A method to evaluate swimming performance based on deep learning and a single inertial sensor
Project/Area Number |
17K13179
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Sports science
|
Research Institution | Tokyo National College of Technology |
Principal Investigator |
Yuto Omae 東京工業高等専門学校, 電気工学科, 助教 (00781874)
|
Research Collaborator |
TAKAHASHI Hirotaka
KOBAYASHI Masahiro
SAKAI Kazuki
|
Project Period (FY) |
2017-04-01 – 2019-03-31
|
Project Status |
Completed (Fiscal Year 2018)
|
Budget Amount *help |
¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
Keywords | スポーツ工学 / 機械学習 / 深層学習 / 競泳 / スポーツ / ディープラーニング / 人工知能 / 慣性センサ / アルゴリズム |
Outline of Final Research Achievements |
In this research, we propose an algorithm to evaluate swimming performance and develop a system included it by using a single inertial sensor and deep learning. Algorithms to recognition of swimming style and detect starting and ending timing of each stroke and turn motion are embedded into the system. They are developed by the random forests and deep learning. As a result, swimmers can know each motion performance (each stroke and turn).
|
Academic Significance and Societal Importance of the Research Achievements |
これまでの一般的なトレーニング現場では、1回1回のストローク(1回目は1.2sec, 2回目は1.3secなど)のパフォーマンスを競技終了後即座に知ることは困難であった。しかし、本研究で開発されたシステムにより、競技者はこれを競技終了後即座に知ることが可能となる。これにより、自らの動作のどこが悪かったのか、知る機会を得ることができるため、パフォーマンス向上に寄与すると考えられる。
|
Report
(3 results)
Research Products
(17 results)
-
-
-
-
[Journal Article] Swimming Motion Classification for Coaching System by Using a Sensor Device2018
Author(s)
Masahiro Kobayashi, Yuto Omae, Kazuki Sakai, Akira Shionoya, Hirotaka Takahashi, Takuma Akiduki, Kazufumi Nakai, Nobuo Ezaki, Yoshihisa Sakurai, Chikara Miyaji
-
Journal Title
ICIC Express Letters, Part B: Applications
Volume: 09
Issue: 03
Pages: 209
DOI
NAID
ISSN
2185-2766
Related Report
Peer Reviewed / Open Access
-
-
[Journal Article] Swimming Style Classification Based on Ensemble Learning and Adaptive Feature Value by Using Inertial Measurement Unit2017
Author(s)
Yuto Omae, Yoshihisa Kon, Masahiro Kobayashi, Kazuki Sakai, Akira Shionoya, Hirotaka Takahashi, Takuma Akiduki, Kazufumi Nakai, Nobuo Ezaki, Yoshihisa Sakurai, Chikara Miyaji
-
Journal Title
Journal of Advanced Computational Intelligence and Intelligent Informatics
Volume: 21
Issue: 4
Pages: 616-631
DOI
NAID
ISSN
1343-0130, 1883-8014
Year and Date
2017-07-20
Related Report
Peer Reviewed / Open Access
-
-
-
-
-
-
-
-
-
-
-