Updated on 2021/11/17

写真a

 
FUJII Keisuke
 
Organization
Graduate School of Informatics Department of Intelligent Systems 1 Associate professor
Graduate School
Graduate School of Informatics
Undergraduate School
School of Informatics Department of Computer Science
School of Engineering Electrical Engineering, Electronics, and Information Engineering
Title
Associate professor
Contact information
メールアドレス
External link

Degree 3

  1. 博士(人間・環境学) ( 2014.3   京都大学 ) 

  2. 修士(人間・環境学) ( 2011.3   京都大学 ) 

  3. 学士(総合人間学) ( 2009.3   京都大学 ) 

Research Interests 3

  1. Machine learning

  2. Collective motions

  3. Sports Science

Research Areas 2

  1. Informatics / Intelligent informatics

  2. Life Science / Sports sciences

Current Research Project and SDGs 1

  1. Technologies for explanation and decision making in biological multi-agent motions

Research History 9

  1. Nagoya University   Graduate School of Informatics   Associate professor

    2021.5

      More details

    Country:Japan

    researchmap

  2. Japan Science and Technology Agency   PRESTO   Researcher

    2020.12

      More details

  3. 理化学研究所   Advanced Intelligence Project   Visiting Scientist

    2019.5

      More details

  4. Nagoya University   Graduate School of Informatics   Assistant Professor

    2019.4 - 2021.4

      More details

    Country:Japan

    researchmap

  5. 理化学研究所   革新知能統合研究センター   研究員

    2017.2 - 2019.4

      More details

    Country:Japan

    researchmap

  6. Japan Society for Promotion of Science

    2014.4 - 2017.1

      More details

    Country:Japan

  7. Nagoya University

    2014.4 - 2017.1

      More details

    Country:Japan

  8. 京都大学大学院   人間・環境学研究科   博士課程

    2011.4 - 2014.3

      More details

    Country:Japan

  9. Japan Society for Promotion of Science

    2011.4 - 2014.3

      More details

    Country:Japan

▼display all

Education 2

  1. Kyoto University   Graduate School, Division of Human and Environmental Studies

    2009.4 - 2014.3

      More details

    Country: Japan

  2. Kyoto University   Faculty of Integrated Human Studies

    2005.4 - 2009.3

      More details

    Country: Japan

Professional Memberships 5

  1. JAPANESE SOCIETY OF BIOMECHANICS

      More details

  2. 日本バスケットボール学会

      More details

  3. THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS

      More details

  4. JAPAN SOCIETY OF PHYSICAL EDUCATION, HEALTH AND SPORT SCIENCES

      More details

  5. THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE

      More details

Committee Memberships 11

  1. International Joint Conferences on Artificial Intelligence (IJCAI)   Program Committee  

    2021.8   

      More details

    Committee type:Academic society

  2. International Conference on Learning Representations (ICLR) 2021   Program Committee  

    2021.5   

      More details

    Committee type:Academic society

  3. JSAI2020, 2021   Award committee  

    2020.6 - 2021.6   

      More details

    Committee type:Academic society

  4. Conference on Neural Information Processing Systems (NeurIPS)   Program Committee  

    2019.12 - 2020.12   

      More details

    Committee type:Academic society

  5. Australasian AI conference 2019   Program Committee  

    2019.12   

      More details

    Committee type:Academic society

  6. Workshop on Informatics: WinF 2019-2020   Program Committee  

    2019.11 - 2020.11   

      More details

    Committee type:Academic society

  7. IBIS2019   Program Committee  

    2019.11   

      More details

    Committee type:Academic society

  8. The Japan Society for Basketball Studies   Editorial committee  

    2019.4 - 2021.3   

      More details

    Committee type:Academic society

  9. AAAI Conference on Artificial Intelligence 2019, 2020   Program Committee  

    2019.2 - 2020.2   

      More details

    Committee type:Academic society

  10. Kei-Hiroba (in Japanese Society for Biomechanics) 2020-2021   Organizing Committee  

       

      More details

    Committee type:Academic society

  11. Kei-Hiroba (in Japanese Society for Biomechanics) 2020-2021   Organizing Committee  

       

      More details

    Committee type:Academic society

    researchmap

▼display all

Awards 18

  1. Excellence Award (Soccer Division)

    2021.1   The 10th Sports Data Analysis Competition (Statistics in Sports: A section in Japan Statistical Society)   Evaluation of soccer team defense based on prediction models of ball recovery and being attacked

    Kosuke Toda, Masakiyo Teranishi, Keisuke Kushiro, Keisuke Fujii

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

    researchmap

  2. 口頭発表賞

    2020.12   日本バスケットボール学会 第7回大会  

    藤井 慶輔, 武石 直也, 河原 吉伸, 武田 一哉

     More details

  3. Best Paper Award in 2020

    2020.12   Japanese Neural Network Society   Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables

    Keisuke Fujii, Yoshinobu Kawahara

     More details

  4. Presentation Award

    2020.12   37th Annual Meeting of the Japanese Cognitive Science Society   Investigation of Roles in Group Behavior Using a Coordinative Drawing Task

    Jun Ichikawa, Keisuke Fujii

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

    researchmap

  5. Excellent Student Paper Award (On-demand), Bronze Prize

    2020.11   IEEE 9th Global Conference on Consumer Electronics (GCCE 2020)   Trajectory prediction with imitation learning reflecting defensive evaluation in team sports

    Masakiyo Teranishi, Keisuke Fujii, Kazuya Takeda

     More details

    Award type:Award from international society, conference, symposium, etc.  Country:Japan

  6. Excellent Student Paper Award (On-demand), Bronze Prize

    2020.11   IEEE 9th Global Conference on Consumer Electronics (GCCE 2020)   Trajectory prediction with imitation learning reflecting defensive evaluation in team sports

    Masakiyo Teranishi, Keisuke Fujii, Kazuya Takeda

     More details

    Award type:Award from international society, conference, symposium, etc.  Country:Japan

    researchmap

  7. オープン部門 発表賞

    2020.6   第2回彗ひろば(バイオメカニクス研究会)  

    藤井 慶輔

     More details

  8. 学生部門 発表賞

    2020.6   第2回彗ひろば(バイオメカニクス研究会)   サッカーにおける守備評価を考慮したデータ駆動的集団運動モデリング

    寺西真聖, 藤井慶輔, 武田一哉

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

    researchmap

  9. 学生部門 発表賞

    2020.6   第2回彗ひろば(バイオメカニクス研究会)   サッカーにおける守備評価を考慮したデータ駆動的集団運動モデリング

    寺西真聖, 藤井慶輔, 武田一哉

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

    researchmap

  10. 口頭発表賞

    2019.12   日本バスケットボール学会 第6回大会  

    藤井 慶輔

     More details

  11. Oral Presentation Award

    2019.12   The Japan Society for Basketball Studies   Automatic classification of team strategy using machine learning

    Keisuke Fujii

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  12. Presentation Award

    2019.6   1st Kei-Hiroba (Biomechanics Research Society)   Data-driven spectral analysis for social biomechanics

    Keisuke Fujii, Naoya Takeishi, Yuki Inaba, Benio Kibushi, Motoki Kouzaki, Yoshinobu Kawahara

     More details

  13. 桜舞賞(研究奨励賞)

    2019.3   理化学研究所  

    藤井 慶輔

     More details

  14. べストプレゼンテーション賞

    2018.11   第21回情報論的学習理論ワークショップ   観測量間の動的構造を抽出するベクトル値再生核ヒルベルト空間における動的モード分解

    藤井 慶輔・河原 吉伸

  15. 若手研究優秀賞

    2015.8   第66回日本体育学会   球技における味方を助ける行動―空間マルチスケール性に着目して

    藤井 慶輔・小山 孟志・陸川 章・山田 洋・山本 裕二

  16. 若手研究奨励賞

    2011.3   第140回京都体育学会大会   球技における防御者が意思決定に用いる情報とは何か―倒立振子モデルによるアプローチ―

    藤井 慶輔・進矢正宏・山下大地・小田伸午

  17. サッカー部門 優秀賞

    第10回日本統計学会スポーツ統計分科会スポーツデータ解析コンペティション   サッカーにおけるボール奪取・被有効攻撃予測に基づくチームの守備評価

    戸田康介・寺西真聖・久代恵介・藤井慶輔

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  18. 大会発表賞

    日本認知科学会第37回大会   なぞり課題を用いた運動協調における役割の検討

    市川淳・藤井慶輔

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

▼display all

 

Papers 38

  1. Learning interaction rules from multi-animal trajectories via augmented behavioral model Reviewed

    Keisuke Fujii, Naoya Takeishi, Kazushi Tsutsui, Emyo Fujioka, Nozomi Nishiumi, Ryoya Tanaka, Mika Fukushiro, Kaoru Ide, Hiroyoshi Kohno, Ken Yoda, Susumu Takahashi, Shizuko Hiryu, Yoshinobu Kawahara

    Advances in Neural Information Processing Systems (NeurIPS'21)   Vol. 34   2021.12

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  2. Data-driven Analysis for Understanding Team Sports Behaviors Reviewed

    Keisuke Fujii

    Journal of Robotics and Mechatronics     2021.6

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  3. Data-Driven Analysis for Understanding Team Sports Behaviors Reviewed

    Fujii Keisuke

    Journal of Robotics and Mechatronics   Vol. 33 ( 3 ) page: 505 - 514   2021

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:富士技術出版株式会社  

    <p>Understanding the principles of real-world biological multi-agent behaviors is a current challenge in various scientific and engineering fields. The rules regarding the real-world biological multi-agent behaviors such as those in team sports are often largely unknown due to their inherently higher-order interactions, cognition, and body dynamics. Estimation of the rules from data, i.e., via data-driven approaches such as machine learning, provides an effective way to analyze such behaviors. Although most data-driven models have non-linear structures and high predictive performances, it is sometimes hard to interpret them. This survey focuses on data-driven analysis for quantitative understanding of behaviors in invasion team sports such as basketball and football, and introduces two main approaches for understanding such multi-agent behaviors: (1) extracting easily interpretable features or rules from data and (2) generating and controlling behaviors in visually-understandable ways. The first approach involves the visualization of learned representations and the extraction of mathematical structures behind the behaviors. The second approach can be used to test hypotheses by simulating and controlling future and counterfactual behaviors. Lastly, the potential practical applications of extracted rules, features, and generated behaviors are discussed. These approaches can contribute to a better understanding of multi-agent behaviors in the real world.</p>

    DOI: 10.20965/jrm.2021.p0505

    CiNii Article

  4. Flexible prediction of target motion with internal representation in chase behavior Reviewed

    TSUTSUI Kazushi, FUJII Keisuke, KUDO Kazutoshi, TAKEDA Kazuya

    Proceedings of the Annual Conference of JSAI   Vol. 2021 ( 0 ) page: 2D1OS604 - 2D1OS604   2021

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Japanese Society for Artificial Intelligence  

    <p>Skilled interception behavior often relies on accurate predictions of external objects because there is a large delay in our sensorimotor systems. To deal with the sensorimotor delay, the brain needs to predicts future states of the target based on the current state available, but it is not well understood how we predict the motion of interactive targets such as evasive opponents. Here we conduct one-on-one chase and escape task and estimated the predictive manner of pursuer by analyzing the response behavior to a sudden directional change of evader. In addition, we verified that a prediction as estimated is computationally feasible using neural network models. These suggest that the predictive mechanisms that humans use to compensate for sensorimotor delays during pursuit are more sophisticated than previously thought and that the internal representation acquired through prior experience in similar situations may be useful even in predicting the motion of unknown opponent.</p>

    DOI: 10.11517/pjsai.JSAI2021.0_2D1OS604

    CiNii Article

  5. Evaluation of group behavior sequences based on a prediction model: Application to soccer team defense Reviewed

    TODA Kosuke, TERANISHI Masakiyo, KUSHIRO Keisuke, FUJII Keisuke

    Proceedings of the Annual Conference of JSAI   Vol. 2021 ( 0 ) page: 2D1OS605 - 2D1OS605   2021

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Japanese Society for Artificial Intelligence  

    <p>With the development of measurement technology, data on the movements of actual games in various sports has become available and is expected to be used for strategy and evaluation. In particular, defenses in team sports are generally difficult to be evaluated because they are played as a team and their statistics are not often recorded. Conventional evaluation methods based on predictions of scores are considered to be unstable because they predict rare events in the entire game, and it is difficult to evaluate various plays leading up to the score. On the other hand, evaluation methods based on certain plays that lead to scoring and dominant region are sometimes difficult to evaluate players and teams in relation to their overall performance (e.g., points scored). In this study, we propose a method for evaluating a team's defense from a comprehensive perspective related to the team's performance, based on the prediction of ball recovery and being attacked, which occur more frequently than goals, using player behavior and positional information of all players and the ball. Using data from 45 soccer matches, we examined the relationship between our index and the team's performances in actual matches and the season.</p>

    DOI: 10.11517/pjsai.JSAI2021.0_2D1OS605

    CiNii Article

  6. Physically-interpretable classification of biological network dynamics for complex collective motions. Reviewed International journal

    Keisuke Fujii, Naoya Takeishi, Motokazu Hojo, Yuki Inaba, Yoshinobu Kawahara

    Scientific Reports   Vol. 10 ( 1 ) page: 3005 - 3005   2020.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Understanding biological network dynamics is a fundamental issue in various scientific and engineering fields. Network theory is capable of revealing the relationship between elements and their propagation; however, for complex collective motions, the network properties often transiently and complexly change. A fundamental question addressed here pertains to the classification of collective motion network based on physically-interpretable dynamical properties. Here we apply a data-driven spectral analysis called graph dynamic mode decomposition, which obtains the dynamical properties for collective motion classification. Using a ballgame as an example, we classified the strategic collective motions in different global behaviours and discovered that, in addition to the physical properties, the contextual node information was critical for classification. Furthermore, we discovered the label-specific stronger spectra in the relationship among the nearest agents, providing physical and semantic interpretations. Our approach contributes to the understanding of principles of biological complex network dynamics from the perspective of nonlinear dynamical systems.

    DOI: 10.1038/s41598-020-58064-w

    Web of Science

    Scopus

    PubMed

    researchmap

  7. Data-driven spectral analysis for coordinative structures in periodic human locomotion. Reviewed International journal

    Keisuke Fujii, Naoya Takeishi, Benio Kibushi, Motoki Kouzaki, Yoshinobu Kawahara

    Scientific reports   Vol. 9 ( 1 ) page: 16755 - 16755   2019.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Living organisms dynamically and flexibly operate a great number of components. As one of such redundant control mechanisms, low-dimensional coordinative structures among multiple components have been investigated. However, structures extracted from the conventional statistical dimensionality reduction methods do not reflect dynamical properties in principle. Here we regard coordinative structures in biological periodic systems with unknown and redundant dynamics as a nonlinear limit-cycle oscillation, and apply a data-driven operator-theoretic spectral analysis, which obtains dynamical properties of coordinative structures such as frequency and phase from the estimated eigenvalues and eigenfunctions of a composition operator. Using segmental angle series during human walking as an example, we first extracted the coordinative structures based on dynamics; e.g. the speed-independent coordinative structures in the harmonics of gait frequency. Second, we discovered the speed-dependent time-evolving behaviours of the phase by estimating the eigenfunctions via our approach on the conventional low-dimensional structures. We also verified our approach using the double pendulum and walking model simulation data. Our results of locomotion analysis suggest that our approach can be useful to analyse biological periodic phenomena from the perspective of nonlinear dynamical systems.

    DOI: 10.1038/s41598-019-53187-1

    Web of Science

    Scopus

    PubMed

    researchmap

  8. Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables. Reviewed International journal

    Keisuke Fujii, Yoshinobu Kawahara

    Neural networks : the official journal of the International Neural Network Society   Vol. 117   page: 94 - 103   2019.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Understanding nonlinear dynamical systems (NLDSs) is challenging in a variety of engineering and scientific fields. Dynamic mode decomposition (DMD), which is a numerical algorithm for the spectral analysis of Koopman operators, has been attracting attention as a way of obtaining global modal descriptions of NLDSs without requiring explicit prior knowledge. However, since existing DMD algorithms are in principle formulated based on the concatenation of scalar observables, it is not directly applicable to data with dependent structures among observables, which take, for example, the form of a sequence of graphs. In this paper, we formulate Koopman spectral analysis for NLDSs with structures among observables and propose an estimation algorithm for this problem. This method can extract and visualize the underlying low-dimensional global dynamics of NLDSs with structures among observables from data, which can be useful in understanding the underlying dynamics of such NLDSs. To this end, we first formulate the problem of estimating spectra of the Koopman operator defined in vector-valued reproducing kernel Hilbert spaces, and then develop an estimation procedure for this problem by reformulating tensor-based DMD. As a special case of our method, we propose the method named as Graph DMD, which is a numerical algorithm for Koopman spectral analysis of graph dynamical systems, using a sequence of adjacency matrices. We investigate the empirical performance of our method by using synthetic and real-world data.

    DOI: 10.1016/j.neunet.2019.04.020

    Web of Science

    Scopus

    PubMed

    researchmap

  9. Frechet and Hausdorff Kernels for Trajectory Data Analysis Reviewed

    Koh Takeuchi, Masaaki Imaizumi, Shunsuke Kanda, Keisuke Fujii, Masakazu Ishihata, Takuya Maekawa, Ken Yoda, Yasuo Tabei

    29th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2021)     2021.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  10. Skill Differences in a Discrete Motor Task Emerging From the Environmental Perception Phase Reviewed

    Yumiko Hasegawa, Ayako Okada, Keisuke Fujii

    Frontiers in Psychology   Vol. 12   2021.10

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:Frontiers Media SA  

    Because of the challenges associated with measuring human perception and strategy, the process of human performance from perception to motion to results is not fully understood. Therefore, this study clarifies the phase at which errors occur and how differences in skill level manifest in a motor task requiring an accurate environmental perception and fine movement control. We assigned a golf putting task and comprehensively examined various errors committed in five phases of execution. Twelve tour professionals and twelve intermediate amateur golfers performed the putting task on two surface conditions: flat and a 0.4-degree incline. The participants were instructed to describe the topographical characteristics of the green before starting the trials on each surface (environmental perception phase). Before each attempt, the participants used the reflective markers to indicate their aim point from which the ball would be launched (decision-making phase). We measured the clubface angle and impact velocity to highlight the pre-motion and motion errors (pre-motion and motion phase). In addition, mistakes in the final ball position were analyzed as result errors (post-performance phase). Our results showed that more than half of the amateurs committed visual–somatosensory errors in the perception phase. Moreover, their aiming angles in the decision-making phase differed significantly from the professionals, with no significant differences between slope conditions. In addition, alignment errors, as reported in previous studies, occurred in the pre-motion phase regardless of skill level (i.e., increased in the 0.4-degree condition). In the motion phase, the intermediate-level amateurs could not adjust their clubhead velocity control to the appropriate level, and the clubhead velocity and clubface angle control were less reproducible than those of the professionals. To understand the amateur result errors in those who misperceived the slopes, we checked the individual results focusing on the final ball position. We found that most of these participants had poor performance, especially in the 0.4-degree condition. Our results suggest that the amateurs’ pre-motion and strategy errors depended on their visual–somatosensory errors.

    DOI: 10.3389/fpsyg.2021.697914

    researchmap

  11. Supervised sequential pattern mining of event sequences in sport to identify important patterns of play: An application to rugby union Reviewed

    Rory Bunker, Keisuke Fujii, Hiroyuki Hanada, Ichiro Takeuchi

    PLOS ONE   Vol. 16 ( 9 ) page: e0256329 - e0256329   2021.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Public Library of Science (PLoS)  

    Given a set of sequences comprised of time-ordered events, sequential pattern mining is useful to identify frequent subsequences from different sequences or within the same sequence. However, in sport, these techniques cannot determine the importance of particular patterns of play to good or bad outcomes, which is often of greater interest to coaches and performance analysts. In this study, we apply a recently proposed supervised sequential pattern mining algorithm called safe pattern pruning (SPP) to 490 labelled event sequences representing passages of play from one rugby team’s matches in the 2018 Japan Top League season. We obtain patterns that are the most discriminative between scoring and non-scoring outcomes from both the team’s and opposition teams’ perspectives using SPP, and compare these with the most frequent patterns obtained with well-known unsupervised sequential pattern mining algorithms when applied to subsets of the original dataset, split on the label. From our obtained results, line breaks, successful line-outs, regained kicks in play, repeated phase-breakdown play, and failed exit plays by the opposition team were found to be the patterns that discriminated most between the team scoring and not scoring. Opposition team line breaks, errors made by the team, opposition team line-outs, and repeated phase-breakdown play by the opposition team were found to be the patterns that discriminated most between the opposition team scoring and not scoring. It was also found that, probably because of the supervised nature and pruning/safe-screening mechanisms of SPP, compared to the patterns obtained by the unsupervised methods, those obtained by SPP were more sophisticated in terms of containing a greater variety of events, and when interpreted, the SPP-obtained patterns would also be more useful for coaches and performance analysts.

    DOI: 10.1371/journal.pone.0256329

    researchmap

  12. Flexible prediction of opponent motion with internal representation in interception behavior Reviewed

    Kazushi Tsutsui, Keisuke Fujii, Kazutoshi Kudo, Kazuya Takeda

    Biological Cybernetics     2021.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Springer Science and Business Media LLC  

    <title>Abstract</title>Skilled interception behavior often relies on accurate predictions of external objects because of a large delay in our sensorimotor systems. To deal with the sensorimotor delay, the brain predicts future states of the target based on the current state available, but it is still debated whether internal representations acquired from prior experience are used as well. Here we estimated the predictive manner by analyzing the response behavior of a pursuer to a sudden directional change of the evasive target, providing strong evidence that prediction of target motion by the pursuer was incompatible with a linear extrapolation based solely on the current state of the target. Moreover, using neural network models, we validated that nonlinear extrapolation as estimated was computationally feasible and useful even against unknown opponents. These results support the use of internal representations in predicting target motion, suggesting the usefulness and versatility of predicting external object motion through internal representations.

    DOI: 10.1007/s00422-021-00891-9

    researchmap

    Other Link: https://link.springer.com/article/10.1007/s00422-021-00891-9/fulltext.html

  13. Extraction of swing motion contributing to prediction of shuttle drop position in badminton Reviewed

    Tatsuya Yoshikawa, Kazushi Tsutsui, Kazuya Takeda, Keisuke Fujii

    30th International Joint Conference on Artificial Intelligence (IJCAI-21) workshop on AI for Sports Analytics (AISA)     2021.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  14. Understanding Others' Roles Based on Perspective Taking in Coordinated Group Behavior Reviewed

    Jun Ichikawa, Keisuke Fujii

    Proceedings of the Annual Meeting of the Cognitive Science Society   Vol. 43   page: 1285 - 1291   2021.8

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  15. Quantitative analysis of spontaneous sociality in children's group behavior during nursery activity. Reviewed International journal

    Jun Ichikawa, Keisuke Fujii, Takayuki Nagai, Takashi Omori, Natsuki Oka

    PloS one   Vol. 16 ( 2 ) page: e0246041   2021.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Sociality is the tendency to spontaneously interact with others to establish and maintain relationships. Some approaches, including questionnaires, tests, controlled experiments, and qualitative field research, cannot capture complex social interactions, such as in children during nursery activities, because of problems with ecological validity and the labor cost of analysis. Here, we introduced a new methodology for the quantitative analysis of spontaneous social movement and investigated children's group behavior using position data. We periodically visited a nursery and recorded videos of eurhythmics, in which children move in tune with music, in different classes. The results revealed that children in the six-year-old class approached others in a short period of time (within one second) and established group behavior like that in a game of tag. It can be interpreted that such social behavior may include actions related to the cognition of anticipating others' behaviors in a complex situation. Although only a small amount of data could be acquired, this study suggests one of the characteristics of social behaviors in the classroom considering an ecological approach.

    DOI: 10.1371/journal.pone.0246041

    Web of Science

    Scopus

    PubMed

    researchmap

  16. Investigation of roles in group behavior using a coordinative drawing task Reviewed

    Ichikawa Jun, Fujii Keisuke

    Cognitive Studies: Bulletin of the Japanese Cognitive Science Society   Vol. 28 ( 1 ) page: 170 - 173   2021

     More details

    Publishing type:Research paper (scientific journal)   Publisher:Japanese Cognitive Science Society  

    DOI: 10.11225/cs.2020.069

    CiNii Article

  17. Expectations for Data-Driven Science in Real-World Collective Motions Reviewed

    FUJII Keisuke

    Journal of The Society of Instrument and Control Engineers   Vol. 60 ( 1 ) page: 2 - 3   2021

     More details

    Publishing type:Research paper (scientific journal)   Publisher:The Society of Instrument and Control Engineers  

    DOI: 10.11499/sicejl.60.2

    CiNii Article

  18. Trajectory prediction with imitation learning reflecting defensive evaluation in team sports. Reviewed

    Masakiyo Teranishi, Keisuke Fujii, Kazuya Takeda

    IEEE 9th Global Conference on Consumer Electronics (GCCE 2020)     page: 124 - 125   2020.12

     More details

    Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/GCCE50665.2020.9291841

    Scopus

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/gcce/gcce2020.html#TeranishiFT20

  19. Cognition and interpersonal coordination of patients with schizophrenia who have sports habits. Reviewed International journal

    Keisuke Fujii, Yujiro Yoshihara, Yukiko Matsumoto, Keima Tose, Hideaki Takeuchi, Masanori Isobe, Hiroto Mizuta, Daisuke Maniwa, Takehiko Okamura, Toshiya Murai, Yoshinobu Kawahara, Hidehiko Takahashi

    PloS one   Vol. 15 ( 11 ) page: e0241863   2020.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Team sports activities are effective for improving the negative symptoms and cognitive functions in patients with schizophrenia. However, the interpersonal coordination during the sports and visual cognition of patients with schizophrenia who have team sports habits are unknown. The main objectives of this study were to test two hypotheses: first, patients with schizophrenia perform the skill requiring ball passing and receiving worse than healthy controls; and second, the patients will be impaired in these functionings in accordance with the previous studies regarding schizophrenia in general. Twelve patients with schizophrenia and 15 healthy controls, who had habits in football, participated in this study. The participants performed three conventional cognitive tests and a 3-vs-1 ball possession task to evaluate their interpersonal coordination. The results showed that in the 3-vs-1 possession task, the displacement in the pass angle for the patients was significantly smaller than that for the control. The recall in the complex figure test, the performance in the trail making test, and that in the five-choice reaction task for the patients were worse than those for the control. Moreover, we found the significant partial correlations in the patients between the extradimensional shift error and the pass angle as well as between the time in the trail making test and the displacement in the pass angle, whereas there was no significant correlation in the control group. This study clarified the impaired interpersonal coordination during team sports and the visual cognition of patients with schizophrenia who have team sports habits.

    DOI: 10.1371/journal.pone.0241863

    Web of Science

    Scopus

    PubMed

    researchmap

  20. Succinct Trit-array Trie for Scalable Trajectory Similarity Search. Reviewed

    Shunsuke Kanda, Koh Takeuchi, Keisuke Fujii, Yasuo Tabei

    Proceedings of 28th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2020)     page: 518 - 529   2020.11

     More details

    Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1145/3397536.3422210

    Scopus

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/gis/gis2020.html#KandaTFT20

  21. COGNITION AND SOCIAL BEHAVIORS IN SPORTS FOR PATIENTS WITH SCHIZOPHRENIA ENGAGED IN SPORTS HABITS Reviewed

    Yoshihara Yujiro, Fujii Keisuke, Murai Toshiya, Takahashi Hidehiko

    SCHIZOPHRENIA BULLETIN   Vol. 46   page: S128 - S128   2020.4

     More details

    Publishing type:Research paper (scientific journal)  

    Web of Science

  22. Practice Motions Performed During Preperformance Preparation Drive the Actual Motion of Golf Putting Reviewed

    Yumiko Hasegawa, Akito Miura, Keisuke Fujii

    Frontiers in Psychology   Vol. 11   page: Article 513   2020.3

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Frontiers Media SA  

    DOI: 10.3389/fpsyg.2020.00513

    Web of Science

    Scopus

    PubMed

    researchmap

  23. Practice Motions Performed During Preperformance Preparation Drive the Actual Motion of Golf Putting Reviewed

    Yumiko Hasegawa, Akito Miura, Keisuke Fujii

    Frontier in Psychology   Vol. 11 ( 513 ) page: https://doi.org/10.3389/fpsyg.2020.00513   2020.3

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: https://doi.org/10.3389/fpsyg.2020.00513

  24. Dynamic mode decomposition via dictionary learning for foreground modeling in videos Reviewed

    Israr Ul Haq, Keisuke Fujii, Yoshinobu Kawahara

    15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP'20)   Vol. 5 ( - ) page: 476-483   2020.3

     More details

    Language:English  

    DOI: 10.5220/0009144604760483

  25. Physically-interpretable classification of network dynamics for complex collective motions Reviewed

    Keisuke Fujii, Naoya Takeishi, Motokazu Hojo, Yuki Inaba, Yoshinobu Kawahara

    Scientific Reports   Vol. 10 ( 3005 ) page: https://doi.org/10.1038/s41598-020-58064-w   2020.2

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (scientific journal)  

    DOI: https://doi.org/10.1038/s41598-020-58064-w

  26. 協調に関する議論に向けたアプローチの提案-集団運動からみる他者の行動予測と適応- Reviewed

    市川 淳, 藤井 慶輔

    認知科学   Vol. 27 ( 3 ) page: xx - xx   2020

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  27. Proposal of a research approach for discussion of a dynamic coordination mechanism: Investigation of anticipating others' behaviors and adaptation through quantitative analysis of group behavior Reviewed

    Ichikawa Jun, Fujii Keisuke

    Cognitive Studies: Bulletin of the Japanese Cognitive Science Society   Vol. 27 ( 3 ) page: 377 - 385   2020

     More details

    Publishing type:Research paper (scientific journal)   Publisher:Japanese Cognitive Science Society  

    <p>In this paper, we propose a research approach that is used in cognitive science to investigate more complex coordination mechanisms between three or more people. That is, we propose an approach that uses position data to quantitatively analyze group behavior and to link these characteristics with the cognition of anticipating others' behaviors. It is important for coordination to anticipate others' behaviors and to adapt one's own body movement to others based on anticipation. We highlight previous studies on problem solving and learning in cognitive science which have investigated interaction processes from verbal protocols during task implementation and indicated the importance of understanding others' perspectives. Additionally, recent cognitive models of estimating others' intentions and anticipating others' behaviors during interactions using non-verbal information such as eye movement, posture, and gesture, have been investigated. Considering these previous studies, we focus on group behavior and propose to apply the new approach mentioned above to discuss a mechanism of more complex coordination. We also refer to some studies of biological group behaviors in biology, artificial life, and sports science, and demonstrate a potential issue that such papers did not focus on the cognition related to coordinative group behaviors. This paper illustrates an example of discussing interactions with others, to which the new approach is applied. Our previous study here analyzed children's group behavior during nursery activities using position data and linked these characteristics with the cognitive development of anticipating others' behaviors based on spontaneous sociality. However, it is difficult to investigate some details of group behavior due to the limitation of field measurement, for example, the accuracy of a child's anticipation and whether a child moved based upon anticipation. In future work, it is important to analyze controlled group behavior and to indicate accuracy of individuals' anticipation from movement data to solve these problems.</p>

    DOI: 10.11225/cs.2020.026

    CiNii Article

  28. Succinct Trie Index for Fast and Memory-Efficient Trajectory Similarity Search Reviewed

    KANDA Shunsuke, TAKEUCHI Koh, FUJII Keisuke, TABEI Yasuo

    Proceedings of the Annual Conference of JSAI   Vol. 2020 ( 0 ) page: 2C4OS7a01 - 2C4OS7a01   2020

     More details

    Publishing type:Research paper (scientific journal)   Publisher:The Japanese Society for Artificial Intelligence  

    <p>This paper proposes an efficient similarity search method for massive collections of trajectories. This method enables fast similarity searches by leveraging locality sensitive hashing and tries. To achieve memory efficiency, we propose two novel techniques of node reduction and a space-efficient representation for tries. We experimentally test our method on its ability to retrieve similar trajectories for a query from large collections of trajectories and show that our method performs superiorly with respect to search time and memory efficiency.</p>

    DOI: 10.11517/pjsai.JSAI2020.0_2C4OS7a01

    CiNii Article

  29. Trajectory generation with imitation learning reflecting evaluation of defensive teams in soccer Reviewed

    TERANISHI Masakiyo, FUJII Keisuke, TAKEDA Kazuya

    Proceedings of the Annual Conference of JSAI   Vol. 2020 ( 0 ) page: 2C6OS7c04 - 2C6OS7c04   2020

     More details

    Publishing type:Research paper (scientific journal)   Publisher:The Japanese Society for Artificial Intelligence  

    <p>Soccer is a complex sport with the interaction among 22 players and the ball. Player position data has been recently measured. However, the usage is limited to individual movements, and videos are mainly used for decision making of team tactics. Most of previous studies in team trajectory generation have been evaluated only on prediction errors and did not take tactical evaluations (e.g., good defense) into consideration. In this study, we focus on team defense, which has relatively few individual differences, and explicitly add the index whether the defensive team protects the goal to the feature vector, and perform multi-agent imitation learning reflecting the evaluation. The results showed that the proposed method had the similar prediction performance to the existing method (Le et al. 2017), but generated an improved trajectory in terms of defensive evaluation. This indicates that it is effective for the learning to reflect the tactical evaluation to generate a tactically meaningful trajectory in team sports.</p>

    DOI: 10.11517/pjsai.JSAI2020.0_2C6OS7c04

    CiNii Article

  30. Investigation for Advanced Discussions of Coordination:Anticipating Others' Behaviors and Adaptation in Group Behavior Using a Coordinative Drawing Task Reviewed

    ICHIKAWA Jun, FUJII Keisuke

    Proceedings of the Annual Conference of JSAI   Vol. 2020 ( 0 ) page: 3Rin493 - 3Rin493   2020

     More details

    Publishing type:Research paper (scientific journal)   Publisher:The Japanese Society for Artificial Intelligence  

    <p>We proposed a research approach for discussing mechanisms of more complex coordination between three or more than three people. That is to quantitatively analyze group behavior and to link these characteristics with the cognition of anticipating others' behaviors. It is important for coordination to anticipate others' behaviors and adapt one's own body movement to others. This paper mainly introduced previous studies of cognitive science, biology, artificial life, and sports science. Considering them, we propose to apply the new approach. This paper illustrates an example of discussing interactions with others, in which the new approach has been applied as our previous study; however, it is difficult to investigate some details of group behavior due to the limitation of field measurement. Hence, analyzing controlled group behavior and indicating accuracy of individuals' anticipation from movement data are needed. Finally, we also propose a coordinative drawing task, which suggests values of the new approach.</p>

    DOI: 10.11517/pjsai.JSAI2020.0_3Rin493

    CiNii Article

  31. Data-driven modeling in human collective motions Reviewed

    FUJII Keisuke

    Proceedings of the Annual Conference of JSAI   Vol. 2020 ( 0 ) page: 2C6OS7c02 - 2C6OS7c02   2020

     More details

    Publishing type:Research paper (scientific journal)   Publisher:The Japanese Society for Artificial Intelligence  

    <p>Modeling and understanding collective motions in which elements complexly interact is an important problem in engineering, physics, and biology. However, in real-world organisms, the elements are not physically connected to each other, and the rules behind them are often unknown. Therefore, data-driven approaches of estimating and understanding the mechanism of collective motions are effective. Here, I will introduce various approaches to solve this problem, and as an example, introduce a graph dynamic mode decomposition that extracts dynamical property in a dynamic network of multi-agent interactions. In the experiment, we classified the team offense and defense strategies with higher accuracy than the existing methods, and clarified the mode of label-dependent individual interactions. In the presentation, I would like to introduce other approaches that are currently being taken.</p>

    DOI: 10.11517/pjsai.JSAI2020.0_2C6OS7c02

    CiNii Article

  32. Data-driven modeling of trajectory in human chase and escape behaviors Reviewed

    TSUTSUI Kazushi, FUJII Keisuke, TAKEDA Kazuya

    Proceedings of the Annual Conference of JSAI   Vol. 2020 ( 0 ) page: 2C6OS7c01 - 2C6OS7c01   2020

     More details

    Publishing type:Research paper (scientific journal)   Publisher:The Japanese Society for Artificial Intelligence  

    <p>Chase and escape behaviors are fundamental skills in many sports and are crucial for the survival of many animals in the wild. The prediction of the locomotion trajectory of the opponent is important for achieving the purpose (i.e., escape or interception) but is difficult because a number of factors, such as strategy, kinematic ability, and surroundings, are involved in making the decisions on locomotion trajectory. In particular, the modeling of escape behavior has not been successful due to its diversity. Here, we challenged to predict the locomotion trajectory of evader and pursuer using a data-driven model based on a recurrent neural network (RNN). Our results showed the superior performances of the RNN model to the conventional models. These results suggest that there are some rules for escape and chase behaviors, and that it is possible to predict the trajectory by learning from repeated observations.</p>

    DOI: 10.11517/pjsai.JSAI2020.0_2C6OS7c01

    CiNii Article

  33. Motor control of practice and actual strokes by professional and amateur golfers differ but feature a distance-dependent control strategy. Reviewed International journal

    Yumiko Hasegawa, Keisuke Fujii, Akito Miura, Keiko Yokoyama, Yuji Yamamoto

    European journal of sport science   Vol. 19 ( 9 ) page: 1204 - 1213   2019.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    We explored how practice and actual putting strokes differed between professionals and high-level golf amateurs, and how practice strokes reflected subtle differences in putting distances. We analysed swing amplitude, impact velocity, and acceleration profile of the club-head. The acceleration profiles showed that the motor control pattern of the practice stroke differed from that of the actual stroke. To clarify the effects of different putting distances on the practice stroke and to analyse how much the actual stroke could be explained by the practice stroke, we conducted individual regression analyses. The practice strokes of all participants could be divided into three strategies and five types by the coefficient of determination and the slope. This implies that the purpose of the practice stroke varied among golfers. Most golfers used the individual velocity criteria in their practice strokes, which resulted in different putting distances based on their criteria. Unexpectedly, we found no significant difference in skill level between professionals and high-level amateurs. The results of this study imply that the practice stroke does not duplicate the actual stroke, even for professional golfers with excellent skills. However, most high-level golfers adopted distance-dependent control strategies for slightly different putting distances.

    DOI: 10.1080/17461391.2019.1595159

    Web of Science

    Scopus

    PubMed

    researchmap

  34. The kinetic mechanisms of vertical pointing movements. Reviewed International journal

    Shinji Yamamoto, Keisuke Fujii, Kisho Zippo, Keisuke Kushiro, Masanobu Araki

    Heliyon   Vol. 5 ( 7 ) page: e02012   2019.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    The present study utilized induced acceleration analysis to clarify the contributions of muscular and gravitational torques to the kinematics of vertical pointing movements performed by the upper limb. The study included eight healthy men with a mean age of 25 years. The experiment was divided into three blocks with ten trials in each, comprising five upward and five downward, randomly executed movements. The movements were recorded by a motion capture system and were subsequently analyzed. During the deceleration phase of the upward movement and the acceleration phase of the downward movement, the angular acceleration induced by gravitational torque contributed more to the generation of net induced angular acceleration than the angular acceleration induced by muscular torque. In addition, the difference between the net induced angular acceleration profiles during the upward and downward movements was mainly attributable to the difference between the respective angular acceleration profiles induced by muscular torque. These findings suggest that the central nervous system considers the gravitational effect on the upper limb in a phase-specific manner and accordingly generates a torque-derived kinematic difference with respect to the movement direction.

    DOI: 10.1016/j.heliyon.2019.e02012

    PubMed

    researchmap

  35. Analysis of factors predicting who obtains a ball in basketball rebounding situations Reviewed

    Motokazu Hojo, Keisuke Fujii, Yoshinobu Kawahara

    International Journal of Performance Analysis in Sport   Vol. 19 ( 2 ) page: 192 - 205   2019.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  36. Supervised Dynamic Mode Decomposition via Multitask Learning Reviewed

    Keisuke Fujii, Yoshinobu Kawahara

    Pattern Recognition Letters   Vol. 122 ( 1 ) page: 7 - 13   2019.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  37. 指導者から見た「研究と現場の橋渡し」:陸川章先生に聞く Reviewed

    陸川 章, 小山 孟志, 青木 美帆, 藤井 慶輔

    バスケットボール研究   Vol. 5 ( 0 ) page: 17 - 25   2019

     More details

    Publishing type:Research paper (scientific journal)   Publisher:日本バスケットボール学会  

    DOI: 10.34396/jsbs.5.0_17

    CiNii Article

  38. "Bridging the gap between the field and the laboratory" Reviewed

    Fujii Keisuke, Nagata Naoya

    The Japan Journal of Basketball Studies   Vol. 5 ( 0 ) page: 1 - 2   2019

     More details

    Publishing type:Research paper (scientific journal)   Publisher:The Japan Society for Basketball Studies  

    DOI: 10.34396/jsbs.5.0_1

    CiNii Article

▼display all

Books 14

  1. 実世界集団運動のデータ駆動科学, Society 5.0を支える未来のリーダー FACE the future, 計測と制御

    藤井慶輔( Role: Contributor ,  60(1), 2-3)

    2021.1 

     More details

    Language:Japanese

    researchmap

  2. 集団スポーツに関するデータ駆動的解析手法, 特集=実用応用技術のシステム開発と応用, ケミカルエンジニヤリング

    藤井慶輔( Role: Contributor ,  65(9), 561-566)

    化学工業社  2020.9 

     More details

    Language:Japanese

    researchmap

  3. これからの集団運動科学の展望

    藤井 慶輔( Role: Sole author)

    杏林書院  2020.5 

     More details

    Language:Japanese

  4. これからの集団運動科学の展望, 連載 集団運動を科学する― 6, 体育の科学

    藤井慶輔( Role: Contributor ,  70(5), 349-353)

    杏林書院  2020.5 

     More details

    Language:Japanese

    researchmap

  5. 1対1の攻防における競合スキルの評価, 連載 集団運動を科学する― 5, 体育の科学

    筒井和詩, 藤井慶輔( Role: Contributor ,  70(4))

    杏林書院  2020.4 

     More details

    Language:Japanese

    researchmap

  6. 1対1の攻防における競合スキルの評価

    筒井 和詩, 藤井 慶輔( Role: Joint author)

    杏林書院  2020.4 

     More details

    Language:Japanese

  7. どこまで集団運動を解明できるのか

    藤井 慶輔( Role: Sole author)

    杏林書院  2019.12 

     More details

    Language:Japanese

  8. どこまで集団運動を解明できるのか, 連載 集団運動を科学する― 1, 体育の科学

    藤井 慶輔( Role: Contributor ,  69(12) 907-911)

    杏林書院  2019.12 

     More details

    Language:Japanese

    researchmap

  9. 特集 トレーニングを運動学習として捉える対人競技における学習された動きの評価

    藤井 慶輔, 山下大地( Role: Joint author ,  対人競技における学習された動きの評価)

    日本トレーニング科学会  2019.2 

     More details

    Responsible for pages:23-29   Language:Japanese

    researchmap

  10. バスケットボールが科学で強くなる! 小谷 究, 柏倉 秀徳 (監修)

    藤井慶輔( Role: Contributor ,  3章 ディフェンスの科学)

    日東書院  2019 

     More details

    Language:Japanese

    researchmap

  11. バスケットボール学入門

    藤井 慶輔( Role: Joint author ,  13章 方法学)

    流通経済大学出版会  2017.11 

     More details

    Total pages:16   Language:Japanese

  12. バスケットボール用語事典

    藤井 慶輔( Role: Joint author)

    廣済堂出版  2017.6 

  13. ヒト集団の競合・協働を研究する際の注意点-集団スポーツを例として-

    藤井 慶輔( Role: Joint author)

    体育の科学(杏林書院)  2016.10 

     More details

    Language:Japanese

  14. なぜ陸上のトラックは左回りなの?/なぜ速く走るときは腕を振るの?

    藤井 慶輔( Role: Joint author)

    ヒトの動き百話(市村出版)  2011 

     More details

    Total pages:4   Language:Japanese

▼display all

MISC 13

  1. Data-driven spectral analysis for coordinative structures in periodic human locomotion. Reviewed

    Fujii K, Takeishi N, Kibushi B, Kouzaki M, Kawahara Y

    Scientific reports   Vol. 9 ( 1 ) page: 16755   2019.11

     More details

    Language:English  

    DOI: 10.1038/s41598-019-53187-1

    PubMed

  2. The kinetic mechanisms of vertical pointing movements. Reviewed

    Yamamoto S, Fujii K, Zippo K, Kushiro K, Araki M

    Heliyon   Vol. 5 ( 7 ) page: e02012   2019.7

     More details

    Language:English  

    DOI: 10.1016/j.heliyon.2019.e02012

    PubMed

  3. Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables Reviewed

    Keisuke Fujii, Yoshinobu Kawahara

    Neural Networks     page: .   2019.5

     More details

    Language:English  

  4. Analysis of factors predicting who obtains a ball in basketball rebounding situations Reviewed

    Motokazu Hojo, Keisuke Fujii, Yoshinobu Kawahara

    International Journal of Performance Analysis in Sport   Vol. 19 ( 2 ) page: 192-205   2019.2

     More details

    Language:English  

  5. Supervised Dynamic Mode Decomposition via Multitask Learning Reviewed

    Keisuke Fujii, Yoshinobu Kawahara

    Pattern Recognition Letters   Vol. 122 ( 1 ) page: 7-13   2019.2

     More details

    Language:English  

  6. 横-トレーニング-06 機械学習による集団スポーツの選手の動きの分類・予測手法を利活用する方法の提案

    藤井 慶輔, 方城 素和, 元安 陽一, 稲葉 優希

    日本体育学会大会予稿集   Vol. 70 ( 0 ) page: 77_3 - 77_3   2019

     More details

    Language:Japanese   Publisher:一般社団法人 日本体育学会  

    <p> 近年では全選手とボールの位置を計測するシステムがプロスポーツにおいて導入され、移動距離などのフィットネス指標や、特定のプレーの空間分布などの情報を得られるようになった。しかし、依然として戦術面に関しては、シュートなどある時点での空間分布の分析もしくはビデオベースの人の目視による分析が主であり、複数の選手の動きを考慮したプレーに関する自動分類・予測手法についてはほとんど利用されていない。そこで我々は、機械学習技術を用いてバスケットボールの集団攻撃プレーを自動分類する手法や、リバウンドと呼ばれるシュート後にボールを獲得する選手や得点を予測する手法を開発した。これらの方法によって、これまで経験のあるスタッフが時間を掛けて分類・評価してきた作業を自動で行うことにより、作業の負担を軽減することが期待できる。また、そのプレーに貢献する重要な選手の動きを、プレーの経験を必要とせずに根拠をもって定量的に説明することが期待できる。発表当日では、より具体的にこれらの自動分類・予測手法を練習などで利活用する方法を提案する。</p>

    DOI: 10.20693/jspehss.70.77_3

    CiNii Article

    researchmap

  7. Motor control of practice and actual strokes by professional and amateur golfers differ but feature a distance-dependent control strategy Reviewed

    Yumiko Hasegawa, Keisuke Fujii, Akito Miura, Keiko Yokoyama, Yuji Yamamoto

    European Journal of Sport Science   Vol. Accepted   page: .   2019

     More details

    Language:English  

  8. Automatically recognizing strategic cooperative behaviors in various situations of a team sport Reviewed

    Motokazu Hojo, Keisuke Fujii, Yuki Inaba, Yoichi Motoyasu,Yoshinobu Kawahara

    PLoS One   Vol. 13 ( 12 ) page: e0209247   2018.12

     More details

    Language:English  

  9. Metric on nonlinear dynamical systems with Koopman operators Reviewed

    Isao Ishikawa, Keisuke Fujii, Masahiro Ikeda, Yuka Hashimoto, Yoshinobu Kawahara

    Advances in Neural Information Processing Systems 31 (NeurIPS'18)   Vol. 31   page: 2858-2868   2018.12

     More details

    Language:English  

  10. Prediction and classification in equation-free collective motion dynamics Reviewed

    Keisuke Fujii, Takeshi Kawasaki, Yuki Inaba, Yoshinobu Kawahara

    PLoS Computational Biology   Vol. 14 ( 11 ) page: e1006545   2018.11

     More details

    Language:English  

  11. Quantitative analysis and visualization of children's group behavior from the perspective of development of spontaneity and sociality Reviewed

    Jun Ichikawa, Keisuke Fujii, Takayuki Nagai, Takashi Omori, Natsuki Oka

    24th Conference of Collaboration Researchers International Working Group (CRIWG'18)     page: 169-176   2018.9

     More details

    Language:English  

  12. Social forces for team coordination in ball possession game Reviewed

    Keiko Yokoyama, Hiroyuki Shima, Keisuke Fujii, Noriyuki Tabuchi, Yuji Yamamoto

    Physical Review E   Vol. 97 ( 022410 ) page: .   2018.2

     More details

    Language:English  

  13. 競技レベルの高い相手との試合中におけるバスケットボール選手の運動出力と心拍応答 Reviewed

    藤井 慶輔, 小山 孟志

    スポーツパフォーマンス研究   Vol. 9   page: 542-556   2018.1

     More details

    Language:Japanese  

▼display all

Presentations 32

  1. 集団スポーツにおける機械学習を用いたデータ駆動科学 Invited

    藤井 慶輔

    第18回認知的コミュニケーションワークショップ  2019.9.16 

     More details

    Event date: 2019.9

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

    researchmap

  2. 機械学習による集団スポーツの選手の動きの分類・予測手法を利活用する方法の提案

    藤井慶輔, 方城素和, 元安陽一, 稲葉優希

    日本体育学会第70回大会  2019.9.10 

     More details

    Event date: 2019.9

    Language:Japanese   Presentation type:Poster presentation  

    Country:Japan  

    researchmap

  3. Dynamic mode decomposition and its applications (II) Invited International conference

    Keisuke Fujii

    2019 Distinguished Lecture and International Interdisciplinary Workshop  2019.8.6 

     More details

    Event date: 2019.8

    Language:English   Presentation type:Oral presentation (invited, special)  

    Country:Korea, Republic of  

    researchmap

  4. Dynamic mode decomposition and its applications (I) Invited International conference

    Keisuke Fujii

    2019 Distinguished Lecture and International Interdisciplinary Workshop  2019.8.5 

     More details

    Event date: 2019.8

    Language:English   Presentation type:Oral presentation (invited, special)  

    Country:Korea, Republic of  

    researchmap

  5. Data-driven spectral analysis for social biomechanics

    Keisuke Fujii, Naoya Takeishi, Yuki Inaba, Benio Kibushi, Motoki Kouzaki, Yoshinobu Kawahara

    1st Kei-Hiroba (Biomechanics Research Society)  2019.6.15 

     More details

    Event date: 2019.6

    Language:English   Presentation type:Oral presentation (general)  

    Country:Japan  

    researchmap

  6. 観測量間の動的構造を抽出するベクトル値再生核ヒルベルト空間における動的モード分解 International conference

    藤井 慶輔、河原 吉伸

    第21回情報論的学習理論ワークショップ(IBIS2018) 

     More details

    Event date: 2018.11

    Language:Japanese   Presentation type:Poster presentation  

    Country:Japan  

  7. 集団スポーツを例としたヒト集団の競合や協働に関する研究 Invited International conference

    藤井 慶輔

    運動制御学セミナー 

     More details

    Event date: 2018.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:大阪大学   Country:Japan  

  8. 集団スポーツの動きの情報処理とそのモデル化 Invited International conference

    藤井 慶輔

    映像情報メディア学会 冬季大会 2017 

     More details

    Event date: 2017.12

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  9. Human creative interaction of group sports: Information-based modeling Invited

    Keisuke Fujii

    The fourth international workshop on Skill Science 

     More details

    Event date: 2017.11

    Language:English   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  10. 集団スポーツを例とした現象の主体と観測者から見た認知過程 Invited International conference

    藤井 慶輔

    日本認知科学会第34回大会 

     More details

    Event date: 2017.9

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  11. Identification of multi-player cooperative play by machine learning using group sports position information data International conference

    Keisuke Fujii

    Identification of multi-player cooperative play by machine learning using group sports position information data 

     More details

    Event date: 2017.5

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  12. 集団スポーツにおける自己と他者 Invited International conference

    藤井 慶輔

    第11回内部観測研究会 

     More details

    Event date: 2017.2

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  13. An attack-and-defend competition as a redundant cognitive-motor system

    Keisuke Fujii, Yuki Yoshihara, Yuji Yamamoto

    Society for Neuroscience 

     More details

    Event date: 2016.11

    Language:English  

    Country:United States  

  14. 身体・個・群れとしての集団スポーツ Invited International conference

    藤井 慶輔

    群れシンポジウム(早稲田大学) 

     More details

    Event date: 2016.10

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  15. 集団スポーツにおける部分と全体から見たインタラクションに関する問題 Invited International conference

    藤井 慶輔

    第15回認知的コミュニケーションワークショップ 

     More details

    Event date: 2016.9

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  16. 大規模トラッキング・センサデータを利活用する手法の展望 Invited International conference

    藤井 慶輔

    第67回日本体育学会大会ランチョンセミナー 

     More details

    Event date: 2016.8

    Language:Japanese  

    Country:Japan  

  17. トラッキング・センサデータを用いたバスケットボールにおけるチームプレー・対人スキルに関する研究報告とその展望 Invited International conference

    藤井 慶輔

    第2回日本バスケットボール学会サマーレクチャー 

     More details

    Event date: 2016.8

    Language:Japanese  

    Country:Japan  

  18. 集団球技の巧みさとチームワークを通して身体的・社会的知能を理解する Invited International conference

    藤井 慶輔

    第1回脳情報学セミナー(静岡大学) 

     More details

    Event date: 2016.5

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  19. 集団スポーツの動きに関する仕組みと振舞い、あるいは部分と全体 Invited International conference

    藤井 慶輔

    第24回NS研究会(立命館大学) 

     More details

    Event date: 2016.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:立命館大学   Country:Japan  

  20. Globally competitive and locally coordinative dynamics and behavior in group sports Invited

    Keisuke Fujii

    International Symposium Integrated Understanding for Emergent Property of Cooperation and Competition Dynamics 

     More details

    Event date: 2016.3

    Language:English   Presentation type:Symposium, workshop panel (nominated)  

    Country:Japan  

  21. Helping behavior toward a teammate: real-time group problem-solving at multiple spatial scales during a ballgame

    Keisuke Fujii, Takeshi Koyama, Akira Rikukawa, Hiroshi Yamada, Yuji Yamamoto

    The First International Symposium on Swarm Behavior and Bio-Inspired Robotics 

     More details

    Event date: 2015.10

    Language:English  

    Country:Japan  

  22. 実践的学習方法とその効果―スポーツ場面での全体-部分練習効果 Invited International conference

    藤井 慶輔

    第79回日本心理学会チュートリアルワークショップ 

     More details

    Event date: 2015.9

    Language:Japanese   Presentation type:Symposium, workshop panel (nominated)  

    Country:Japan  

  23. Interpersonal competition dynamics in a ballgame: Modeling of a 1-on-1 game and two opposing cognitive systems International conference

    Keisuke Fujii, Yuji Yamamoto

    International Society of Posture and Gait Research 

     More details

    Event date: 2015.6

    Language:English   Presentation type:Oral presentation (general)  

    Country:Spain  

  24. The role of the kinetic preparatory state in defending against a dribbler in a basketball 1-on-1 subphase

    Keisuke Fujii, Shinsuke Yoshioka, Tadao Isaka, Motoki Kouzaki

    The Asian-South Pacific Association of Sport Psychology (ASPASP) 

     More details

    Event date: 2014.8

    Language:English   Presentation type:Oral presentation (general)  

    Country:United States  

  25. 集団スポーツの戦術に関するデータ解析手法 Invited

    藤井 慶輔

    第6回愛媛大学DS研究セミナー  2021.3.18 

     More details

    Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  26. Data-driven Analysis for Multi-agent Trajectories in Team Sports

    Keisuke Fujii

    17th AIP Open Seminar, Talks by Structured Learning Team in RIKEN Advanced Intelligence Project  2021.3.17 

     More details

  27. サッカーにおけるボール奪取・被有効攻撃予測に基づくチームの守備評価

    戸田康介, 寺西真聖, 久代恵介, 藤井慶輔

    第10回日本統計学会スポーツ統計分科会スポーツデータ解析コンペティション  2020.12.27 

     More details

    Presentation type:Oral presentation (general)  

    researchmap

  28. 選手らしい動きと部分的な観測に基づく選手軌道予測モデル

    藤井 慶輔, 武石 直也, 河原 吉伸, 武田 一哉

    日本バスケットボール学会第 7 回学会大会  2020.12.19 

     More details

    Presentation type:Oral presentation (general)  

    researchmap

  29. 集団スポーツにおけるデータ駆動的モデルを用いた理解 Invited

    藤井 慶輔

    第19回認知的コミュニケーションワークショップ  2020.11.3 

     More details

    Presentation type:Oral presentation (invited, special)  

    researchmap

  30. 部分観測過程におけるデータ駆動的エージェントモデリング Invited

    藤井 慶輔

    日本認知科学会第37回大会 OS2 認知的インタラクションフレームワークの構築  2020.9.16 

     More details

  31. Automatic classification of offensive and defensive tactical plays in team sports

    Keisuke Fujii

    The 2020 Yokohama Sport Conference  2020.9.9 

     More details

    Language:English   Presentation type:Oral presentation (general)  

    researchmap

  32. 集団運動におけるデータ駆動科学(企画セッション:データ駆動科学と機械学習) Invited

    藤井 慶輔

    第22回情報論的学習理論ワークショップ  2019.11.22 

     More details

    Presentation type:Oral presentation (invited, special)  

    researchmap

▼display all

Research Project for Joint Research, Competitive Funding, etc. 3

  1. バスケットボールの実際のゲーム中における動きの激しさの評価

    2016.4 - 2017.3

    スポーツチャレンジ研究助成 

      More details

    Grant type:Competitive

  2. 球技のゲーム中に選手にかかる運動・生理的負荷の包括的理解

    2016.3 - 2017.4

    スポーツ学等研究助成 

      More details

    Grant type:Competitive

  3. 相手がいる状況においてバスケットボール選手が素早く動き出すメカニズムの解明

    2014.4 - 2015.3

    スポーツチャレンジ研究助成 

      More details

    Grant type:Competitive

KAKENHI (Grants-in-Aid for Scientific Research) 11

  1. 階層ナビゲーションのための数理・学習ベース解析手法と介入方策決定技術

    Grant number:21H05300  2021.9 - 2026.3

    科学研究費助成事業  学術変革領域研究(A)

    藤井 慶輔

      More details

    Authorship:Principal investigator 

    Grant amount:\95940000 ( Direct Cost: \73800000 、 Indirect Cost:\22140000 )

  2. Cross-disciplinary research on the prediction and control of real-world interactions based on evidence and causality

    Grant number:21H04892  2021.4 - 2024.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (A)  Grant-in-Aid for Scientific Research (A)

      More details

    Authorship:Coinvestigator(s) 

    researchmap

  3. チームワークの良さを支える神経基盤の解明

    Grant number:20H04087  2020.4 - 2023.3

    日本学術振興会  科学研究費助成事業 基盤研究(B)  基盤研究(B)

    水口 暢章, 藤井 慶輔, 福谷 充輝, 藤井 慶輔, 福谷 充輝

      More details

    Authorship:Coinvestigator(s) 

    サッカーやバスケットボールなどのチームスポーツにおいて味方選手と協調して攻撃・守備をする能力、すなわちチーム戦術を遂行する能力は個人のスキルや身体能力と同様に勝敗を分ける重要な要素である。本研究では、チーム戦術遂行能力に関連する神経基盤を明らかにすることを目的としている。そのために、試合中の選手の動きを分析と磁気共鳴画像法を用いた脳画像解析を行う。本研究は、個人の神経学的特徴に合わせたチーム戦術トレーニング法の提案につながるなど応用研究としてもさらなる発展が期待できる。

    researchmap

  4. Easily available information technology based on the data-driven models for social biomechanics

    Grant number:20H04075  2020.4 - 2023.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B)  Grant-in-Aid for Scientific Research (B)

      More details

    Authorship:Principal investigator 

    Grant amount:\16900000 ( Direct Cost: \13000000 、 Indirect Cost:\3900000 )

    researchmap

  5. 目的志向的な相互作用を含む集団移動系列・経路の解析手法の開発

    Grant number:19H04941  2019.4 - 2021.3

    新学術領域研究(研究領域提案型)

    藤井 慶輔

      More details

    Authorship:Principal investigator 

    Grant amount:\3770000 ( Direct Cost: \2900000 、 Indirect Cost:\870000 )

    複雑な動きをみせる生物などの群れでは、目的志向的な味方や外敵などの移動体との協力・逃避などの相互作用が起きている。一般に集団移動運動に関するデータ駆動的な解析手法においては、方法論的に明示的なモデルを仮定することが難しいため、未だ相互作用の性質を明らかにする決定的な方法論が確立されていない。そこで本研究では工学的な目標として、集団移動系列・経路データから相互作用を可視化して分類や予測を行う手法を開発し、その科学的な応用として、目的志向的な生物集団移動の機能や原理などを発見・理解することを目的とした研究を行う。
    本年度は、主に(1)観測量間の動的構造を抽出するためのモード分解手法(2)複雑な集団運動におけるネットワークダイナミクスの物理的に解釈可能な分類手法に関する研究を行った。
    研究1では、観測量間で構造を持つ非線形動的システムを対象に、ベクトル値再生核ヒルベルト空間で定義されたKoopman作用素のスペクトル解析を定式化し、その推定アルゴリズムを開発した。この研究成果は、機械学習分野の学術雑誌であるNeural Networks誌に採択された。
    研究2では、研究1の応用として、観測量間の動的構造を抽出するグラフ動的モード分解をスポーツ分類に応用する研究を行った。データ空間における分解のため、より簡潔に再定式化し、各スライド窓で分解する手法を適用して、物理的・意味的に解釈可能な動的構造を抽出し、複雑な集団運動の自動分類を行った。この研究成果は、一般学術雑誌であるScientific Reports誌に採択された。
    予定していた研究が遂行され、該当年度に論文が出版されたため。
    本年度は、移動経路の相互作用の階層的な特性を可視化し分類・予測することで、個体の動き、局所的な相互作用、大域的な集団運動との関連について統合的に検討する。例えば、まず個体の多様な移動経路を停止などのイベントで区切り、自然言語でいう文字のように基本的な構成要素として離散記号化する。次に、構成要素(文字)を組合せて局所的な相互作用(単語)を作る。次に例えば自然言語処理で用いられる手法を用いて、各局所相互作用(単語)をベクトル表現に次元削減し、かつ局所相互作用(単語)間の関係性も考慮する手法を提案する予定である。このことによって、移動経路及びその組合せで表現できる局所相互作用が、どのような定量的性質を持つかを集団移動データから発見することが期待される。

  6. 目的志向的な相互作用を含む集団移動系列・経路の解析手法の開発

    2019.4 - 2021.3

    日本学術振興会科学研究費  新学術領域研究(研究領域提案型) 

    藤井 慶輔

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  7. 支配法則が非自明なヒト集団運動における社会的行動の可視化技術

    Grant number:18K18116  2018.4 - 2021.3

    若手研究

    藤井 慶輔

      More details

    Authorship:Principal investigator 

    Grant amount:\4290000 ( Direct Cost: \3300000 、 Indirect Cost:\990000 )

    本研究の目的は、ヒト集団運動において社会的行動を可視化する技術を開発して実践的に利活用する基礎を作ることである。当該年度は、集団運動のダイナミク
    スを理解するため、主に2つの技術を開発した。
    1つ目の研究では、冗長かつ支配方程式が不明なヒトの多関節運動に関して、非線形動的システムの観点から理解するために、作用素のスペクトル解析的な観点からデータ駆動的に合成作用素の固有値や固有関数を推定する方法を用いて検証する研究を行った。この研究成果は、一般学術雑誌であるScientific Reports誌に採択された。
    2つ目の研究では、観測量間の動的構造を抽出するグラフ動的モード分解と呼ばれる手法をスポーツ分類に応用する研究を行った。データ空間における分解のため、より簡潔に再定式化し、各スライド窓で分解する手法を適用して、物理的・意味的に解釈可能な動的構造を抽出し、複雑な集団運動の自動分類を行った。この研究成果は、一般学術雑誌であるScientific Reports誌に採択された。
    当該年度に計画した研究について、論文が出版されたため。
    今後は、移動経路の相互作用の階層的な特性を可視化し分類・予測することで、個体の動き、局所的な相互作用、大域的な集団運動との関連について統合的に検討する。例えば、まず個体の多様な移動経路を停止などのイベントで区切り、自然言語でいう文字のように基本的な構成要素として離散記号化する。次に、構成要素(文字)を組合せて局所的な相互作用(単語)を作る。次に自然言語処理で用いられる手法を用いて、各局所相互作用(単語)をベクトル表現に次元削減し、かつ局所相互作用(単語)間の関係性も考慮する手法を提案する予定である。このことによって、移動経路及びその組合せで表現できる局所相互作用が、どのような定量的性質を持つかを集団運動データから発見することが期待される。

  8. 支配法則が非自明なヒト集団運動における社会的行動の可視化技術

    2018.4 - 2020.3

    日本学術振興会科学研究費  若手研究 

    藤井 慶輔

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  9. 対人競技の巧みさの評価方法の開発:制御理論と力学系理論を相補的に用いて

    2016.4 - 2019.3

    日本学術振興会科学研究費  挑戦的萌芽研究  挑戦的萌芽研究

    藤井 慶輔

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  10. 球技を通して時空間マルチスケールな分岐現象を解明する

    2014.4 - 2017.1

    科学研究費補助金 

  11. 3次元倒立振子モデルを用いた方向転換走動作における予測・運動制御メカニズムの解明

    2011.4 - 2014.3

    科学研究費補助金 

▼display all

 

Teaching Experience (Off-campus) 2

  1. System Mathematics 1,2

    2020.10 Nagoya University)

     More details

  2. Mathematics II and Tutorial

    2019.10 Nagoya University)

     More details