11, 2, 75, 81, 2017年11月
メディカルレビュー社, 日本語

ヘルスモニタリングのための心拍変動解析
藤原 幸一, システム/制御/情報, 61, 9, 381, 386, 2017年09月, ［査読有り］, ［招待有り］
日本語

多変量統計的プロセス管理と心拍変動解析を用いたてんかん発作予知技術の開発
藤原幸一, 宮島美穂, 鈴木陽子, 山川俊貴, 加納学, 計測と制御, 56, 7, 526, 529, 2017年07月, ［査読有り］, ［招待有り］
日本語

ソフトセンサー構築支援ツールの開発
金子弘昌, 金尚弘, 藤原幸一, 化学工学, 80, 12, 773, 775, 2016年12月, ［招待有り］
化学工学会, 日本語

10年後の看 -ウェアラブデバイスが拓くヘルスモニタサービス-
藤原 幸一, 化学工学,, 80, 2, 91, 95, 2016年02月, ［招待有り］
化学工学会, 日本語

てんかんの心臓自律神経モニタリング 心拍変動モニタリングによるてんかん発作早期検出の試み　　　　　　　　　　　　　　　
宮島 美穂, 藤原 幸一, 山川 俊貴, 笹井 妙子, 加納 学, 前原 健寿, 笹野 哲郎, 太田 克也, 松浦 雅人, 松島 英介, 臨床神経生理学, 43, 5, 337, 337, 2015年10月
(一社)日本臨床神経生理学会, 日本語

てんかんの心臓自律神経モニタリング ウェアラブルな心拍変動モニタリングシステムの開発　　　　　　　　　　　　　　　
山川 俊貴, 宮島 美穂, 藤原 幸一, 阿部 恵理花, 鈴木 陽子, 澤田 由梨子, 加納 学, 渡辺 裕貴, 前原 健寿, 臨床神経生理学, 43, 5, 337, 337, 2015年10月, ［査読有り］
(一社)日本臨床神経生理学会, 日本語

音楽による気分変化と、その生理指標変化
松尾 雅博, 増田 史, 角 幸頼, 藤原 幸一, 森島 守人, 山木 清志, 山田 尚登, 角谷 寛, 臨床神経生理学, 43, 5, 445, 445, 2015年10月
(一社)日本臨床神経生理学会, 日本語

Efficient wavenumber selection based on nearest correlation Louvain method for NIR calibration modeling
Taku Uchimaru, Koji Hazama, Koichi Fujiwara, Manabu Kano, 2015 10th Asian Control Conference: Emerging Control Techniques for a Sustainable World, ASCC 2015, 2015年09月08日, ［査読有り］
© 2015 IEEE.In process analytical technology (PAT), partial least squares (PLS) regression has been widely used to construct calibration models for near-infrared (NIR) spectroscopy. To construct a highly accurate calibration model, wavenumber selection is crucial. In the present work, an efficient wavenumber selection method especially for PLS is proposed. The proposed method is referred to as nearest correlation Louvain method-based variable selection (NCLM-VS). NCLM-VS is a correlation-based group-wise method; it constructs an affinity matrix of input variables by the nearest correlation (NC) method, partitions the affinity matrix by the Louvain method (LM), consequently clusters input variables into multiple variable groups, and finally selects variable groups according to their contribution to estimates. LM is very fast and optimizes the number of groups automatically unlike spectral clustering (SC). The advantage of NCLM-VS over conventional methods including nearest correlation spectral clustering-based method (NCSC-VS) is demonstrated through their applications to calibration modeling based on near-infrared (NIR) spectra. In particular, it is confirmed that NCLM-VS is significantly faster than NCSC-VS while NCLM-VS can achieve as good estimation performance as NCSC-VS.

Calibration model design based on weighted nearest correlation spectral clustering
Koichi Fujiwara, Manabu Kano, 2015 10th Asian Control Conference: Emerging Control Techniques for a Sustainable World, ASCC 2015, 2015年09月08日, ［査読有り］
© 2015 IEEE.Calibration models have been widely used for estimating product quality or other key variables with near-infrared spectroscopy (NIRS), and it is important to select appropriate input variables (wavelengths) for building a highly accurate calibration model. A novel input variable selection method based on nearest correlation spectral clustering (NCSC), which is a correlation-based clustering method, was proposed, and it is referred to as NCSC-based variable selection (NCSC-VS). In NCSC-VS, some variable groups are clustered by NCSC, and a few variable groups are selected by their contribution to estimates. Although variable selection performance of NCSC-VS depends on variable group clustering by NCSC, its clustering results easily fluctuate according to measurement noise. The present work proposes an improved version of NCSC that can cope with measurement noise by introducing a weighting function into affinity matrix construction. In addition, the proposed clustering method, referred to as weighted NCSC (WNCSC), is applied to variable selection in calibration model design. WNCSC-VS can achieve a higher estimation performance than NCSC-VS. The usefulness of the proposed WNCSC-VS is demonstrated through an application to calibration model design for a pharmaceutical process.

One Class SVMを用いたてんかん発作兆候監視アルゴリズムの開発
藤原幸一, 鈴木陽子, 宮島美穂, 山川俊貴, 加納学, 自動制御連合講演会(CD-ROM), 57th, ROMBUNNO.2D08-2, 1570, 2014年11月10日
てんかん患者は，てんかん発作によって事故を起こしたり怪我を負うことがあるが，発作起始前にアラームを発報できれば，患者は身を守ることができると期待される．一方，心拍間隔は自然にゆらぎがあり，これを心拍変動（HRV）と呼ぶが，てんかん発作はHRVに影響するため，HRVを解析することで発作兆候を検出できる可能性がある．そこで本研究は，HRVと異常検出手法であるOne Class SVMに基づいたてんかん発作兆候監視アルゴリズムを提案する．提案法を臨床データに適用した結果，発作起始の1分前に発作兆候を検出することができた．, 自動制御連合講演会, 日本語

Epileptic seizure monitoring by One-Class Support Vector Machine
Koichi Fujiwara, Erika Abe, Yoko Suzuki, Miho Miyajima, Toshitaka Yamakawa, Manabu Kano, Taketoshi Maehara, Katsuya Ohta, Tetsuo Sasano, 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014, 2014年02月12日, ［査読有り］
© 2014 Asia-Pacific Signal and Information Processing Ass. Although refractory epileptic patients suffer from uncontrolled seizures, their quality of life (QoL) may be improved if the seizure can be predicted in advance. On the hypothesis that the excessive neuronal activity of epilepsy affects the autonomie nervous system and the fluctuation of the R-R interval (RRI) of an electrocardiogram (ECG), called heart rate variability (HRV), reflects the autonomie nervous function, there is possibility that an epileptic seizure can be predicted through monitoring RRI data. The present work proposes an HRV-based epileptic seizure monitoring method by utilizing One Class Support Vector Machine (OCSVM). Various HRV features are derived from the RRI data in both the interictal period and the preictal period, and an OCSVM-based seizure prediction model is built from the interictal HRV features. The application results of the proposed monitoring method to a clinical data are reported.

Real-time heart rate variability monitoring employing a wearable telemeter and a smartphone
Toshitaka Yamakawa, Toshitaka Yamakawa, Koichi Fujiwara, Miho Miyajima, Erika Abe, Manabu Kano, Yuichi Ueda, 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014, 2014年02月12日, ［査読有り］
© 2014 Asia-Pacific Signal and Information Processing Ass. A telemetry system for the measurement of heart rate variability (HRV) has been developed with a low-cost manufacturing process and a low-power consumption design. All the components and functions for the RRI measurement were implemented on a wearable telemeter which can operate for up to 10 hours with a rechargeable Li-Polymer battery, and the RRI data is stored into a smartphone via a Bluetooth wireless transmission. In a long-term measurement of a young subject that extended over 48 hours in total, the results showed a 1% probability of recurring errors. The obtained results suggest that the proposed fully-wearable system enables the continuous monitoring of HRV for both clinical care and healthcare operated by a non-expert.

心拍変動解析と多変量統計的プロセス管理によるドライバの眠気検出
阿部恵里花, 藤原幸一, 平岡敏洋, 山川俊貴, 加納学, 人間工学, 50, 2014年
日本語

Analysis of Changes in HRV of Epileptic Patients in Preictal Period
Hashimoto Hirotsugu, Fujiwara Koichi, Suzuki Yoko, Miyajima Miho, Yamakawa Toshitaka, Kano Manabu, Maehara Taketoshi, Matsuura Masato, 生体医工学, 51, R, 198-R-198, 2013年07月, ［査読有り］
Japanese Society for Medical and Biological Engineering, 英語

Development of a wearable HRV telemetry system to be operated by non-experts in daily life
Toshitaka Yamakawa, Toshitaka Yamakawa, Toshitaka Yamakawa, Koichi Fujiwara, Manabu Kano, Miho Miyajima, Yoko Suzuki, Taketoshi Maehara, Katsuya Ohta, Tetsuo Sasano, Masato Matsuura, Eisuke Matsushima, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013, 2013年, ［査読有り］
A telemetry system for the measurement of heart rate variability (HRV) with automatic gain control has been developed with a low-cost manufacturing process and a low-power consumption design. The proposed automatic gain control technique provided highly reliable RR interval (RRI) detection for subjects of different ages, and enabled the subjects to use the system without any expert knowledge of the electrocardiogram (ECG) measurement. All the components and functions for the RRI measurement were implemented on a wearable telemeter which can operate for up to 440 h with a CR2032 coin battery, and the wirelessly transmitted RRI data is stored into a PC by a receiver via a USB connection. The errors of the RRI detection occurred at less than 2% probability in subjects of five different ages. In a long-term measurement of a young subject that extended over 48 h, the results showed a 0.752% probability of recurring errors. The obtained results suggest that the proposed system enables the long-term monitoring of HRV for both clinical care and healthcare operated by a non-expert. © 2013 APSIPA., 英語

Heart rate variability features for epilepsy seizure prediction
Hirotsugu Hashimoto, Koichi Fujiwara, Yoko Suzuki, Miho Miyajima, Toshitaka Yamakawa, Manabu Kano, Taketoshi Maehara, Katsuya Ohta, Tetsuo Sasano, Masato Matsuura, Eisuke Matsushima, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013, 2013年, ［査読有り］
Although refractory epileptic patients suffer from uncontrolled seizures, their quality of life (QoL) may be improved if an epileptic seizure can be predicted in advance. In the preictal period, an excessive neuronal activity of epilepsy affects the autonomic nerve system. Since the fluctuation of the R-R interval (RRI) of an electrocardiogram (ECG), called heart rate variability (HRV), reflects the autonomic nervous function, an epileptic seizure may be predicted through monitoring HRV data of an epileptic patient. In the present work, preictal and interictal HRV data of epileptic patients were analyzed for developing an epilepsy seizure prediction system. The HRV data of five patients were collected, and their HRV features were calculated. The analysis results showed that frequency HRV features, such as LF and LF/HF, changed at least one minute before seizure onset in all seizure episodes. The possibility of realizing a HRV-based seizure prediction system was shown through these analysis. © 2013 APSIPA.

Feature extraction of heart rate variability for epileptic seizure
Suzuki Y, Hashimoto H, Fujiwara K, Miyajima M, Yamakawa T, Kano M, Maehara T, Ohta K, Sasano T, Matsuura M, Matsushima E, Proceedings of the SICE Annual Conference, 1713, 1715, 2013年, ［査読有り］
Although refractory epileptic patients suffer from uncontrolled seizures, their quality of life may be improved if an epileptic seizure can be predicted in advance. In the preictal period, an excessive neuronal activity of epilepsy affects the autonomic nervous system. Since heart rate variability (HRV) reflects the autonomic nervous function, an epileptic seizure may be predicted through monitoring HRV data of an epileptic patient. In the present study, preictal HRV data of epileptic patients were analyzed for developing an epilepsy seizure prediction system. The preictal HRV data of nine epileptic seizure episodes of four patients were collected, and their HRV indexes were calculated. The analysis results showed that frequency HRV indexes changed at least one minute before seizure onset in all seizure episodes. The possibility of realizing a HRV-based seizure prediction system was shown., 英語

Efficient input variable selection for calibration model design
Koichi Fujiwara, Manabu Kano, 2013 9th Asian Control Conference, ASCC 2013, 2013年, ［査読有り］
In pharmaceutical processes, near-infrared spec-troscopy (NIRS) is a key tool of process analytical technology (PAT), and very accurate calibration models need to be developed with NIR spectra. Partial least squares (PLS) regression, in particular, is accepted as a useful technique for calibration model design. When a calibration model is built, appropriate input variables have to be selected to achieve high estimation performance. Recently, a new methodology for selecting input variables based on nearest correlation spectral clustering (NCSC) has been proposed. Referred to as NCSC-based variable selection (NCSC-VS), it clusters input variables into some variable groups based on the correlation by using NCSC, and selects a few variable groups according to their contribution to output estimates. We report here an industrial application of NCSC-VS to calibration model design for a pharmaceutical process. NCSC-VS can select important variables and improve the estimation performance greatly in comparison to conventional variable selection methods. © 2013 IEEE., 英語

局所PLSを用いた多品種バッチプロセスの製品品質推定
北川裕一, 河野浩司, 真子秀樹, 藤原幸一, 加納学, 長谷部伸治, 化学工学会秋季大会研究発表講演要旨集(CD-ROM), 42nd, ROMBUNNO.B121, 41, 2010年08月06日
公益社団法人 化学工学会, 日本語

変数間の相関関係に基づいたクラスタリング手法の開発とソフトセンサへの応用
藤原幸一, 加納学, 長谷部伸治, 化学工学会秋季大会研究発表講演要旨集(CD-ROM), 41st, S201, 574, 2009年08月16日
公益社団法人 化学工学会, 日本語

Correlation-based pattern recognition and its application to adaptive soft-sensor design
Koichi Fujiwara, Manabu Kano, Shinji Hasebe, IFAC Proceedings Volumes (IFAC-PapersOnline), 7, PART 1, 661, 666, 2009年, ［査読有り］
Although soft-sensors have been widely used for estimating product quality or other key variables, they do not always function well in practice due to changes in process characteristics. The Correlation-based Just-In-Time (CoJIT) modeling has been proposed to cope with changes in process characteristics. In the CoJIT modeling, the samples used for local modeling are selected on the basis of correlation together with distance, since changes in process characteristics are expressed as the difference of the correlation. In addition, the individuality of production devices should be considered when they are operated in parallel. However, the CoJIT modeling cannot cope with the individuality of production devices because it is only applicable to time-series data. In the present work, a new pattern recognition method, referred to as the Nearest Correlation (NC) method is proposed, and it selects samples whose correlations are similar to the query. In addition, the proposed NC method is integrated with the CoJIT modeling. The advantages of the proposed CoJIT modeling with the NC method are demonstrated through a case study of a parallelized CSTR process., 英語

変数間の相関に着目したクラスタリング手法およびその多変量統計モデリングへの利用
向井洋介, 藤原幸一, 加納学, 長谷部伸治, 化学工学会秋季大会研究発表講演要旨集(CD-ROM), 40th, K302, 499, 2008年08月24日
公益社団法人 化学工学会, 日本語

相関型Just‐In‐Timeモデリングの化学プロセスへの適用
藤原幸一, 加納学, 長谷部伸治, 滝波明敏, システム制御情報学会研究発表講演会講演論文集(CD-ROM), 52nd, 677, 678, 2008年05月16日
日本語

プロセス特性変化に着目した相関型Just‐In‐Timeモデリングによるソフトセンサ設計
藤原幸一, 加納学, 長谷部伸治, 化学工学会年会研究発表講演要旨集, 73rd, 270, 277, 2008年02月17日
公益社団法人 化学工学会, 日本語

Development of a new pattern recognition method and its application to just-in-time modeling
Koichi Fujiwara, Yosuke Mukai, Manabu Kano, Shinji Hasebe, AIChE Annual Meeting, Conference Proceedings, 688b, 2008年, ［査読有り］
英語

Correlation-Based Just-In-Time Modeling for Soft-Sensor Design
Koichi Fujiwara, Manabu Kano, Shinji Hasebe, 18TH EUROPEAN SYMPOSIUM ON COMPUTER AIDED PROCESS ENGINEERING, 25, 471, 476, 2008年, ［査読有り］
Soft-sensors are widely used for estimating product quality or other key variables when on-line analyzers are not available. However their estimation performance deteriorates when the process characteristics change. To cope with such changes and update the model, recursive methods such as recursive PLS and Just-In-Time (JIT) modeling have been developed. When process characteristics change abruptly, however, they do not always function well. In the present work, a new method for constructing soft-sensors based on a JIT modeling technique is proposed. In the proposed method, referred to as correlation-based JIT modeling, the samples used for local modeling are selected on the basis of the correlation among variables instead of or together with distance. The proposed method can adapt a model to changes in process characteristics and also cope with process nonlinearity. The superiority of the proposed method over the conventional methods is demonstrated through a case study of a CSTR process in which catalyst deactivation and recovery are considered as changes in process characteristics., ELSEVIER SCIENCE BV, 英語

Modeling and optimization of batch process through wavelet analysis and multivariate analysis
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno, IFAC Proceedings Volumes (IFAC-PapersOnline), 40, 5, 99, 104, 2007年, ［査読有り］
© Copyright 2007 IFAC. An efficient method is developed to build a batch process model and optimize its operating conditions including time-dependent operation profiles. In the proposed method, referred to as wavelet regression and optimization (WRO), important wavelet coefficients of operation profiles are selected as input variables of a statistical model, and then further dimensionality reduction is achieved through multivariate analysis. Then, on the basis of the developed model, optimal operation profiles are derived through wavelet reconstruction. In addition, WRO is integrated with an indicator variable technique for trajectory alignment. A case study of lysine production based on a semi-batch fermentation process demonstrates the superiority of the proposed method over the conventional multiway method., 英語

ウェーブレット解析と多変量解析を用いたバッチプロセス操作プロファイルの最適化
藤原幸一, 加納学, 長谷部伸治, 大野弘, 化学工学会秋季大会研究発表講演要旨集(CD-ROM), 38th, S125, 820, 2006年08月16日
公益社団法人 化学工学会, 日本語

Operation profile optimization for batch process through wavelet analysis and multivariate analysis
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno, 2006 SICE-ICASE INTERNATIONAL JOINT CONFERENCE, VOLS 1-13, 2810, +, 2006年, ［査読有り］
A new regression method, wavelet coefficient regression (WCR), based on wavelet analysis and multivariate analysis is proposed. It can build a statistical model that relates operation profiles with product quality in a batch process. In WCR, selected wavelet coefficients of operation profiles are used as input variables of a statistical model; thus time-related information such as timing of manipulation can be successfully modeled. In addition, by integrating multivariate analysis and wavelet analysis, WCR can cope with correlation of input variables. As a result, WCR enables us to build an accurate statistical model of a batch process. On the basis of WCR, a data-driven method for improving product quality in a batch process is also proposed. The proposed method can determine operation profiles that can achieve the desired product quality and optimize the operation profiles under a given performance index and various constraints. The usefulness of the proposed WCR and profile optimization method is demonstrated through a case study of lysine production based on a semi-batch fermentation process., IEEE, 英語

統計的品質改善のための枠組み
加納学, 藤原幸一, 長谷部伸治, システム制御情報学会研究発表講演会講演論文集, 49th, 409, 410, 2005年05月18日
日本語

Data-Driven Approach for Improving Product Yield
Koichi Fujiwara, Manabu Kano, Shinji Hasebe, Hiromu Ohno, The 10th Asian Pacific Confederation of Chemical Engineering, 2004, 188, 188, 2004年, ［査読有り］
A data-driven methodology for improving product yield by integrating principal component analysis (PCA) and liner discriminant analysis (LDA) is proposed. Referred to as Data-Driven Quality Improvement (DDQI), the proposed method can cope with qualitative as well as quantitative quality variables, determine the operating conditions that can achieve the desired product quality, optimize the operating condition under various constraints, and also evaluate the validity of the results. The relationship between product quality and operating conditions can be modeled by PCR when quality variables are quantitative. On the other hand, LDA can be used for modeling when quality variables are qualitative, e.g., good or bad. For such a qualitative quality variable, the yield, that is the percentage of good products to all products, can be specified on the basis of histograms for given categories. The histograms can be obtained from operation data, and they can be drawn against the axis defined by LDA. Once the desired yield is specified, the operating condition that can achieve the desired yield can be determined. The usefulness of the proposed method is demonstrated through a case study., 公益社団法人 化学工学会, 英語

Data-driven approach for product quality/yield improvement: How to specify target of qualitative quality variables
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno, AIChE Annual Meeting, Conference Proceedings, 429c, 7727, 2004年, ［査読有り］
How can we improve product quality and yield? More than ever, the answer to this question is vital as product life cycles are getting shorter and international competition is getting keener. Since this question arises repeatedly when a new product is developed, quality improvement should be achieved faster and in a more systematic way. In the present work, a data-based methodology for improving product quality/yield is proposed. Referred to as Data-Driven Quality Improvement (DDQI), the proposed method can cope with qualitative as well as quantitative variables, determine the operating conditions that can achieve the desired product quality, optimize operating condition under constraints, and also evaluate the validity of the results. In DDQI, a space where operating conditions can achieve the desired quality is searched within subspace spanned by principal components. However, desired product quality cannot be specified quantitatively when the quality variable is qualitative, e.g., whether there is any defect on the surface of specialty sheet steel. For such a qualitative quality variable, yield, i.e., the percentage of good products to all products, can be specified instead of the quality itself. In the proposed method, the yield is defined on the basis of histograms for two categories such as good and bad. The histograms can be obtained from operation data, and they can be drawn against the axis defined by a discriminant function. Once the desired yield is specified, operating conditions that can achieve the desired yield can be easily found. This paper aims to formulate DDQI and demonstrate its usefulness with an illustrative example. In addition, possible extensions and remaining problems are discussed based on the authors' experience of succeeding in improving product quality by applying DDQI to several industrial processes., 英語

主成分回帰を用いた製品品質・歩留り改善のための最適運転条件推定法
藤原幸一, 加納学, 長谷部伸治, 大野弘, システム制御情報学会研究発表講演会講演論文集, 48th, 385, 386, 2004年
日本語

スモールデータ解析と機械学習
藤原, 幸一(工学)
オーム社, 2022年02月, 9784274227783, xi, 282p, 日本語

次世代医療AI : 生体信号を介した人とAIの融合
藤原, 幸一(工学), 久保, 孝富, 山川, 俊貴, 伊藤, 健史, 中野, 高志, 吉本, 潤一郎, 松尾, 剛行, 藤田, 卓仙, 桐山, 瑶子
コロナ社, 2021年07月, 9784339033816, x, 257p, 日本語

ウェアラブル心電計と経静脈的患者自己調節鎮痛法を用いた手術後の痛み増強を予測するAIの開発
中西 俊之, 藤原 幸一, 仙頭 佳起, 祖父江 和哉
人工知能学会全国大会論文集, 2023年, 一般社団法人 人工知能学会, 日本語
2023年 - 2023年, 痛みは主観的な感覚であるため，自己評価スケールで評価されてきた．しかし，自己評価スケールは時間的に連続評価ができず，意識レベル低下時や小児では実施が難しい．そのため，熱や電気刺激に対する生体信号の変化を痛みの正解データとして用いることで，痛みの客観化が試みられてきた．しかし，実験環境での解析結果をそのまま実際の患者に適応できるかどうかは明らかでない．我々は，患者自身が痛みの増強時に鎮痛剤を投与する経静脈的患者自己調節鎮痛法（IV-PCA）の使用記録から痛みの経時変化を推定できると考えた．本研究の目的は，ウェアラブル心電計とIV-PCAを用い，生体信号と機械学習により術後の痛みを連続的に評価し，その増強を予測することである．時系列性を考慮した異常検知モデルである自己注意機構付きオートエンコーダ（SA-AE）を採用し，心拍変動指標を入力特徴量に用いて痛み増強を予測するAIを構築した．IV-PCAの使用を痛みの増強と定義し，8人の術後患者において痛み増強の15分前にTPR 54%，FPR 1.76 回/hの性能で予測できた．今後，データを蓄積してモデルの性能を改善する．

Nearest Neighbor Search-Based Modification of RRI Data with Premature Atrial Contraction and Premature Ventricular Contraction　　　　　　　　　　　　　　　
Sifeng Chen, Shota Kato, Koichi Fujiwara, Manabu Kano
2023 SICE INTERNATIONAL SYMPOSIUM ON CONTROL SYSTEMS, SICE ISCS, 2023年, IEEE, 英語
2023年 - 2023年, Heart rate variability (HRV) analysis plays an essential role in healthcare. HRV features cannot be extracted accurately from the R-R interval (RRI) when RRI data contains artifacts. Previous research for modifying RRI data with artifacts considered premature atrial contraction (PAC) and premature ventricular contraction (PVC), which are the most common types of extrasystoles occurring every day in healthy persons. This research proposed three new RRI modification algorithms for PAC and PVC using nearest neighbor search (NNS) algorithms: k-nearest neighbors (KNN), clustering-KNN (CKNN), and approximate nearest neighbors (ANN). The present work demonstrated that the ANN-based RRI modification (ANN-RM) algorithm achieved lower root mean squared errors (RMSEs) than the CKNN-based RRI modification algorithm and the highest computational speed. The RMSEs of ANN-RM for PAC and PVC were 23.0 ms and 26.2 ms, respectively.

レム睡眠行動障害におけるデルタ・ガンマ帯域パワー値の増大は夢内容行動化と関連する　　　　　　　　　　　　　　　
伊達 俊坪, 藤原 幸一, 角 幸頼, 角谷 寛, 今井 眞, 小川 景子
日本睡眠学会定期学術集会プログラム・抄録集, 2022年06月, (一社)日本睡眠学会, 日本語
2022年06月 - 2022年06月

睡眠脳波に基づく日中の疲労と眠気の鑑別に関する調査　　　　　　　　　　　　　　　
藤原 幸一, 後藤 有貴, 角 幸頼, 加納 学, 角谷 寛
日本睡眠学会定期学術集会プログラム・抄録集, 2021年09月, (一社)日本睡眠学会, 日本語
2021年09月 - 2021年09月

SST-RUSを用いた睡眠脳波解析による異なる音環境下でのスピンドル出現の評価　　　　　　　　　　　　　　　
小枝 正汰, 藤原 幸一, 木下 貴文, 角 幸頼, 角谷 寛, 山木 清志, 森島 守人, 川嶋 隆宏
日本睡眠学会定期学術集会プログラム・抄録集, 2021年09月, (一社)日本睡眠学会, 日本語
2021年09月 - 2021年09月

畳み込みニューラルネットワークを用いた睡眠時無呼吸症候群スクリーニング　　　　　　　　　　　　　　　
王 歩雲, 岩崎 絢子, 藤原 幸一, 永元 哲治, 角 幸頼, 加納 学, 井関 邦敏, 名嘉村 博, 角谷 寛
日本睡眠学会定期学術集会プログラム・抄録集, 2021年09月, (一社)日本睡眠学会, 日本語
2021年09月 - 2021年09月

医学と工学の垣根を越えた医療AI開発　　　　　　　　　　　　　　　
藤原幸一
マイクロソフトDeep Learning Lab Healthcare Day 2021 ~医療 x AI への参入障壁を乗り越える~, 2021年02月20日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］

Preliminary Study Using Autoencoder for Early Detection of Heat Illness from Heart Rate Variability Obtained with Wearable Device.
Nao Inatsu, Aoi Noguchi, Koshi Ota, Koichi Fujiwara, Takatomi Kubo, Toshitaka Yamakawa
APSIPA ASC, 2021年
2021年 - 2021年

心拍変動のAI解析に基づく焦点起始両側強直間代発作検知アルゴリズムの検討　　　　　　　　　　　　　　　
芹野真郷, 宮島美穂, 藤原幸一, 鈴木陽子, 加納学, 稲次基希, 橋本聡華, 中里信和, 神一敬, 星田徹, 澤井康子, 渡辺裕貴, 山本信二, 岩崎真樹, 前原健寿
てんかん研究, 2021年
2021年 - 2021年

レム睡眠行動障害研究の進歩 レム睡眠行動障害の自律神経障害
角 幸頼, 松尾 雅博, 尾関 祐二, 仲山 千佳夫, 藤原 幸一, 角谷 寛
臨床神経生理学, 2020年10月, (一社)日本臨床神経生理学会, 日本語
2020年10月 - 2020年10月

レム睡眠行動障害研究の進歩 レム睡眠行動障害の自律神経障害
角 幸頼, 松尾 雅博, 尾関 祐二, 仲山 千佳夫, 藤原 幸一, 角谷 寛
臨床神経生理学, 2020年10月, (一社)日本臨床神経生理学会, 日本語
2020年10月 - 2020年10月

AI/IoTによるソーシャルディスンス社会におけるヒトのセンシング　　　　　　　　　　　　　　　
藤原幸一
名古屋大学高等研究院ウェビナー, 2020年06月02日, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］

IoTシステム設計において考慮すべきこと　　　　　　　　　　　　　　　
藤原幸一
化学工学会第51回Continuing Educationシリーズ講習, 2020年01月21日, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］

レム睡眠行動障害の自律神経障害　　　　　　　　　　　　　　　
角幸頼, 松尾雅博, 尾関祐二, 仲山千佳夫, 藤原幸一, 角谷寛
臨床神経生理学(Web), 2020年
2020年 - 2020年

シンクロスクイージングウェーブレット変換とRUSBoostの融合による睡眠紡錘波検出アルゴリズムの開発　　　　　　　　　　　　　　　
藤原幸一, 木下貴文, 角幸頼, 松尾雅博, 小川景子, 加納学, 角谷寛
人工知能学会全国大会(Web), 2020年
2020年 - 2020年

Views of patients with epilepsy on wearable seizure prediction system; impact of two different type of devices on sleep quality
M. Miyajima, T. Yamakawa, K. Fujiwara, T. Seki, T. ohno, M. Iimori, M. Inaji, H. Osoegawa, M. Kano, T. Maehara
Sleep Medicine, 2019年12月, Elsevier {BV}, 英語
2019年12月 - 2019年12月

新たなてんかんケアの可能性～てんかん発作予知システムの開発　　　　　　　　　　　　　　　
藤原 幸一
名古屋大学医学部市民公開講座, 2019年12月01日, 日本語, 口頭発表（招待・特別）
［招待講演］, ［国内会議］

医療AI開発とその活用 〜てんかん発作予知を例に　　　　　　　　　　　　　　　
藤原 幸一
第39回医療情報学連合大会企画カンファレンス, 2019年11月22日, 英語, シンポジウム・ワークショップパネル（指名）
［招待講演］, ［国内会議］

人工知能で測れないものを測る　　　　　　　　　　　　　　　
藤原 幸一
天白高校・出前授業, 2019年11月07日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

医師患者関係のトラスト構築に向けたAI活用の可能性　　　　　　　　　　　　　　　
藤田 卓仙, 江間 有沙, 近藤 諭, 藤原 幸一, 中谷内 一也, 尾藤 誠司
医療情報学連合大会論文集, 2019年11月, (一社)日本医療情報学会, 日本語
2019年11月 - 2019年11月

心拍変動解析を用いたてんかん発作予知・検知技術の開発　　　　　　　　　　　　　　　
藤原 幸一
名古屋大・聖隷浜松合同カンファレンス, 2019年10月05日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

Closed-Loop てんかんケアの実現に向けたてんかん発作予知アルゴリズムの開発　　　　　　　　　　　　　　　
藤原 幸一
電子情報通信学会ソサイエティ大会, 2019年09月12日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

てんかん患者におけるウェアラブル自律神経機能モニタリングの試み てんかん突然死のリスク評価を目指し　　　　　　　　　　　　　　　
宮島 美穂, 山川 俊貴, 藤原 幸一, 関 拓哉, 稲次 基希, 橋本 聡華, 岩崎 真樹, 長綱 敏和, 藤井 正美, 山本 信二, 加納 学, 前原 健寿
てんかん研究, 2019年09月, (一社)日本てんかん学会, 日本語
2019年09月 - 2019年09月

AI/IoT を活用した新たなてんかん治療法の開発　　　　　　　　　　　　　　　
藤原 幸一
名古屋大学医学部脳とこころの研究センタ・サマースクール, 2019年07月17日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

医学における AI の活用てんかん・睡眠障害を例に　　　　　　　　　　　　　　　
藤原 幸一
東京医科歯科大学脳機能外科セミナー, 2019年07月02日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

Development of a Sleep Apnea Detection Algorithm Using Long Short-Term Memory and Heart Rate Variability.
Ayako Iwasaki, Chikao Nakayama, Koichi Fujiwara, Yukiyoshi Sumi, Masahiro Matsuo, Manabu Kano, Hiroshi Kadotani
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2019年07月, 英語
2019年07月 - 2019年07月, Sleep apnea syndrome (SAS) is a prevalent disorder which causes daytime fatigue with the increased risk of lifestyle diseases. A large number of patients are undiagnosed and untreated partly because of the difficulty in performing its gold standard test, polysomnography (PSG). In this research, we propose a simple screening method utilizing heart rate variability (HRV) and long short-term memory (LSTM) which is a kind of neural network techniques. The result of applying this algorithm to clinical data demonstrates that it can discriminate between patients and healthy people with high sensitivity (100%) and specificity (100%).

医療AI人材とか何か〜てんかん・睡眠障害のモニタリングAIの開発を例に　　　　　　　　　　　　　　　
藤原 幸一
日本睡眠学会医師向けセミナー, 2019年06月27日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

心拍変動解析を用いたCPAPの自律神経活動への短期的効果の検証　　　　　　　　　　　　　　　
仲山 千佳夫, 藤原 幸一, 松尾 雅博, 加納 学, 角谷 寛
日本睡眠学会定期学術集会プログラム・抄録集, 2019年06月, (一社)日本睡眠学会, 日本語
2019年06月 - 2019年06月

ウェーブレット・シンクロスクイージング変換とランダムアンダーサンプリングによる高精度睡眠紡錘波検出アルゴリズムの開発　　　　　　　　　　　　　　　
藤原 幸一, 木下 貴文, 角 幸頼, 松尾 雅博, 角谷 寛, 加納 学
日本睡眠学会定期学術集会プログラム・抄録集, 2019年06月, (一社)日本睡眠学会, 日本語
2019年06月 - 2019年06月

サポートベクターマシンに基づいた変数重要度による手首アクチグラフによる週末の寝だめ有無の推定および要因検討　　　　　　　　　　　　　　　
後藤 有貴, 藤原 幸一, 角 幸頼, 松尾 雅博, 加納 学, 角谷 寛
日本睡眠学会定期学術集会プログラム・抄録集, 2019年06月, (一社)日本睡眠学会, 日本語
2019年06月 - 2019年06月

MATLABを用いた医療機器ソフトウェア開発心拍変動解析とてんかん発作予知　　　　　　　　　　　　　　　
藤原 幸一
MATALB Expo 2019, 2019年05月28日, 英語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

若手研究者による講演　　　　　　　　　　　　　　　
藤原 幸一
JSPS卓越研究員事業説明会, 2019年03月02日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

医療×AIシンポジウム -医療×AI推進人材を考える　　　　　　　　　　　　　　　
藤原 幸一
日本マイクロソフトDeep Learning Lab, 2019年02月10日, 英語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

手首アクチグラフによる週末の寝だめ有無の推定および変数重要度に基づいた要因検討　　　　　　　　　　　　　　　
後藤有貴, 藤原幸一, 角幸頼, 松尾雅博, 加納学, 角谷寛
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), 2019年
2019年 - 2019年

シンクロスクイージングウェーブレット変換とRUSBoostによる睡眠紡錘波検出アルゴリズム　　　　　　　　　　　　　　　
藤原幸一, 木下貴文, 角幸頼, 松尾雅博, 角谷寛, 加納学
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), 2019年
2019年 - 2019年

長期短期記憶と心拍変動に基づく睡眠時無呼吸症候群のスクリーニング
岩崎 絢子, 仲山 千佳夫, 藤原 幸一, 角 幸頼, 松尾 雅博, 加納 学, 角谷 寛
人工知能学会全国大会論文集, 2019年, 一般社団法人 人工知能学会, 日本語
2019年 - 2019年,

睡眠時無呼吸症候群 (SAS) は, 睡眠中に呼吸の停止あるいは呼吸量の減少が頻回に起こる疾患であり, 日中の眠気などの症状を引き起こすほか, 心血管系の合併症のリスクを高める. しかし, 自覚症状に乏しいケースも存在することから, 診断および治療に至っていない患者が多く存在すると考えられている. SAS の診断には終夜睡眠ポリグラフ検査 (PSG) が用いられるが, PSG を実施できる施設が少ないことが問題となっていた. そこで本研究では, 心拍変動解析と長期短期記憶を組み合わせた簡便なスクリーニング手法を提案する. SAS 患者および健常者計 59 名のデータに対して提案法を適用したところ, 感度 100%, 特異度 100% で SAS のスクリーニングが可能であることが判明した.

スモールデータ解析でAIに勝つ〜データ解析を活用した医療機器開発　　　　　　　　　　　　　　　
藤原 幸一
ものづくり企業に役立つ応用数理手法の研究会, 2018年12月12日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］

Analysis of VNS Effect on EEG Connectivity with Granger Causality and Graph Theory　　　　　　　　　　　　　　　
T. Uchida, K. Fujiwara, T. Inoue, Y. Maruta, M. Kano, M. Suzuki
APSIPA ASC 2018, 2018年11月, 英語
2018年11月 - 2018年11月

ウェアラブル心拍変動センサを用いたてんかん発作予測システムの開発　　　　　　　　　　　　　　　
藤原 幸一
第52回日本てんかん学会学術集会, 2018年10月27日, 英語, シンポジウム・ワークショップパネル（指名）
［招待講演］, ［国内会議］

スモールデータでAIに勝つ～てんかん発作予知を例に　　　　　　　　　　　　　　　
藤原 幸一
鉄鋼協会産学若手交流セミナー, 2018年09月08日, 英語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

睡眠時無呼吸症候群患者における多変量統計的プロセス管理と心拍変動解析を用いた持続陽圧呼吸療法の自律神経活動への短期的効果の検証　　　　　　　　　　　　　　　
仲山 千佳夫, 藤原 幸一, 松尾 雅博, 角谷 寛, 加納 学
日本睡眠学会定期学術集会プログラム・抄録集, 2018年07月, (一社)日本睡眠学会, 日本語
2018年07月 - 2018年07月

Denoising Autoencoder-based Modification of RRI data with Premature Ventricular Contraction for Precise Heart Rate Variability Analysis　　　　　　　　　　　　　　　
S. Miyatani, K. Fujiwara, M. Kano
IEEE EMBC 2018, 2018年07月, 英語
2018年07月 - 2018年07月

特異スペクトル解析とDenoising Autoencoderの組み合わせによるRR間隔データ補正法とそのオープンデータへの適用
宮谷将太, 藤原幸一, 加納学
システム制御情報学会研究発表講演会講演論文集(CD-ROM), 2018年05月16日, 日本語
2018年05月16日 - 2018年05月16日

脳神経保護を目的とした局所脳冷却デバイスの流路構造及び操作条件最適化
阿部拓斗, 井上貴雄, 藤原幸一, 野村貞宏, 井本浩哉, 鈴木倫保, 加納学
システム制御情報学会研究発表講演会講演論文集(CD-ROM), 2018年05月16日, 日本語
2018年05月16日 - 2018年05月16日

Design of false heart rate feedback system for improving game experience
Sayaka Ogawa, Koichi Fujiwara, Toshitaka Yamakawa, Erika Abe, Manabu Kano
2018 IEEE International Conference on Consumer Electronics, ICCE 2018, 2018年03月26日, 英語
2018年03月26日 - 2018年03月26日, © 2018 IEEE. When players are excited by playing a video game, corresponding physiological responses such as sweating or changes in heart rate may appear. It is assumed that presenting physiological responses during game play to players in real-time alters their game experience even when they play the same game. Based on this assumption, this work investigated the effect of false heart rate (HR) feedback on game experience through experiments using a simple action game. Our experimental results indicated that false HR feedback not only prevented the players from becoming tired of the game but also enhanced players' experiences. In addition, a new game controller that can present HR information audibly and tactually was developed for realizing a game system based on false HR feedback.

相関識別法を用いた入力変数重み付けによる高精度ソフトセンサの開発
藤原幸一, 加納学
計測自動制御学会制御部門マルチシンポジウム(CD-ROM), 2018年03月08日, 日本語
2018年03月08日 - 2018年03月08日

非線形システムの時系列データを対象とした因果推論手法の比較
和田拓也, 藤原幸一, 加納学
計測自動制御学会制御部門マルチシンポジウム(CD-ROM), 2018年03月08日, 日本語
2018年03月08日 - 2018年03月08日

Causal analysis based on non-time-series kernel Granger causality in a steelmaking process
Ryosuke Sato, Koichi Fujiwara, Masahiro Tani, Junichi Mori, Junji Ise, Kohhei Harada, Manabu Kano
2017 Asian Control Conference, ASCC 2017, 2018年02月07日, 英語
2018年02月07日 - 2018年02月07日, © 2017 IEEE. In the manufacturing industry, it is extremely important to identify variables that affect product quality. Identifying variables which affect quality variables is called causal analysis. In batch processes, time-series data of process variables and the corresponding data of quality variables are generally acquired. Since causal analysis using the raw data needs a large computation load, it is often performed after compressing time-series process variables data into non-time-series feature variables data. Various causal analysis methods using such data have been developed, however, none have shown effective results in actual plants. In the present work, non-time-series kernel Granger causality (NTS-KGC) is proposed for causal analysis with non-time-series data of batch processes. This is a method that kernel Granger causality [1], which is used for causal analysis with time-series data in nonlinear systems, is expanded for causal analysis with non-time-series data. The validity of the proposed method is demonstrated through a numerical example of a nonlinear batch process. In addition, we conducted a case study of applying NTS-KGC to data obtained from a real steelmaking process. The results demonstrate that NTS-KGC is superior to other existing methods using the following indexes, i.e. variable influence on projection (VIP) of partial least squares (PLS), regression coefficients of PLS, and variable importance of Random Forest.

CFD-Based Design of Focal Brain Cooling System for Suppressing Epileptic Seizures
Kei Hata, Takuto Abe, Takao Inoue, Koichi Fujiwara, Takatomi Kubo, Toshitaka Yamakawa, Sadahiro Nomura, Hirochika Imoto, Michiyasu Suzuki, Manabu Kano
Computer Aided Chemical Engineering, 2018年01月01日
2018年01月01日 - 2018年01月01日, © 2018 Elsevier B.V. Epilepsy is a group of neurological disorders which is caused by excessive neuronal activities in cerebrum and characterized by recurrent seizures. A quarter of patients have intractable epilepsy and do not become seizure-free with medication. We are developing an implantable and wearable focal brain cooling system, which enables the patients to lead ordinary daily life. The system cools the epileptic focus, where the excessive neuronal activities begin, by delivering cold saline to a cranially implanted cooling device. In this research, we developed a whole system model through the first principles and animal experiments. The results of system design have shown that a cooling device with more complex channel structure achieves higher temperature uniformity in the brain with lower flow rate of saline. The optimal structure was derived by taking account of the trade-off between pressure drop and temperature uniformity. In addition, the results have demonstrated that the cooling duration is less than 10 minutes for the average temperature 2 mm below the cooling device (inside the brain) to reach 25 °C; it is short enough to cool the brain after seizure is predicted by existing electroencephalogram (EEG)-based algorithms. Moreover, the frequency of battery charging would be once in several days for most patients.

心拍変動解析に基づいた全般性てんかん発作予測および全般性発作に先行する自律神経活動に関する考察
坂根 史弥, 藤原 幸一, 宮島 美穂, 鈴木 陽子, 山川 俊貴, 加納 学, 前原 健寿
生体医工学, 2018年, 公益社団法人 日本生体医工学会, 日本語
2018年 - 2018年, <p>てんかん発作を予測できれば，難治性てんかん患者のQoLを改善できると期待される．そこで本研究では，心拍変動(HRV)解析と多変量統計的プロセス管理を用いて，焦点性発作と同様に全般性発作においても発作予測が可能であるかを調べた．１１名の全般性てんかん患者より取得した１７例の発作周辺期データおよび約６３時間分の７４例の発作間欠期データにより全般性発作予測を試みたところ，１７例中１３例の発作を予測でき，このときの偽陽性率は１．３９回/hであった．また検証用発作間欠期のうち発作周辺期と誤検出された時間の割合は５．９６％であった．本結果から全般性発作においてもHRV解析を用いて発作予測できる可能性が示唆された．本研究で用いたアルゴリズムが発作周辺期と判定した区間のHRV指標を調べたところ，全般性発作起始前に，必ずしも交感神経活動が優位とはならず，交感神経活動と副交感神経活動のバランスが変化していることが確認された．さらに，本解析結果と全般性発作の機序に関する過去の研究に基づいて，全般性発作起始前においてHRVが変化する要因について考察し，発作起始前の自律神経系活動の変化が全般性発作起始を誘発するという仮説を提案した．しかし，HRV解析では変化の生じた自律神経系の部位の特定はできないため，動物実験等のHRV解析以外の方法で，提案した仮説を検証する必要がある．</p>

心拍数変動解析と多変量統計的プロセス管理を用いたウェアラブルてんかん発作予知システムの開発　　　　　　　　　　　　　　　
山川 俊貴, 宮島 美穂, 藤原 幸一, 加納 学, 鈴木 陽子, 渡辺 裕貴, 渡邊 さつき, 村田 佳子, 星田 徹, 前原 健寿
てんかん研究, 2018年01月, (一社)日本てんかん学会, 日本語
2018年01月 - 2018年01月

睡眠時無呼吸症候群患者における持続陽圧呼吸療法の心拍への短期的効果
藤原幸一, 仲山千佳夫, 松尾雅博, 加納学, 角谷寛
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), 2017年11月25日, 日本語
2017年11月25日 - 2017年11月25日

心拍変動解析と多変量統計的プロセス管理による全般性てんかん発作予測
坂根史弥, 藤原幸一, 宮島美穂, 鈴木陽子, 山川俊貴, 加納学, 前原健寿
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), 2017年11月25日, 日本語
2017年11月25日 - 2017年11月25日

次第に速くなる心拍音提示によるゲーム体験の向上
小川紗也加, 藤原幸一, 山川俊貴, 阿部恵里花, 加納学
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), 2017年11月25日, 日本語
2017年11月25日 - 2017年11月25日

中大脳動脈閉塞ラットモデルを用いた心拍変動解析による脳卒中早期検知システム実現性の検証
藤原幸一, 鎌田啓輔, 児玉智信, 加納学, 村山雄一, 結城一郎
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), 2017年11月25日, 日本語
2017年11月25日 - 2017年11月25日

リアルタイム心拍変動解析を用いたヘルスモニタリング　　　　　　　　　　　　　　　
藤原 幸一
京都大学テックフォーラム, 2017年11月06日, 英語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

心拍変動を用いた入眠検出　　　　　　　　　　　　　　　
藤原 幸一
第24回日本時間生物学会学術大会シンポジウム, 2017年10月29日, 日本語, シンポジウム・ワークショップパネル（指名）
［招待講演］, ［国内会議］

Validation of HRV-Based Drowsy-Driving Detection Method with EEG Sleep Stage Classification　　　　　　　　　　　　　　　
T. Yamakawa, K. Fujiwara, T. Hiraoka, M. Kano, Y. Sumi, F. Masuda, M. Matsuo, H. Kadotani
Proc. of World Sleep Congress, 2017年10月, 英語
2017年10月 - 2017年10月

てんかん発作抑制を目指した局所脳冷却システムの設計
畑啓, 藤原幸一, 加納学, 井上貴雄, 野村貞宏, 井本浩哉, 鈴木倫保
化学工学会秋季大会研究発表講演要旨集(CD-ROM), 2017年09月20日, 日本語
2017年09月20日 - 2017年09月20日

A new infarction detection method based on heart rate variability in rat middle cerebral artery occlusion model
Tomonobu Kodata, Keisuke Kamata, Koichi Fujiwara, Manabu Kano, Toshiki Yamakawa, Ichiro Yuki, Yuichi Murayama
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2017年09月13日, 英語
2017年09月13日 - 2017年09月13日, © 2017 IEEE. Objective: The present study proposes a cerebral infarction detection algorithm based on heart rate variability (HRV). Methods: It has been reported that infarction affects HRV. Therefore, infarction could be detected at an acute stage by monitoring HRV. This study uses multivariate statistical process control (MSPC), which is a well-known anomaly monitoring method. HRV data shortly after infarction onsets are collected by using the middle cerebral artery occlusion (MCAO) model in rats. This study prepares 11 MCAO-operated rats and 11 sham-operated rats. Three sham-operated rats' data are used for model construction of MSPC, and the other 19 rats' data are used for its validation. Results: The sensitivity and specificity of the proposed algorithm were 82 % and 75 %, respectively. Conclusion: An infarction onset could be detected at an acute stage by monitoring HRV.

Design of focal brain cooling system for suppressing epileptic seizures
Kei Hata, Koichi Fujiwara, Manabu Kano, Takao Inoue, Sadahiro Nomura, Hirochika Imoto, Michiyasu Suzuki
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2017年09月13日, 英語
2017年09月13日 - 2017年09月13日, © 2017 IEEE. Epilepsy is a group of diseases caused by excessive neuronal activities, and one-quarter of the patients do not become seizure-free by the existing treatments. The potential treatments include focal brain cooling, which aims to cool the region where the excessive neuronal activities begin. We are developing a focal brain cooling system. The system delivers cold saline to a cranially implanted cooling device. The outflow is cooled by a Peltier device and pumped for circulation. The Peltier device and the pump are activated only when a seizure is predicted. In this research, the length of time for cooling the brain was calculated with a computational fluid dynamics (CFD)-based model of the focal brain cooling system. As a result, it takes less than 10 minutes for the average temperature 2 mm below the cooling device to reach 25.0 °C. It is much shorter than the time from seizure prediction to seizure onset when an existing algorithm for prediction is used.

心拍変動解析と機械学習を用いたてんかんアラーム〜スモールデータ解析でAIに勝つ,　　　　　　　　　　　　　　　
藤原 幸一
市村学術賞受賞記念講演, 2017年09月06日, 英語, 口頭発表（招待・特別）
［招待講演］, ［国内会議］

人と人をつなぐテクノロジ　　　　　　　　　　　　　　　
藤原 幸一
七尾市青年会議所公開授業, 2017年09月05日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

Development of correlation-based process characteristics visualization method and its application to fault detection
Koichi Fujiwara, Manabu Kano
IEEE International Conference on Control and Automation, ICCA, 2017年08月04日, 英語
2017年08月04日 - 2017年08月04日, © 2017 IEEE. Although process monitoring is important for maintaining safety and product quality, it is difficult to understand process characteristics particularly when they are changing. Since the correlation among variables changes due to changes in process characteristics, process data visualization based on the correlation among variables helps process characteristic understanding. In the present work, a new correlation-based data visualization method is proposed by integrating joint decorrelation (JD) and stochastic proximity embedding (SPE). JD is a blind source separation (BSS) method that can separates sample based on the correlation, and SPE is a self-organizing algorithm that can map high-dimensional data to a two-dimensional plane. The proposed method, referred to as JD-SPE, separates samples based on the correlation using JD and the separated samples are visualized in the two-dimensional plane by SPE. Correlation matrices have to be constructed before sample separation for JD; however how to construct them is not clear. The present work also proposes a correlation matrix construction method for JD by using nearest correlation spectral clustering (NCSC), which is a correlation-based clustering method. In addition, a new process monitoring method based on multivariate statistical process control (MSPC) which is a well-known process monitoring algorithm and JD-SPE. This monitoring method is referred to as JD-SPE-r2. The proposed JD-SPE-Γ2 can detect a fault that can not detected by the conventional MSPC. The usefulness of the proposed methods is demonstrated through numerical examples.

心拍変動解析と多変量統計的プロセス管理に基づく全般性てんかん発作予測
坂根史弥, 藤原幸一, 宮島美穂, 鈴木陽子, 山川俊貴, 加納学, 前原健寿
システム制御情報学会研究発表講演会講演論文集(CD-ROM), 2017年05月23日, システム制御情報学会, 日本語
2017年05月23日 - 2017年05月23日

熱中症アラーム開発の取り組み - 2020年に向けて　　　　　　　　　　　　　　　
藤原 幸一
鹿児島県西之表市「スマートエコアイランド種子島」シンポジウム, 2017年03月08日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

報道と研究 - 現場から　　　　　　　　　　　　　　　
藤原 幸一
新聞労連研修会, 2017年01月21日, 日本語, シンポジウム・ワークショップパネル（指名）
［国内会議］

Canine emotional states assessment with heart rate variability
Eri Nakahara, Yuki Maruno, Takatomi Kubo, Rina Ouchi, Maki Katayama, Koichi Fujiwara, Miho Nagasawa, Takefumi Kikusui, Kazushi Ikeda
2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016, 2017年01月17日, Institute of Electrical and Electronics Engineers Inc., 英語
2017年01月17日 - 2017年01月17日, Emotions of a person affect the person's performance in a task and so do emotions of a rescue dog that works after disasters. Hence, estimating emotions of a rescue dog by the handler can improve its performance and welfare. Emotions also appear in physiological signals such as heart rate variability (HRV). In fact, HRV has information of emotions in both cases of human and dogs. To make emotion estimation more practical, we proposed a method for emotion estimation from HRV of dogs and evaluated its performance using real data. The method classified positive, negative, and neutral emotions with 88% accuracy within each subject and 72% over all subjects. These accuracies are high enough for practical use in rescue dogs.

リアルタイム心拍変動解析技術を用いたドライバ状態推定 – 発作・居眠り運転による事故を防ぐ　　　　　　　　　　　　　　　
藤原 幸一
CEATEC JAPAN 2016 自動運転コンファレンス企画, 2016年10月07日, 日本語, 口頭発表（基調）
［招待講演］, ［国内会議］

Wakefulness keeping support system for drivers based on game using body movement and voice input command　　　　　　　　　　　　　　　
T. Hiraoka, T. Ibe, E. Abe, K. Fujiwara, T. Yamakawa
Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2016年08月
2016年08月 - 2016年08月

Application of Process Data Analysis Techniques to Health Monitoring Device Development　　　　　　　　　　　　　　　
藤原 幸一
PSE Asia2016, 2016年07月26日, 英語, 口頭発表（一般）
［招待講演］, ［国際会議］

産業分野におけるデータ解析事例から眺める医療データ標準フォーマット化への期待　　　　　　　　　　　　　　　
藤原 幸一
日本睡眠学会定期学術集会, 2016年07月08日, 英語, シンポジウム・ワークショップパネル（指名）
［招待講演］, ［国内会議］

グレンジャー因果性とグラフ理論を用いた迷走神経刺激療法における脳波コネクティビティ変化解析
内田 剛志, 藤原 幸一, 井上 貴雄, 丸田 雄一, 加納 学, 鈴木 倫保
システム制御情報学会研究発表講演会講演論文集, 2016年05月25日, システム制御情報学会, 日本語
2016年05月25日 - 2016年05月25日

面センシング臥位脈派計測装置を用いた皮下血流量変化推定
小川 紗也加, 藤原 幸一, 千明 裕, 山川 俊貴, 加納 学, 渡部 智樹
システム制御情報学会研究発表講演会講演論文集, 2016年05月25日, システム制御情報学会, 日本語
2016年05月25日 - 2016年05月25日

局所PLSを用いた欠損RRIデータ補間の提案と健常者RRIデータへの適用
鎌田 啓輔, 藤原 幸一, 加納 学, 山川 俊貴
システム制御情報学会研究発表講演会講演論文集, 2016年05月25日, システム制御情報学会, 日本語
2016年05月25日 - 2016年05月25日

非負値行列因子分解を用いた心拍変動解析における個人差低減手法の開発とその眠気検出モデルへの適用
阿部 恵里花, 藤原 幸一, 加納 学
システム制御情報学会研究発表講演会講演論文集, 2016年05月25日, システム制御情報学会, 日本語
2016年05月25日 - 2016年05月25日

心拍変動（HRV）解析を用いたヘルスモニタサービスの開発　　　　　　　　　　　　　　　
藤原 幸一
JST 京都大学新技術説明会, 2016年05月24日, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

プロセス異常検出技術によるてんかん発作予知の実現
藤原幸一, 阿部恵里花, 加納学, 山川俊貴, 澤田由梨子, 鈴木陽子, 宮島美穂
化学工学会年会研究発表講演要旨集(CD-ROM), 2016年03月13日, 日本語
2016年03月13日 - 2016年03月13日

てんかん発作抑制を目指した局所脳冷却デバイスの設計
畑慶, 藤原幸一, 加納学, 井上貴雄, 野村貞宏, 井本浩哉, 鈴木倫保
化学工学会年会研究発表講演要旨集(CD-ROM), 2016年03月13日, 日本語
2016年03月13日 - 2016年03月13日

能動的行為を伴うシステムを用いたドライバの覚醒支援　　　　　　　　　　　　　　　
伊部達朗, 平岡敏洋, 阿部恵里花, 藤原幸一, 山川俊貴
情報処理学会研究報告（第39回情報処理学会 エンタテインメントコンピューティング研究会）, 2016年03月, 日本語
2016年03月 - 2016年03月

脈波センサ埋め込み型ビデオゲームコントローラの開発 (ITS)
阿部 恵里花, 千明 裕, 藤原 幸一
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報, 2016年02月22日, 電子情報通信学会, 日本語
2016年02月22日 - 2016年02月22日

脈波センサ埋め込み型ビデオゲームコントローラの開発 (マルチメディアストレージ コンシューマエレクトロニクス ヒューマンインフォメーション メディア工学 映像表現&コンピュータグラフィックス)
阿部 恵里花, 千明 裕, 藤原 幸一, 加納 学, 山川 俊貴
映像情報メディア学会技術報告 = ITE technical report, 2016年02月, 映像情報メディア学会, 日本語
2016年02月 - 2016年02月

Development of Photoplethysmogram Sensor-embedded Video Game Controller
Erika Abe, Koichi Fujiwara, Manabu Kano, Hiroshi Chigira, Toshitaka Yamakawa
2016 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE), 2016年, IEEE, 英語
2016年 - 2016年, If player condition during video game playing could be measured in real time, it would become possible to develop a new game interaction system. Since heart rate (HR) has been used for various psychological condition estimation, it can be used for player condition estimation. In the present work, a new game controller that can measure player HR without letting the player be conscious of the controller based on a photoplethysmogram (PPG) was developed. The experiment result demonstrated that the newly developed game controller could measure the player HR with sufficiently high accuracy.

ウェアラブル心拍数変動センサの開発と臨床・ヘルスケア応用-てんかん発作や居眠り運転事故の「予知」-　　　　　　　　　　　　　　　
山川俊貴, 山川俊貴, 藤原幸一, 平岡敏洋, 加納学, 宮島美穂, 前原健寿, 太田克也, 笹野哲郎, 松浦雅人, 松島英介
電子情報通信学会技術研究報告, 2016年
2016年 - 2016年

運転中の能動的行為によるドライバの覚醒維持効果と運転安全性　　　　　　　　　　　　　　　
伊部達朗, 平岡敏洋, 阿部恵里花, 藤原幸一, 山川俊貴
自動車技術会大会学術講演会講演予稿集(CD-ROM), 2016年
2016年 - 2016年

Individuality Reduction in Heart Rate Variability for Drowsy Driving Detection　　　　　　　　　　　　　　　
Koichi Fujiwara, Erika Abe, Toshitaka Yamakawa, Manabu Kano
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2016年
2016年 - 2016年

Real-Time Epileptic Seizure Prediction System Employing a Wearable HRV Telemeter and a Smartphone　　　　　　　　　　　　　　　
Miho Miyajima, Toshitaka Yamakawa, Koichi Fujiwara, Yuriko Sawada, Yoko Suzuki, Erika Abe, Manabu Kano, Satsuki Watanabe, Yoshiko Murata, Yutaka Watanabe, Taketoshi Maehara, Eisuke Matsushima
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2016年
2016年 - 2016年

Variable Elimination-Based Contribution for Accurate Fault Identification
Yusuke Satoyama, Koichi Fujiwara, Manabu Kano
IFAC PAPERSONLINE, 2016年, ELSEVIER SCIENCE BV, 英語
2016年 - 2016年, We propose a new fault identification method, which can describe the contribution of each process variable to a detected fault and identify a faulty variable more accurately than conventional methods. In the proposed method, in addition to a fault detection model that describes normal operating condition (NOC), multiple fault identification models that describe the saute NOC are also constructed by eliminating one variable front all monitored variables at a time. After a fault is detected with the fault detection model, the fault detection index, e.g. a combined index of the T-2 and Q statistics, is calculated by using each of the fault identification models. When the faulty variable is eliminated, the index does not change before and after the fault occurs. On the other hand, when the normal variable is eliminated, the index is affected by the fault and increases after the fault occurs. Thus, the eliminated variable corresponding to the index that does not, increase after the occurrence of the fault is identified as a faulty variable. In the proposed method, the ratio of the average index in NOC to the current index is used as a fault identification index or a contribution. To validate the proposed method, VEC was compared with the reconstruction-based contribution (RBC) through numerical examples. The results have demonstrated that VEC outperformed RBC in fault identification performance both in the linear case and in the nonlinear case. (C) 2016, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

Missing RRI interpolation for HRV analysis using Locally-Weighted Partial Least Squares Regression
Keisuke Kamata, Koichi Fujiwara, Toshiki Yamakawa, Manabu Kano
2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2016年, IEEE, 英語
2016年 - 2016年, The R-R interval (RRI) fluctuation in electrocardiogram (ECG) is called heart rate variability (HRV). Since HRV reflects autonomic nervous function, HRV-based health monitoring services, such as stress estimation, drowsy driving detection, and epileptic seizure prediction, have been proposed. In these HRV-based health monitoring services, precise R wave detection from ECG is required; however, R waves cannot always be detected due to ECG artifacts. Missing RRI data should be interpolated appropriately for HRV analysis. The present work proposes a missing RRI interpolation method by utilizing using just-in-time (JIT) modeling. The proposed method adopts locally weighted partial least squares (LW-PLS) for RRI interpolation, which is a well-known JIT modeling method used in the filed of process control. The usefulness of the proposed method was demonstrated through a case study of real RRI data collected from healthy persons. The proposed JIT-based interpolation method could improve the interpolation accuracy in comparison with a static interpolation method.

心拍変動解析によるウェアラブルてんかん発作兆候検出システムの開発
山川俊貴, 藤原幸一, 阿部恵理花, 加納学, 宮島美穂, 鈴木陽子, 松島英介, 澤田由梨子, 笹野哲郎, 角勇樹, 村田佳子, 渡邊さつき, 渡辺裕貴, 前原健寿, 松浦雅人, 松浦雅人
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), 2015年11月18日, 日本語
2015年11月18日 - 2015年11月18日

Development of sleep apnea syndrome screening algorithm by using heart rate variability analysis and support vector machine
Chikao Nakayama, Koichi Fujiwara, Masahiro Matsuo, Manabu Kano, Hiroshi Kadotani
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2015年11月04日, 英語
2015年11月04日 - 2015年11月04日, © 2015 IEEE. Although sleep apnea syndrome (SAS) is a common sleep disorder, most patients with sleep apnea are undiagnosed and untreated because it is difficult for patients themselves to notice SAS in daily living. Polysomnography (PSG) is a gold standard test for sleep disorder diagnosis, however PSG cannot be performed in many hospitals. This fact motivates us to develop an SAS screening system that can be used easily at home. The autonomic nervous function of a patient changes during apnea. Since changes in the autonomic nervous function affect fluctuation of the R-R interval (RRI) of an electrocardiogram (ECG), called heart rate variability (HRV), SAS can be detected through monitoring HRV. The present work proposes a new HRV-based SAS screening algorithm by utilizing support vector machine (SVM), which is a well-known pattern recognition method. In the proposed algorithm, various HRV features are derived from RRI data in both apnea and normal respiration periods of patients and healthy people, and an apnea/normal respiration (A/N) discriminant model is built from the derived HRV features by SVM. The result of applying the proposed SAS screening algorithm to clinical data demonstrates that it can discriminate patients with sleep apnea and healthy people appropriately. The sensitivity and the specificity of the proposed algorithm were 100% and 86%, respectively.

心拍変動モニタリングによるてんかん発作早期検出の試み
宮島美穂, 藤原幸一, 山川俊貴, 笹井妙子, 加納学, 前原健寿, 笹野哲郎, 太田克也, 太田克也, 太田克也, 松浦雅人, 松浦雅人, 松島英介
臨床神経生理学, 2015年10月01日, 日本語
2015年10月01日 - 2015年10月01日

ウェアラブルな心拍変動モニタリングシステムの開発
山川俊貴, 宮島美穂, 藤原幸一, 阿部恵理花, 鈴木陽子, 澤田由梨子, 加納学, 渡辺裕貴, 前原健寿
臨床神経生理学, 2015年10月01日, 日本語
2015年10月01日 - 2015年10月01日

音楽による気分変化と、その生理指標変化
松尾 雅博, 増田 史, 角 幸頼, 藤原 幸一, 森島 守人, 山木 清志, 山田 尚登, 角谷 寛
臨床神経生理学, 2015年10月, (一社)日本臨床神経生理学会, 日本語
2015年10月 - 2015年10月

Heart rate monitoring on steering wheel using surface type sensor　　　　　　　　　　　　　　　
H. Chigira, T. Hori, K. Fujiwara, T. Hiraoka, T. Tanaka
ITS World Congress, 2015年10月

ウェアラブル心拍変動センサを用いたてんかん発作兆候検出システムの開発
澤田由梨子, 鈴木陽子, 阿部恵理花, 藤原幸一, 宮島美穂, 山川俊貴, 加納学, 村田佳子, 渡邊さつき, 渡邊裕貴, 前原健寿, 笹野哲郎, 角勇樹, 松島英介, 松浦雅人
てんかん研究, 2015年09月17日, 日本語
2015年09月17日 - 2015年09月17日

心拍変動解析によるヘルスモニタリング　　　　　　　　　　　　　　　
藤原 幸一
自動車技術会シンポジウム「自動車開発における人間工学の理論と実践」, 2015年09月, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

心拍変動解析を用いた疾患スクリーニング　　　　　　　　　　　　　　　
藤原 幸一
京都大学数理解析研究所共同研究集会, 2015年07月, 英語, 口頭発表（招待・特別）
［招待講演］, ［国内会議］

運転環境と睡眠　　　　　　　　　　　　　　　
藤原 幸一
日本睡眠学会定期学術集会, 2015年07月, 日本語, シンポジウム・ワークショップパネル（指名）
［招待講演］, ［国内会議］

NCLM法に基づく効率的な変数選択を用いたソフトセンサ設計
内丸拓, 羽間康至, 藤原幸一, 加納学
システム制御情報学会研究発表講演会講演論文集(CD-ROM), 2015年05月20日, システム制御情報学会, 日本語
2015年05月20日 - 2015年05月20日

睡眠時無呼吸症候群スクリーニングを目的とした睡眠時心拍データへのサポートベクターマシンの適用
仲山千佳夫, 藤原幸一, 松尾雅博, 加納学, 角谷寛
システム制御情報学会研究発表講演会講演論文集(CD-ROM), 2015年05月20日, システム制御情報学会, 日本語
2015年05月20日 - 2015年05月20日

重み付きNCスペクトラルクラスタリングを用いたソフトセンサの入力変数選択
藤原幸一, 加納学
化学工学会年会研究発表講演要旨集(CD-ROM), 2015年03月19日, 日本語
2015年03月19日 - 2015年03月19日

Calibration Model Design based on Weighted Nearest Correlation Spectral Clustering
Koichi Fujiwara, Manabu Kano
2015 10TH ASIAN CONTROL CONFERENCE (ASCC), 2015年, IEEE, 英語
2015年 - 2015年, Calibration models have been widely used for estimating product quality or other key variables with near-infrared spectroscopy (NIRS), and it is important to select appropriate input variables (wavelengths) for building a highly accurate calibration model. A novel input variable selection method based on nearest correlation spectral clustering (NCSC), which is a correlation-based clustering method, was proposed, and it is referred to as NCSC-based variable selection (NCSC-VS). In NCSC-VS, some variable groups are clustered by NCSC, and a few variable groups are selected by their contribution to estimates. Although variable selection performance of NCSC-VS depends on variable group clustering by NCSC, its clustering results easily fluctuate according to measurement noise. The present work proposes an improved version of NCSC that can cope with measurement noise by introducing a weighting function into affinity matrix construction. In addition, the proposed clustering method, referred to as weighted NCSC (WNCSC), is applied to variable selection in calibration model design. WNCSC-VS can achieve a higher estimation performance than NCSC-VS. The usefulness of the proposed WNCSC-VS is demonstrated through an application to calibration model design for a pharmaceutical process.

Efficient Wavenumber Selection Based on Nearest Correlation Louvain Method for NIR Calibration Modeling
Taku Uchimaru, Koji Hazama, Koichi Fujiwara, Manabu Kano
2015 10TH ASIAN CONTROL CONFERENCE (ASCC), 2015年, IEEE, 英語
2015年 - 2015年, In process analytical technology (PAT), partial least squares (PLS) regression has been widely used to construct calibration models for near-infrared (NIR) spectroscopy. To construct a highly accurate calibration model, wavenumber selection is crucial. In the present work, an efficient wavenumber selection method especially for PLS is proposed. The proposed method is referred to as nearest correlation Louvain method-based variable selection (NCLM-VS). NCLM-VS is a correlation-based groupwise method; it constructs an affinity matrix of input variables by the nearest correlation (NC) method, partitions the affinity matrix by the Louvain method (LM), consequently clusters input variables into multiple variable groups, and finally selects variable groups according to their contribution to estimates. LM is very fast and optimizes the number of groups automatically unlike spectral clustering (SC). The advantage of NCLM-VS over conventional methods including nearest correlation spectral clustering-based method (NCSC-VS) is demonstrated through their applications to calibration modeling based on near-infrared (NIR) spectra. In particular, it is confirmed that NCLM-VS is significantly faster than NCSC-VS while NCLM-VS can achieve as good estimation performance as NCSC-VS.

Nearest Correlation Louvain Method for Fast and Good Selection of Input Variables of Statistical Model
Taku Uchimaru, Koji Hazama, Koichi Fujiwara, Manabu Kano
IFAC PAPERSONLINE, 2015年, ELSEVIER SCIENCE BV, 英語
2015年 - 2015年, In the present work, a new input variable selection method for building linear regression models proposed. The proposed method is referred to as nearest correlation Louvain method based variable selection (NCLM-VS). NCLM-VS is a correlation-based group-wise method; it constructs an affinity matrix of input, variables by the nearest correlation (NC) method, partitions the affinity matrix by the Louvain method (LM), consequently clusters input variables, into multiple variable classes, and finally selects Variable classes according to their contribution to estimates. LM is very fast and optimizes the number of classes automatically unlike spectral clustering (SC). The advantage of NCLM-VS over conventional methods including NCSC-VS is demonstrated through their applications to soft sensor design for an industrial chemical process and calibration modeling based on near-infrared (NIR) spectra. In particular, it is confirmed that NCLM-VS is significantly faster than the recently proposed NCSC-VS while NCLM-VS cart achieve as good estimation performance as NCSC-VS. (C) 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

Development of Stroke Detection Method by Heart Rate Variability Analysis and Support Vector Machine
Keisuke Kamata, Koichi Fujiwara, Tomonobu Kodama, Manabu Kano, Toshitaka Yamakawa, Norikata Kobayashi, Fuminori Shimizu
2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2015年, IEEE, 英語
2015年 - 2015年, It is important to start stroke treatment as early as possible for patient prognosis. In particular, thrombolysis with the tissue plasminogen activator (tPA) that can dissolve blood clots is effective only when it is given within 4.5 hours from the symptom onset. Since it is sometimes difficult for patients to recognize their symptoms, an early stroke detection system is needed. It is possible that a stroke can be detected by monitoring heart rate variability (HRV) because a stroke affects the autonomic nervous system. In the present work, a stroke detection method was proposed by integrating HRV analysis and support vector machine (SVM). The sensitivity and the specificity of the proposed method were 100% and 80%, respectively. The possibility of realizing an HRV-based stroke detection system was shown.

Heart Rate Monitoring by A Pulse Sensor Embedded Game Controller
Erika Abe, Hiroshi Chigira, Koichi Fujiwarai, Toshitaka Yamakawa, Manabu Kano
2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2015年, IEEE, 英語
2015年 - 2015年, If player condition during video game playing could be measured in real time, it would become possible to develop a new game interaction system. Since heart rate (HR) has been used for various psychological state estimation, it can be used for player condition estimation. The present work consists of two parts: the development of a new game controller that can measure player HR naturally based on a photoplethysmogram (PPG), and simultaneous monitoring of player condition by using the newly developed game controller.
The experiment result demonstrated that the newly developed game controller could measure the player HR with sufficiently high accuracy. In addition, it showed that the correlation coefficient between HR and the game score varied according to player condition. This indicates that player condition during video game could be estimated by monitoring HR and the game score simultaneously.

Accuracy Comparison between Two Microcontroller-embedded R-wave Detection Methods for Heart-rate Variability Analysis
Toshitaka Yamakawa, Ryunosuke Kinoshita, Koichi Fujiwara, Manabu Kano, Miho Miyajima, Tadashi Sakata, Yuichi Ueda
2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2015年, IEEE, 英語
2015年 - 2015年, Analysis of heart rate variability, which is calculated using the R-R intervals (RRI) of electrocardiogram (ECG), provides beneficial information for both clinical and healthcare diagnoses. To achieve the required accuracy for RRI measurement using the wearable telemetery system, two R-wave detection methods (one based on voltage threshold and another that adopts differential peak detection) were developed for implementation in a low-power microcontroller integrated into a wearable telemeter. Accuracy of these methods were compared using a clinical-grade ECG measurement system to evaluate the systematic errors of the proposed methods by correlation and Bland-Altman analyses.

リアルタイムてんかん発作兆候監視アルゴリズムおよび監視装置　　　　　　　　　　　　　　　
藤原 幸一
ウェアラブルEXPO, 2015年01月, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

ウェアラブル心拍センサとスマートフォンを用いたてんかん発作兆候監視システムの開発
藤原幸一, 阿部恵里花, 鈴木陽子, 澤田由梨子, 宮島美穂, 山川俊貴, 笹野哲朗, 加納学, 太田克也, 前原健寿, 松島英介, 松浦雅人
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), 2014年11月21日, 日本語
2014年11月21日 - 2014年11月21日

One Class SVMを用いたてんかん発作兆候監視アルゴリズムの開発
藤原幸一, 鈴木陽子, 宮島美穂, 山川俊貴, 加納学
自動制御連合講演会(CD-ROM), 2014年11月10日, 自動制御連合講演会, 日本語
2014年11月10日 - 2014年11月10日, てんかん患者は，てんかん発作によって事故を起こしたり怪我を負うことがあるが，発作起始前にアラームを発報できれば，患者は身を守ることができると期待される．一方，心拍間隔は自然にゆらぎがあり，これを心拍変動（HRV）と呼ぶが，てんかん発作はHRVに影響するため，HRVを解析することで発作兆候を検出できる可能性がある．そこで本研究は，HRVと異常検出手法であるOne Class SVMに基づいたてんかん発作兆候監視アルゴリズムを提案する．提案法を臨床データに適用した結果，発作起始の1分前に発作兆候を検出することができた．

心拍変動解析を用いたドライバの眠気検出の開発とそのスマートフォンアプリへの実装　　　　　　　　　　　　　　　
阿部恵里花, 藤原幸一, 平岡敏洋, 山川俊貴, 加納学
計測自動制御学会 システム・情報部門学術講演会2014(SSI2014)講演論文集, 2014年11月, 日本語
2014年11月 - 2014年11月

心拍変動解析と多変量統計的プロセス管理によるドライバの眠気検出
阿部恵里花, 藤原幸一, 平岡敏洋, 山川俊貴, 加納学
日本人間工学会第55回大会講演集, 2014年06月, 日本語
2014年06月 - 2014年06月

心拍変動解析に基づくてんかん発作兆候モニタリングデバイス　　　　　　　　　　　　　　　
藤原 幸一
国際バイオテクノロジー展, 2014年05月, 日本語, 公開講演，セミナー，チュートリアル，講習，講義等
［招待講演］, ［国内会議］

統計的プロセス管理に基づいたてんかん発作兆候監視アルゴリズムの開発
藤原幸一, 橋本啓嗣, 鈴木陽子, 宮島美穂, 山川俊貴, 加納学
計測自動制御学会制御部門マルチシンポジウム(CD-ROM), 2014年03月04日, 日本語
2014年03月04日 - 2014年03月04日

NIR検量線作成のための効率的な波数選択法の開発とその製剤工程への応用
内丸拓, 宮野拓也, 藤原幸一, 加納学, 田邊秀章, 中川弘司, 渡部知行, 脇山尚樹
化学工学会秋季大会研究発表講演要旨集(CD-ROM), 2014年, 日本語
2014年 - 2014年

Development of Drowsy Driving Accident Prediction by Heart Rate Variability Analysis
Erika Abe, Koichi Fujiwara, Toshihiro Hiraoka, Toshitaka Yamakawa, Manabu Kano
2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014年, IEEE, 英語
2014年 - 2014年, Drowsy driving accidents can be prevented if it can be predicted in advance. The present work aims to develop a new method for predicting a drowsy driving accident based on the fact that the autonomic nervous function affects heart rate variability (HRV), which is the fluctuation of the RR interval (RRI) obtained from an electrocardiogram (ECG). The proposed method uses HRV features derived through HRV analysis as input variables of multivariate statistical process control (MSPC), which is a well-known anomaly detection method in process control. Driving simulator experiments demonstrated that driver drowsiness was successfully predicted seven out of eight cases before drowsy driving accidents occur.

Epileptic Seizure Monitoring by One-Class Support Vector Machine
Koichi Fujiwara, Erika Abe, Yoko Suzuki, Miho Miyajima, Toshitaka Yamakawa, Manabu Kano, Taketoshi Maehara, Katsuya Ohta, Tetsuo Sasano
2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014年, IEEE, 英語
2014年 - 2014年, Although refractory epileptic patients suffer from uncontrolled seizures, their quality of life (QoL) may be improved if the seizure can be predicted in advance. On the hypothesis that the excessive neuronal activity of epilepsy affects the autonomic nervous system and the fluctuation of the R-R interval (RRI) of an electrocardiogram (ECG), called heart rate variability (HRV), reflects the autonomic nervous function, there is possibility that an epileptic seizure can be predicted through monitoring RRI data. The present work proposes an HRV-based epileptic seizure monitoring method by utilizing One Class Support Vector Machine (OCSVM). Various HRV features are derived from the RRI data in both the interictal period and the preictal period, and an OCSVM-based seizure prediction model is built from the interictal HRV features. The application results of the proposed monitoring method to a clinical data are reported.

Real-Time Heart Rate Variability Monitoring Employing a Wearable Telemeter and a Smartphone
Toshitaka Yamakawa, Koichi Fujiwara, Miho Miyajima, Erika Abe, Manabu Kano, Yuichi Ueda
2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014年, IEEE, 英語
2014年 - 2014年, A telemetry system for the measurement of heart rate variability (HRV) has been developed with a low-cost manufacturing process and a low-power consumption design. All the components and functions for the RRI measurement were implemented on a wearable telemeter which can operate for up to 10 hours with a rechargeable Li-Polymer battery, and the RRI data is stored into a smartphone via a Bluetooth wireless transmission. In a long-term measurement of a young subject that extended over 48 hours in total, the results showed a 1% probability of recurring errors. The obtained results suggest that the proposed fully-wearable system enables the continuous monitoring of HRV for both clinical care and healthcare operated by a non-expert.

Application of Clustering-based Variable Selection Method for PLS Modeling in Near-Infrared Spectroscopic Spectra　　　　　　　　　　　　　　　
Takuya Miyano, Hiroshi Nakagawa, Koichi Fujiwara, Manabu Kano
AAPS Annual Meeting and Exposition, San Antonio, US, 2013年11月, 英語
2013年11月 - 2013年11月

てんかん臨床症状起始前に心拍変動上昇を示した1症例
鈴木陽子, 橋本啓嗣, 藤原幸一, 宮島美穂, 山川俊貴, 加納学, 前原健寿, 太田克也, 笹野哲郎, 松浦雅人, 松島英介
てんかん研究, 2013年09月30日, 日本語
2013年09月30日 - 2013年09月30日

Feature Extraction of Heart Rate Variability Change Prior to Epileptic Seizures　　　　　　　　　　　　　　　
Yoko Suzuki, Hirotsugu Hashimoto, Koichi Fujiwara, Miho Miyajima, Toshitaka Yamakawa, Manabu Kano, Taketoshi Maehara, Katsuya Ohta, Tetsuo Sasano, Masato Matsuura, Eisuke Matsushima
The SICE Annual Conference, Paper MoBT14.16, Nagoya, Japan, 2013年09月, 英語
2013年09月 - 2013年09月

Analysis of Changes in HRV of Epileptic Patients in Preictal Period
Hashimoto Hirotsugu, Fujiwara Koichi, Suzuki Yoko, Miyajima Miho, Yamakawa Toshitaka, Kano Manabu, Maehara Taketoshi, Matsuura Masato
生体医工学, 2013年07月, Japanese Society for Medical and Biological Engineering, 英語
2013年07月 - 2013年07月

Heart Rate Variability Analysis for Epileptic Seizure Prediction　　　　　　　　　　　　　　　
APSIPA BioSiPS Workshop, 2013年03月28日, APSIPA, 英語, 口頭発表（招待・特別）
［招待講演］, ［国際会議］

検量線構築におけるNCスペクトラルクラスタリングとgroup Lassoを用いた効率的な波長選択
藤原幸一, 加納学
計測自動制御学会制御部門大会(CD-ROM), 2013年03月05日, 日本語
2013年03月05日 - 2013年03月05日

心拍変動解析を用いたストレス状態の短時間推定
天ケ瀬匡昭, 藤原幸一, 加納学, 山川俊貴
計測自動制御学会制御部門大会(CD-ROM), 2013年03月05日, 日本語
2013年03月05日 - 2013年03月05日

ソフトセンサ構築における変数間の相関関係に基づいた効率的な変数選択手法
藤原幸一, 加納学
化学工学会年会研究発表講演要旨集(CD-ROM), 2013年02月17日, 日本語
2013年02月17日 - 2013年02月17日

Feature extraction of heart rate variability for epileptic seizure
Suzuki Y, Hashimoto H, Fujiwara K, Miyajima M, Yamakawa T, Kano M, Maehara T, Ohta K, Sasano T, Matsuura M, Matsushima E
Proceedings of the SICE Annual Conference, 2013年, 英語
2013年 - 2013年, Although refractory epileptic patients suffer from uncontrolled seizures, their quality of life may be improved if an epileptic seizure can be predicted in advance. In the preictal period, an excessive neuronal activity of epilepsy affects the autonomic nervous system. Since heart rate variability (HRV) reflects the autonomic nervous function, an epileptic seizure may be predicted through monitoring HRV data of an epileptic patient. In the present study, preictal HRV data of epileptic patients were analyzed for developing an epilepsy seizure prediction system. The preictal HRV data of nine epileptic seizure episodes of four patients were collected, and their HRV indexes were calculated. The analysis results showed that frequency HRV indexes changed at least one minute before seizure onset in all seizure episodes. The possibility of realizing a HRV-based seizure prediction system was shown.

Efficient input variable selection for calibration model design
Koichi Fujiwara, Manabu Kano
2013 9th Asian Control Conference, ASCC 2013, 2013年, 英語
2013年 - 2013年, In pharmaceutical processes, near-infrared spec-troscopy (NIRS) is a key tool of process analytical technology (PAT), and very accurate calibration models need to be developed with NIR spectra. Partial least squares (PLS) regression, in particular, is accepted as a useful technique for calibration model design. When a calibration model is built, appropriate input variables have to be selected to achieve high estimation performance. Recently, a new methodology for selecting input variables based on nearest correlation spectral clustering (NCSC) has been proposed. Referred to as NCSC-based variable selection (NCSC-VS), it clusters input variables into some variable groups based on the correlation by using NCSC, and selects a few variable groups according to their contribution to output estimates. We report here an industrial application of NCSC-VS to calibration model design for a pharmaceutical process. NCSC-VS can select important variables and improve the estimation performance greatly in comparison to conventional variable selection methods. © 2013 IEEE.

Heart Rate Variability Features for Epilepsy Seizure Prediction
Hirotsugu Hashimoto, Koichi Fujiwara, Yoko Suzuki, Miho Miyajima, Toshitaka Yamakawa, Manabu Kano, Taketoshi Maehara, Katsuya Ohta, Tetsuo Sasano, Masato Matsuura, Eisuke Matsushima
2013 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2013年, IEEE, 英語
2013年 - 2013年, Although refractory epileptic patients suffer from uncontrolled seizures, their quality of life (QoL) may be improved if an epileptic seizure can be predicted in advance. In the preictal period, an excessive neuronal activity of epilepsy affects the autonomic nerve system. Since the fluctuation of the R-R interval (RRI) of an electrocardiogram (ECG), called heart rate variability (HRV), reflects the autonomic nervous function, an epileptic seizure may be predicted through monitoring HRV data of an epileptic patient.
In the present work, preictal and interictal HRV data of epileptic patients were analyzed for developing an epilepsy seizure prediction system. The HRV data of five patients were collected, and their HRV features were calculated. The analysis results showed that frequency HRV features, such as LF and LF/HF, changed at least one minute before seizure onset in all seizure episodes. The possibility of realizing a HRV-based seizure prediction system was shown through these analysis.

Development of a Wearable HRV Telemetry System to be Operated by Non-Experts in Daily Life
Toshitaka Yamakawa, Koichi Fujiwara, Manabu Kano, Miho Miyajima, Yoko Suzuki, Taketoshi Maehara, Katsuya Ohta, Tetsuo Sasano, Masato Matsuura, Eisuke Matsushima
2013 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2013年, IEEE, 英語
2013年 - 2013年, A telemetry system for the measurement of heart rate variability (HRV) with automatic gain control has been developed with a low-cost manufacturing process and a low-power consumption design. The proposed automatic gain control technique provided highly reliable RR interval (RRI) detection for subjects of different ages, and enabled the subjects to use the system without any expert knowledge of the electrocardiogram (ECG) measurement. All the components and functions for the RRI measurement were implemented on a wearable telemeter which can operate for up to 440 h with a CR2032 coin battery, and the wirelessly transmitted RRI data is stored into a PC by a receiver via a USB connection. The errors of the RRI detection occurred at less than 2% probability in subjects of five different ages. In a long-term measurement of a young subject that extended over 48 h, the results showed a 0.752% probability of recurring errors. The obtained results suggest that the proposed system enables the long-term monitoring of HRV for both clinical care and healthcare operated by a non-expert.

Epileptic seizure monitoring by using multivariate statistical process control
Hirotsugu Hashimoto, Koichi Fujiwara, Yoko Suzuki, Miho Miyajima, Toshitaka Yamakawa, Manabu Kano, Taketoshi Maehara, Katsuya Ohta, Tetsuo Sasano, Masato Matsuura, Eisuke Matsushima
IFAC Proceedings Volumes (IFAC-PapersOnline), 2013年, 英語
2013年 - 2013年, Although refractory epileptic patients suffer from uncontrolled seizures, their quality of life (QoL) may be improved if the seizure can be predicted in advance. In the preictal period, the excessive neuronal activity of epilepsy affects the autonomic nervous system. Since the fluctuation of the R-R interval (RRI) of an electrocardiogram (ECG), called heart rate variability (HRV), reflects the autonomic nervous function, an epileptic seizure may be predicted through monitoring RRI data. The present work proposes an HRV-based epileptic seizure monitoring method by utilizing multivariate statistical process control (MSPC) technology. Various HRV features are derived from the RRI data in both the interictal period and the preictal period recorded from epileptic patients, and an MSPC-based seizure prediction model is built from the interictal HRV features. The result of applying the proposed monitoring method to a clinical data demonstrates that seizures can be detected at least one minutes prior to the seizure onset. The possibility of realizing an HRV-based seizure monitoring system is shown. © IFAC.

NCスペクトラルクラスタリングを用いたソフトセンサ設計と入力変数選択　　　　　　　　　　　　　　　
第189回委員会・平成24年度第4回研究会, 2012年12月07日, 日本学術振興会プロセスシステム工学第143委員会, 日本語, 口頭発表（招待・特別）
［招待講演］

線形回帰モデルにおけるNCスペクトラルクラスタリングとgroup Lassoを用いた効率的な入力変数選択
藤原幸一, 加納学
自動制御連合講演会(CD-ROM), 2012年11月17日, 日本語
2012年11月17日 - 2012年11月17日

線形回帰モデルにおけるNCスペクトラルクラスタリングを用いた効率的な入力変数選択
藤原幸一, 澤田宏, 加納学
電子情報通信学会技術研究報告, 2012年10月31日, 一般社団法人電子情報通信学会, 日本語
2012年10月31日 - 2012年10月31日, 生産現場では,これまで生産性向上のため操業データの解析に取り組んできた.操業データ解析では,予測精度の高い線形回帰モデルの効率的な構築が成功の鍵を握るが,そのためには適切に回帰に用いる変数を選択する必要がある.本研究では,変数間の相関関係に基づくクラスタリング手法であるNCスペクトラルクラスタリング(NCSC)を用いた変数選択手法を提案する.提案法では,NCSCを用いて入力変数候補をいくつかの変数グループに分類し,各変数グループごとの出力への寄与率を用いて入力変数として採用する変数グループを選択する.これをNCSC型変数選択(NCSC-VS)と呼ぶ.本研究では,化学プロセスの実データを対象としたケーススタディにより提案法の有効性を検証した.

An efficient Input Wavelength Selection for a NIR Calibration Model using NC Spectral Clustering　　　　　　　　　　　　　　　
SPO2012, 2012年10月25日, Academy of Science for Higher Education of Ukraine, 英語, 口頭発表（招待・特別）
［招待講演］

効率的なソフトセンサ構築のための入力変数選択
藤原幸一, 澤田宏, 加納学
計測自動制御学会制御部門大会(CD-ROM), 2012年03月13日, 日本語
2012年03月13日 - 2012年03月13日

局所PLSを用いた多品種バッチプロセスの製品品質推定
北川裕一, 河野浩司, 真子秀樹, 藤原幸一, 加納学, 長谷部伸治
化学工学会秋季大会研究発表講演要旨集(CD-ROM), 2010年08月06日, 公益社団法人 化学工学会, 日本語
2010年08月06日 - 2010年08月06日

Correlation-based spectral clustering for flexible soft-sensor design
Koichi Fujiwara, Manabu Kano, Shinji Hasebe
IFAC Proceedings Volumes (IFAC-PapersOnline), 2010年, 英語
2010年 - 2010年, The current issues concerning soft-sensors are how to cope with changes in process characteristics and how to cope with parallelized, slightly different, multiple processes. To make soft-sensors adaptive and flexible, the development of practical design techniques, instead of impracticable ideas, is crucial; this is the motivation of the present research. In practice, it is difficult to successfully apply a single soft-sensor to parallelized production devices due to their individual difference. Since the individual difference is expressed as difference of the correlation among variables, it is useful to classify samples into multiple clusters according to the correlation in order to adopt a multi-model approach. In the present work, a new correlation-based clustering method, referred to as NC-spectral clustering, is proposed by integrating the nearest correlation (NC) method and spectral clustering. The NC method can detect samples that are similar to the query from the viewpoint of the correlation. In the proposed method, the NC method is used for constructing the weighted graph that expresses the correlation-based similarities between samples and the constructed graph is partitioned by using spectral clustering. In addition, a new soft-sensor design method is proposed on the basis of the proposed NC-spectral clustering. The superiority of the proposed method over conventional methods is demonstrated through a numerical example and a case study of parallelized batch processes. © 2009 IFAC.

変数間の相関関係に基づいたクラスタリング手法の開発とソフトセンサへの応用
藤原幸一, 加納学, 長谷部伸治
化学工学会秋季大会研究発表講演要旨集(CD-ROM), 2009年08月16日, 公益社団法人 化学工学会, 日本語
2009年08月16日 - 2009年08月16日

Correlation-based pattern recognition and its application to adaptive soft-sensor design
Fujiwara K, Kano M, Hasebe S
IFAC Proceedings Volumes (IFAC-PapersOnline), 2009年, 英語
2009年 - 2009年

Development of correlation-based pattern recognition and its application to adaptive soft-sensor design
Koichi Fujiwara, Manabu Kano, Shinji Hasebe
ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings, 2009年, 英語
2009年 - 2009年, Although linear regression is a simple and useful method to build process models, they do not always function well in practice due to not only changes in process characteristics but differences of specifities between the equipments when multiple equipments are operated in parallel. To cope with them, the correlation between variables should be considered. In the present work, a new pattern recognition method, referred to as Nearest Correlation (NC) method that can select samples whose correlations are similar to the query point without supervised signal is proposed. The proposed procedures are as follows: 1) Subtract the query point from all the other samples. 2) Calculate the correlation coefficient between all pairs of arbitrary two subtracted samples, and the pairs whose correlation coefficients are close to -1 are selected. 4) Derive the subspace containing the query point from the selected samples. 4) The Q statistics between all samples and the derived subspace are calculated, and the samples whose Q statistic is small are selected as the similar samples to the query point. In addition, a new soft-sensor design method integrating the NC method and Just-In-Time (JIT) modeling is proposed. This method is referred to as Correlation-based JIT (C-JIT) modeling, and it cope with the changes in process characteristics and the differences of specifities between the equipments. The usefulness of the proposed NC method and C-JIT modeling are demonstrated through case studies of CSTR process. © 2009 SICE.

Development and Application of a New Spectral Clustering Algorithm　　　　　　　　　　　　　　　
Koichi Fujiwara, Manabu Kano, Shinji Hasebe
AIChE Annual Meeting, paper 507d, Nashville, US, Nov. 8-13, 2009年, 英語
2009年 - 2009年

相関型Just‐In‐Timeモデリングのナンバリングアッププロセスへの適用
藤原幸一, 向井洋介, 加納学, 長谷部伸治
化学工学会秋季大会研究発表講演要旨集(CD-ROM), 2008年08月24日, 日本語
2008年08月24日 - 2008年08月24日

変数間の相関に着目したクラスタリング手法およびその多変量統計モデリングへの利用
向井洋介, 藤原幸一, 加納学, 長谷部伸治
化学工学会秋季大会研究発表講演要旨集(CD-ROM), 2008年08月24日, 公益社団法人 化学工学会, 日本語
2008年08月24日 - 2008年08月24日

相関型Just‐In‐Timeモデリングの化学プロセスへの適用
藤原幸一, 加納学, 長谷部伸治, 滝波明敏
システム制御情報学会研究発表講演会講演論文集(CD-ROM), 2008年05月16日, 日本語
2008年05月16日 - 2008年05月16日

プロセス特性変化に着目した相関型Just‐In‐Timeモデリングによるソフトセンサ設計
藤原幸一, 加納学, 長谷部伸治
化学工学会年会研究発表講演要旨集, 2008年02月17日, 公益社団法人 化学工学会, 日本語
2008年02月17日 - 2008年02月17日

Development of a new pattern recognition method and its application to just-in-time modeling
Koichi Fujiwara, Yosuke Mukai, Manabu Kano, Shinji Hasebe
AIChE Annual Meeting, Conference Proceedings, 2008年, 英語
2008年 - 2008年

Soft-sensor Design for Time-Varying Processes through Correlation-Based Just-In-Time Modeling　　　　　　　　　　　　　　　
Koichi Fujiwara, Manabu Kano, Shinji Hasebe
Proceedings of Fifth International Conference on Foundations of Computer-Aided Process Operations (FOCAPO 2008), pp.341-344, Cambridge, MA, June 29-July 2, 2008年, 英語
2008年 - 2008年

Correlation-Based Just-In-Time Modeling for Soft-Sensor Design
Koichi Fujiwara, Manabu Kano, Shinji Hasebe
18TH EUROPEAN SYMPOSIUM ON COMPUTER AIDED PROCESS ENGINEERING, 2008年, ELSEVIER SCIENCE BV, 英語
2008年 - 2008年, Soft-sensors are widely used for estimating product quality or other key variables when on-line analyzers are not available. However their estimation performance deteriorates when the process characteristics change. To cope with such changes and update the model, recursive methods such as recursive PLS and Just-In-Time (JIT) modeling have been developed. When process characteristics change abruptly, however, they do not always function well. In the present work, a new method for constructing soft-sensors based on a JIT modeling technique is proposed. In the proposed method, referred to as correlation-based JIT modeling, the samples used for local modeling are selected on the basis of the correlation among variables instead of or together with distance. The proposed method can adapt a model to changes in process characteristics and also cope with process nonlinearity. The superiority of the proposed method over the conventional methods is demonstrated through a case study of a CSTR process in which catalyst deactivation and recovery are considered as changes in process characteristics.

Batch Process Modeling and Optimization through Wavelet Coefficient Regression　　　　　　　　　　　　　　　
Yosuke Mukai, Kenichi Tasaka, Koichi Fujiwara, Manabu Kano, Shinji Hasebe
Proceedings of International Symposium on Design, Operation and Control of Chemical Processes (PSE ASIA 2007), CD-ROM, F-12, Xi’an, China, Aug. 15-18, 2007年, 英語
2007年 - 2007年

ウェーブレット解析と多変量解析を用いたバッチプロセス操作プロファイルの最適化
藤原幸一, 加納学, 長谷部伸治, 大野弘
化学工学会秋季大会研究発表講演要旨集(CD-ROM), 2006年08月16日, 公益社団法人 化学工学会, 日本語
2006年08月16日 - 2006年08月16日

Modeling and Optimization of Batch Process Operation through Wavelet Analysis and Multivariate Analysis　　　　　　　　　　　　　　　
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno
AIChE Annual Meeting, paper 125a, Sa Francisco, CA, Nov. 13-17, 2006年, 英語
2006年 - 2006年

Operation profile optimization for batch process through wavelet analysis and multivariate analysis
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno
2006 SICE-ICASE INTERNATIONAL JOINT CONFERENCE, VOLS 1-13, 2006年, IEEE, 英語
2006年 - 2006年, A new regression method, wavelet coefficient regression (WCR), based on wavelet analysis and multivariate analysis is proposed. It can build a statistical model that relates operation profiles with product quality in a batch process. In WCR, selected wavelet coefficients of operation profiles are used as input variables of a statistical model; thus time-related information such as timing of manipulation can be successfully modeled. In addition, by integrating multivariate analysis and wavelet analysis, WCR can cope with correlation of input variables. As a result, WCR enables us to build an accurate statistical model of a batch process. On the basis of WCR, a data-driven method for improving product quality in a batch process is also proposed. The proposed method can determine operation profiles that can achieve the desired product quality and optimize the operation profiles under a given performance index and various constraints. The usefulness of the proposed WCR and profile optimization method is demonstrated through a case study of lysine production based on a semi-batch fermentation process.

運転データに基づく階層型品質改善システムの開発―効果的な操作変数の選択―
藤原幸一, LEE Seunghyun, 加納学, 長谷部伸治
化学工学会秋季大会研究発表講演要旨集(CD-ROM), 2005年09月05日, 日本語
2005年09月05日 - 2005年09月05日

統計的手法に基づく階層型品質改善システムの開発 ペニシリン製造プロセスへの適用
LEE Seunghyun, 藤原幸一, 加納学, 長谷部伸治
システム制御情報学会研究発表講演会講演論文集, 2005年05月18日, 日本語
2005年05月18日 - 2005年05月18日

統計的品質改善のための枠組み
加納学, 藤原幸一, 長谷部伸治
システム制御情報学会研究発表講演会講演論文集, 2005年05月18日, 日本語
2005年05月18日 - 2005年05月18日

統計的手法に基づく階層型品質改善システムの開発
LEE Seunghyun, 藤原幸一, 加納学, 長谷部伸治
計測自動制御学会関西支部学生研究発表会講演論文集 平成17年, 2005年, 日本語
2005年 - 2005年

Product quality improvement using multivariate data analysis
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno
IFAC Proceedings Volumes (IFAC-PapersOnline), 2005年, 英語
2005年 - 2005年, A data-based methodology for improving product quality is proposed. Referred to as Data-Driven Quality Improvement (DDQI), the proposed method can cope with qualitative as well as quantitative variables, determine the operating conditions that can achieve the desired product quality, optimize operating condition under various constraints, and thus can provide useful information to improve product quality. This paper aims to formulate DDQI and demonstrate its usefulness with an case study of an industrial steel process. in addition, possible extensions and remaining problems are discussed based on the authors' experience of succeeding in improving product quality by applying DDQI to several industrial processes. Copyright © 2005 IFAC.

製品品質・歩留り改善のための操業条件推定法
藤原幸一, 加納学, 長谷部伸治, 大野弘
化学工学会年会研究発表講演要旨集, 2004年03月02日, 日本語
2004年03月02日 - 2004年03月02日

Data-Driven Approach for Improving Product Yield
Koichi Fujiwara, Manabu Kano, Shinji Hasebe, Hiromu Ohno
The 10th Asian Pacific Confederation of Chemical Engineering, 2004年, 公益社団法人 化学工学会, 英語
2004年 - 2004年, A data-driven methodology for improving product yield by integrating principal component analysis (PCA) and liner discriminant analysis (LDA) is proposed. Referred to as Data-Driven Quality Improvement (DDQI), the proposed method can cope with qualitative as well as quantitative quality variables, determine the operating conditions that can achieve the desired product quality, optimize the operating condition under various constraints, and also evaluate the validity of the results. The relationship between product quality and operating conditions can be modeled by PCR when quality variables are quantitative. On the other hand, LDA can be used for modeling when quality variables are qualitative, e.g., good or bad. For such a qualitative quality variable, the yield, that is the percentage of good products to all products, can be specified on the basis of histograms for given categories. The histograms can be obtained from operation data, and they can be drawn against the axis defined by LDA. Once the desired yield is specified, the operating condition that can achieve the desired yield can be determined. The usefulness of the proposed method is demonstrated through a case study.

Data-Driven Quality Improvement: Handling Qualitative Variables　　　　　　　　　　　　　　　
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno
IFAC Symposium on Dynamics and Control of Process Systems, 2004年, 英語
2004年 - 2004年

Data-driven approach for product quality/yield improvement: How to specify target of qualitative quality variables
Manabu Kano, Koichi Fujiwara, Shinji Hasebe, Hiromu Ohno
AIChE Annual Meeting, Conference Proceedings, 2004年, 英語
2004年 - 2004年, How can we improve product quality and yield? More than ever, the answer to this question is vital as product life cycles are getting shorter and international competition is getting keener. Since this question arises repeatedly when a new product is developed, quality improvement should be achieved faster and in a more systematic way. In the present work, a data-based methodology for improving product quality/yield is proposed. Referred to as Data-Driven Quality Improvement (DDQI), the proposed method can cope with qualitative as well as quantitative variables, determine the operating conditions that can achieve the desired product quality, optimize operating condition under constraints, and also evaluate the validity of the results. In DDQI, a space where operating conditions can achieve the desired quality is searched within subspace spanned by principal components. However, desired product quality cannot be specified quantitatively when the quality variable is qualitative, e.g., whether there is any defect on the surface of specialty sheet steel. For such a qualitative quality variable, yield, i.e., the percentage of good products to all products, can be specified instead of the quality itself. In the proposed method, the yield is defined on the basis of histograms for two categories such as good and bad. The histograms can be obtained from operation data, and they can be drawn against the axis defined by a discriminant function. Once the desired yield is specified, operating conditions that can achieve the desired yield can be easily found. This paper aims to formulate DDQI and demonstrate its usefulness with an illustrative example. In addition, possible extensions and remaining problems are discussed based on the authors' experience of succeeding in improving product quality by applying DDQI to several industrial processes.

主成分回帰を用いた製品品質・歩留り改善のための最適運転条件推定法
藤原幸一, 加納学, 長谷部伸治, 大野弘
システム制御情報学会研究発表講演会講演論文集, 2004年, 日本語
2004年 - 2004年

AI-MAILs - メディカルAI人材養成産学協働拠点・講義　　　　　　　　　　　　　　　
名古屋大学医学部
2021年09月 - 現在

プログラミング演習　　　　　　　　　　　　　　　
名古屋大学
2020年10月 - 現在

先進プロセス情報論　　　　　　　　　　　　　　　
名古屋大学
2019年04月 - 現在

線形代数　　　　　　　　　　　　　　　
名古屋大学
2019年04月 - 現在

システム制御　　　　　　　　　　　　　　　
名古屋大学，同志社大学
2015年10月 - 現在

品質管理　　　　　　　　　　　　　　　
京都大学
2014年04月 - 2016年07月

空間データに対する統計的因果探索手法の開発と製品不良原因解明への応用　　　　　　　　　　　　　　　
官民による若手研究者発掘支援事業/共同研究フェーズ
2025年04月 - 2028年03月
NEDO, 名古屋大学, 研究代表者, 24129494

局所電位の周波数情報のカテーテル アブレーション治療への応用と焼灼巣予測AIの開発
科学研究費助成事業
2024年04月01日 - 2027年03月31日
滝川 正晃, 藤原 幸一
日本学術振興会, 基盤研究(C), 東京医科歯科大学, 24K11212

非侵襲的シミュレーションを可能とするコネクトーム基盤型機能外科手術の開発研究
科学研究費助成事業
2022年04月01日 - 2027年03月31日
前澤 聡, Bagarinao E., 臼井 直敬, 齋藤 竜太, 藤原 幸一, 坪井 崇, 夏目 淳
日本学術振興会, 基盤研究(B), 名古屋大学, 22H03184

心拍変動解析によるてんかん発作予知AIシステムの研究開発
医工連携・人工知能実装研究事業
2021年04月 - 2026年03月
AMED, 名古屋大学, 研究代表者, 競争的資金

認知機能低下に関する修正可能な因子の特定：マルチモーダルな生体データの利用
科学研究費助成事業
2021年04月01日 - 2025年03月31日
角谷 寛, 藤原 幸一, 角 幸頼, 加納 学, 大道 智恵, 須藤 智志
簡便に取得できるマルチモーダルな生体データを統合的に解析することで、認知機能低下の客観的指標の確立を目指す。そのために、アルツハイマー病およびレビー小体型認知症という有病率の高い二つの認知症のハイリスク群および健常高齢者群を対象に、認知機能および心拍変動などの生体データについてベースライン調査を実施する予定であったが、新型コロナウイルス感染症による影響のために、研究協力機関において健常高齢者を対象としたベースライン調査を実施することができなかった。
そこで、主に医療機関受診者を対象として、ベンゾジアゼピン受容体作動薬とせん妄の関係、心拍変動をもとにした睡眠時無呼吸スクリーニングアルゴリズムの開発、レビー小体型認知症のハイリスク群であるレム睡眠行動障害などについての研究を実施してきた。
日本学術振興会, 基盤研究(B), 滋賀医科大学, 23K21863

第二世代ヘルスケアIoT技術を支える生体計測・解析プラットフォームの基盤構築
科学研究費助成事業
2021年04月01日 - 2025年03月31日
山川 俊貴, 藤原 幸一, 宮島 美穂, 下野 僚子
日本学術振興会, 基盤研究(B), 熊本大学, 21H03855

認知機能低下に関する修正可能な因子の特定：マルチモーダルな生体データの利用
科学研究費助成事業
2021年04月01日 - 2025年03月31日
角谷 寛, 藤原 幸一, 角 幸頼, 加納 学, 大道 智恵, 須藤 智志
日本学術振興会, 基盤研究(B), 滋賀医科大学, 21H03851

ウェアラブルデバイスによる熱中症発症予防のための熱中症アラームシステム
科研費基盤B
2019年04月 - 2023年03月
藤原 幸一
JSPS, 研究代表者, 競争的資金

非専門医によるてんかん診療質向上のための診療支援AI基盤の創出
さきがけ
2018年10月 - 2022年09月
藤原 幸一
JST, 研究代表者, 競争的資金

心拍変動解析と機械学習を用いたてんかん発作予知ＡＩの実証研究　　　　　　　　　　　　　　　
研究助成
2021年04月 - 2022年03月
IO-DATA 財団, 研究代表者

サイボーグ技術によって身体を再定義し，自己の能力を従来の人の限界を超えて高め誰もが自己実現できる社会
ムーンショット型研究開発事業 新たな目標検討のためのビジョン公募
2021年02月 - 2021年08月
JST, 名古屋大学, 研究代表者

心拍変動解析に基づくCOVID-19重症化予測機械学習アルゴリズムの開発研究　　　　　　　　　　　　　　　
新型コロナウィルス感染症対策 助成プログラム
2020年07月 - 2021年06月
中谷医工計測技術振興財団, 研究分担者

COVID-19重症化予測AIの開発　　　　　　　　　　　　　　　
牧誠記念研究助成
2020年07月 - 2021年03月
藤原幸一
名古屋大学, 名古屋大学, 研究代表者

心電図解析によるてんかん発作の検知・予知システム確立のための広帯域頭蓋内脳波解析　　　　　　　　　　　　　　　
科研費基盤C
2019年04月 - 2021年03月
前原健寿
JSPS, 競争的資金

AIによる教育と医療で共有可能なADHDスクリーニング及び治療適正化方法の開発　　　　　　　　　　　　　　　
科研費基盤C
2018年04月 - 2021年03月
阪上由子
JSPS, 競争的資金

マルチモダリティ生体信号計測によるてんかん発作自動検出および重症度評価技術の確立　　　　　　　　　　　　　　　
科研費基盤C
2018年04月 - 2021年03月
宮島美穂
JSPS, 競争的資金

てんかん発作オンデマンド介入のための発作予測システムの開発
先端計測プログラム・加速費
2019年11月 - 2020年03月
藤原 幸一
AMED, 研究代表者, 競争的資金

卓越研究員研究費　　　　　　　　　　　　　　　
卓越研究員制度
2018年11月 - 2020年03月
藤原 幸一
JSPS, 研究代表者, 競争的資金

リアルタイム心拍変動解析技術を用いたヘルスケアサービス開発　　　　　　　　　　　　　　　
インキュベーションプログラム
2018年04月 - 2020年03月
藤原 幸一
京都大学, 研究代表者, 競争的資金

てんかん発作オンデマンド介入のための発作予測システムの開発
先端計測分析技術・機器開発プログラム
2017年08月 - 2020年03月
藤原 幸一
AMED, 研究代表者, 競争的資金

生理機能に基づくレビー小体型認知症早期診断ウェアラブルデバイスの開発
科研費基盤A
2017年04月 - 2020年03月
角谷寛
JSPS, 競争的資金

ウェアラブルセンシングと人工知能の融合によるクラウドてんかん発作診療支援システムの開発　　　　　　　　　　　　　　　
挑戦的研究
2017年04月 - 2020年03月
藤原 幸一
セコム科学技術振興財団, 研究代表者, 競争的資金

てんかん発作オンデマンド介入のための発作予測システムの開発
平成30年度第2回医療分野の研究開発関連の調整費
2018年12月 - 2019年03月
藤原 幸一
内閣府, 研究代表者, 競争的資金

保健医療用人工知能の技術革新と国際競争力向上に資する人材育成に関する研究　　　　　　　　　　　　　　　
厚労科研費
2017年10月 - 2019年03月
奥村貴史
厚生労働省, 競争的資金

夜間・休日を含む小児救急医療体制の最適化及び情報発信方法に関する研究　　　　　　　　　　　　　　　
厚労科研費
2017年04月 - 2019年03月
清水直樹
厚生労働省, 競争的資金

センシング技術を基軸とした健康管理システムの地域特性に基づく分析　　　　　　　　　　　　　　　
科研費基盤C
2017年04月 - 2019年03月
下野僚子
JSPS, 競争的資金

心拍変動解析と機械学習の融合による脳卒中検知システムの基盤技術開発　　　　　　　　　　　　　　　
研究助成
2017年04月 - 2019年03月
藤原 幸一
高橋産業経済研究財団, 研究代表者, 競争的資金

治療抵抗性高血圧症に対する頭側延髄腹外側野の微小血管減圧術-確実な診断技術の開発　　　　　　　　　　　　　　　
科研費基盤C
2016年04月 - 2019年03月
浜崎禎
JSPS, 競争的資金

非専門医のてんかん診療の質改善のためのてんかん診療支援クラウドAIの開発
学術研究助成
2018年01月 - 2018年12月
藤原 幸一
住友電工グループ社会貢献基金, 研究代表者, 競争的資金

ロバスト主成分分析を用いたてんかん発作予知システムの実用化研究　　　　　　　　　　　　　　　
工学研究奨励援助金
2017年10月 - 2018年09月
藤原 幸一
服部報公会, 研究代表者, 競争的資金

クラウド型てんかん発作診療支援AIの開発　　　　　　　　　　　　　　　
研究助成
2017年08月 - 2018年07月
藤原 幸一
村田学術振興財団, 研究代表者, 競争的資金

迷走神経刺激療法有効性事前判定のためのてんかん発作軽減効果予測手法の開発　　　　　　　　　　　　　　　
科研費若手B
2014年04月 - 2018年03月
藤原 幸一
JSPS, 研究代表者, 競争的資金

PLSと構造正則化に基づいた高精度溶銑温度予測モデルの開発　　　　　　　　　　　　　　　
助成金
2015年12月 - 2017年11月
藤原 幸一
JFE21世紀財団, 研究代表者, 競争的資金

心拍変動解析と機械学習に基づいた熱中症発症予測アルゴリズム構築
日本人若手研究者研究助成金
2016年04月 - 2017年03月
藤原 幸一
中島記念国際交流財団, 研究代表者, 競争的資金

てんかん発作発現前の生理的脳内ネットワークの変調に基づいた発作予知理論の実証　　　　　　　　　　　　　　　
科研費基盤C
2014年04月 - 2017年03月
丸田雄一
JSPS, 競争的資金

ウェアラブルHRVセンサを用いたてんかん発作兆候検知システムの開発　　　　　　　　　　　　　　　
科研費基盤B
2013年04月 - 2017年03月
宮島美穂
JSPS, 競争的資金

自動車運転中に特化したてんかん発作兆候監視システム開発およびインタフェース設計　　　　　　　　　　　　　　　
自然科学研究助成
2014年10月 - 2016年09月
藤原 幸一
三菱財団, 研究代表者, 競争的資金

心拍変動解析によるてんかん発作早期予知デバイスの開発　　　　　　　　　　　　　　　
研究助成
2014年04月 - 2015年03月
藤原 幸一
国際科学技術財団, 研究代表者, 競争的資金

心拍変動に基づくてんかん発作兆候検知システムの構築
2014年01月 - 2014年12月
藤原 幸一
住友電工グループ社会貢献基金, 研究代表者, 競争的資金

ネックレス型心拍数ワイヤレス計測デバイスを用いた小型・低コストな車載用居眠り検知システムの基盤技術開発
A-Step シーズ顕在化タイプ
2012年10月 - 2014年03月
山川俊貴
JST, 競争的資金

製品品質改善及び操業安定化のための生産プロセスのモデル化・最適化手法の開発　　　　　　　　　　　　　　　
特別研究員科研費
2008年04月 - 2010年03月
藤原 幸一
JSPS, 研究代表者, 競争的資金

分類システム　　　　　　　　　　　　　　　
特許権, 藤原幸一, 尾崎紀夫, 岩本邦弘, 宮田聖子, 角田 柊二, 国立大学法人東海国立大学機構
特願2022-169896, 2022年10月24日

不整脈重症度分類装置　　　　　　　　　　　　　　　
特許権, 藤原幸一, 永田祥也, 国立大学法人東海国立大学機構
特願2022-077509, 2022年05月10日

居眠り検知装置、検知方法、及びコンピュータプログラム　　　　　　　　　　　　　　　
特許権, 藤原幸一, 加納学, 堀憲太郎, 岩本洋紀, 国立大学法人京都大学
特願2021-029195, 2021年07月09日

熱中症発症検知装置　　　　　　　　　　　　　　　
特許権, 藤原幸一, 太田鴻志, 山川俊貴, 久保孝富
特願2020-097152, 2020年06月03日

無呼吸識別システム及びコンピュータプログラム　　　　　　　　　　　　　　　
特許権, 藤原幸一, 仲山千佳夫, 加納学, 京都大学
特願2015-101782, 2015年05月19日
特開2016-214491, 2016年12月22日
特許6691334, 2020年04月14日
2020年04月28日

睡眠時無呼吸症候群判定装置、睡眠時無呼吸症候群判定方法、及び、睡眠 時無呼吸症候群判定プログラム　　　　　　　　　　　　　　　
特許権, 藤原 幸一, 仲山 千佳夫, 岩崎 絢子
特願2019-023217, 2019年02月13日

てんかん発作予測装置、心電指標データの分析方法、発作予測コンピュー タプログラム、モデル構築装置、モデル構築方法、モデル構築コンピュータプログラム　　　　　　　　　　　　　　　
特許権, 藤原幸一, 坂根史弥, 京都大学
特願2018-181414, 2018年09月27日

眠気検出方法及び眠気検出装置　　　　　　　　　　　　　　　
特許権, 山川俊貴, 藤原幸一, 平岡敏洋, 阿部恵里花, 京都大学
特願2014-114093, 2014年06月06日
特開2015-226696, 2015年12月17日
特許6375496
2018年08月03日

てんかん性発作兆候検知装置、てんかん性発作兆候検知モデル生成装置、てんかん性発作兆候検知方法、てんかん性発作兆候検知モデル生成方法、てんかん性発作兆候検知プログラムおよびてんかん性発作兆候検知モデル生成プログラム　　　　　　　　　　　　　　　
特許権, 加納 学, 藤原 幸一, 京都大学
特願2013-258494, 2013年12月13日
特開2015-112423, 2015年06月22日
特許6344912
2018年06月01日

演算装置、検知装置、演算方法、及び、コンピュータプログラム　　　　　　　　　　　　　　　
特許権, 藤原幸一, 宮谷将太, 京都大学
特願2018-90592, 2018年05月09日

予測モデル構築装置、方法、及びプログラム、並びに発電量予測装置、及び方法　　　　　　　　　　　　　　　
特許権, 藤原 幸一, 須山敬之, 日本電信電話株式会社
特願2011-240543, 2011年11月01日
特開2013-99143, 2013年05月20日
特許5661594
2014年12月12日

センサ情報解析装置、携帯情報端末間通信制御装置、方法、及びプログラム　　　　　　　　　　　　　　　
特許権, 藤原 幸一, 竹内考, 日本電信電話株式会社
特願2012-152618, 2012年07月06日
特開2014-17605, 2014年01月30日

プラント制御情報生成装置及び方法、並びにそのためのコンピュータプログラム　　　　　　　　　　　　　　　
特許権, 加納学, 藤原幸一, 京都大学
特願2009-151745, 2009年06月26日
特開2011-008562, 2011年01月13日
特許5457737
2014年01月07日

変数決定方法、変数決定装置、プログラム及び記録媒体　　　　　　　　　　　　　　　
特許権, 加納学, 藤原幸一, 京都大学
特開2008-517936, 2007年05月29日

操作変数選択装置,操作変数選択方法,操作変数選択プログラムおよびそれを記録したコンピュータ読み取り可能な記録媒体　　　　　　　　　　　　　　　
特許権, 加納学, 藤原幸一
特開2006-323523, 2006年11月30日

七尾市鵬学園高校 出前授業　　　　　　　　　　　　　　　
2017年09月05日
講師
七尾市青年会議所

京都市立衣笠小学校 出前授業　　　　　　　　　　　　　　　
2016年10月28日
講師
出前授業
京都新聞
ソフィアがやってきた

鹿児島県立種子島高校 出前授業　　　　　　　　　　　　　　　
2016年10月10日
講師
出前授業
西之表市