2023 Fiscal Year Final Research Report
A development of AI-based tailor-made system to evaluate and improve sport skills
| Project/Area Number |
19K22807
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Medium-sized Section 59:Sports sciences, physical education, health sciences, and related fields
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
荻野 正樹 関西大学, 総合情報学部, 教授 (00397639)
青山 千紗 大阪大学, 大学院医学系研究科, 助教 (80823939)
|
|---|
| Project Period (FY) |
2019-06-28 – 2024-03-31
|
| Keywords | AI / LightGBM |
|---|
| Outline of Final Research Achievements |
This research aimed to improve table tennis skills with a "tailor-made, coach-free, athletic skill measurement and improvement system" as a real-space task and a virtual-space (VR) task, in which AI performs all processes from "measurement of skills for each athlete, analysis of the measurement results, detection of weaknesses and habits based on the analysis results, provision of practice and training menus to correct them, and verification of the effectiveness" without relying on humans at all.
The type of ball in multi-ball practice, and the characteristics and weaknesses of the player (poor courses and shot patterns) were effectively extracted using LightGBM, and individually optimized training was realized by adjusting the ball distribution pattern based on this.
|
| Free Research Field |
スポーツ神経科学
|
| Academic Significance and Societal Importance of the Research Achievements |
卓球の多球練習におけるAI解析の研究成果は、スポーツにおけるトレーニング革命をもたらすきっかけと成り得る。AIとスポーツの融合により、選手のパフォーマンスデータを高度に解析し、新たなトレーニング理論や方法論の開発が促進されるとともに、他のスポーツ分野への応用展開が期待される。社会的意義は大きく、個別の弱点を特定することで効率的なトレーニングの提供が可能となり、選手の競技力向上に寄与するとともに、スポーツ分野全体において、客観的データに基づく科学的なトレーニング方法が普及することで、一般のアスリートからスポーツ愛好者まで様々なレベルでの技術向上が容易となり、スポーツの普及に繋がる。
|
