- Role
- Finalist
- Region
- Greater Vancouver
- Pronouns
- he/him/his
Christopher Lin
ea adipisicing consectetur ex in sit enim duis consequat exercitation officia sit fugiat eiusmod ex cupidatat in laborum dolore amet magna sunt culpa ea pariatur consectetur enim ex consequat laborum laborum irure exercitation culpa non amet
Project
Modeling Human Movement: ML-Driven Biomechanical Analysis of Throwing Motion Using BiLSTMs
Project #4211
Biomechanics—the science of human movement—plays a vital role in injury prevention, rehabilitation, and sports performance. Despite its importance, biomechanical analysis remains largely inaccessible, as existing tools are expensive and impractical. Systems often cost over $10,000, with motion capture labs exceeding $100,000. Manual observation methods are slow, subjective, and lack real-time feedback, making motion analysis unscalable for most applications. This project addresses these challenges using low-cost wearable inertial measurement units (IMUs) and machine learning. Specifically, it employs Bidirectional Long Short-Term Memory (BiLSTM) networks with Temporal Attention to deliver an AI-powered system for analyzing baseball throwing motion. The system identifies critical movement phases, detects inefficiencies, and enhances human performance modeling. With broad applications in sports science, rehabilitation, ergonomics, and clinical gait analysis, this work offers an affordable, scalable wearable solution for biomechanical analysis, representing a new frontier in AI-powered biomechanics.
- Challenge
- Digital Technology
- Category
- Intermediate
- Type
- Innovation