AI in Kinesiology and Biometric Analysis
School Name
South Carolina Governor's School for Science and Mathematics
Grade Level
12th Grade
Presentation Topic
Computer Science
Presentation Type
Mentored
Abstract
This research investigated whether artificial intelligence could provide hobbyists and professionals in sports with an accessible and inexpensive method for receiving personalized movement analysis and coaching without requiring in-person instruction or extensive self-research. As AI has been increasingly developed to assist in the humanities, STEM, and household tasks, the question arises on how sports performance analysis through intelligent systems could bridge the gap between amateur and professional-level feedback. The project began with the goal of creating and launching a market-ready mobile application. The first steps were to research video parsing techniques and how datasets like MotionBERT (Motion Bidirectional Encoder Representations from Transformers) could mathematically analyze movement points, angles, and biomechanical patterns. Afterwards, professional athlete movement data was integrated and sorted based on specific movements, sports, and the visuals themselves to give optimal performance benchmarks for comparison analysis. Vision Language Models (VLM) with Google Gemini API calls were utilized to shift the focus of the research toward practical product design and comprehensive app development for eventual App Store deployment. Results included a fully functional AI coaching system capable of parsing video input, extracting precise biomechanical patterns, and generating personalized feedback recommendations for golfing and can be expanded to other sports later on. This work establishes a foundation for revolutionary advancements in accessible athletic enhancement tools while demonstrating AI's transformative potential in understanding human kinesiology, ultimately advancing both athletic performance optimization and longevity research through deeper comprehension of human movement mechanics.
Recommended Citation
Hopkins, Jack, "AI in Kinesiology and Biometric Analysis" (2026). South Carolina Junior Academy of Science. 40.
https://scholarexchange.furman.edu/scjas/2026/all/40
Location
Furman Hall 204
Start Date
3-28-2026 10:00 AM
Presentation Format
Oral Only
Group Project
No
AI in Kinesiology and Biometric Analysis
Furman Hall 204
This research investigated whether artificial intelligence could provide hobbyists and professionals in sports with an accessible and inexpensive method for receiving personalized movement analysis and coaching without requiring in-person instruction or extensive self-research. As AI has been increasingly developed to assist in the humanities, STEM, and household tasks, the question arises on how sports performance analysis through intelligent systems could bridge the gap between amateur and professional-level feedback. The project began with the goal of creating and launching a market-ready mobile application. The first steps were to research video parsing techniques and how datasets like MotionBERT (Motion Bidirectional Encoder Representations from Transformers) could mathematically analyze movement points, angles, and biomechanical patterns. Afterwards, professional athlete movement data was integrated and sorted based on specific movements, sports, and the visuals themselves to give optimal performance benchmarks for comparison analysis. Vision Language Models (VLM) with Google Gemini API calls were utilized to shift the focus of the research toward practical product design and comprehensive app development for eventual App Store deployment. Results included a fully functional AI coaching system capable of parsing video input, extracting precise biomechanical patterns, and generating personalized feedback recommendations for golfing and can be expanded to other sports later on. This work establishes a foundation for revolutionary advancements in accessible athletic enhancement tools while demonstrating AI's transformative potential in understanding human kinesiology, ultimately advancing both athletic performance optimization and longevity research through deeper comprehension of human movement mechanics.
