Healthy Research Rewards
ResearchHub is incentivizing healthy research behavior. At this time, first authors of open access papers are eligible for rewards. Visit the publications tab to view your eligible publications.
Got it
XZ
Xiaoliang Zhao
Author with expertise in Electrocatalysis for Energy Conversion
Achievements
Cited Author
Key Stats
Upvotes received:
0
Publications:
3
(33% Open Access)
Cited by:
189
h-index:
19
/
i10-index:
22
Reputation
Biology
< 1%
Chemistry
< 1%
Economics
< 1%
Show more
How is this calculated?
Publications
0

Accuracy and Adaptability Improvement in Aerobic Training: Integration of Self-Attention Mechanisms in 3D Pose Estimation and Kinematic Modeling

Xiaoliang Zhao et al.Jan 1, 2024
Accurately tracking and analyzing human motion during aerobic exercise poses significant challenges due to the dynamic complexity of human biomechanics. Traditional methods often fail to capture this complexity, resulting in training plans that lack personalization and an increased risk of exercise-related injuries. Therefore, developing a method capable of accurately understanding and analyzing the dynamics of human motion has become particularly important. The motivation behind this study is to enhance the safety and effectiveness of aerobic exercise training. By accurately monitoring and analyzing the movements of athletes during their training, it aims to prevent injuries and create personalized training plans. To this end, we believe a new approach is needed to deeply understand human motion, one that can adapt to various environmental changes and provide real-time feedback. We propose a framework that combines 3D pose estimation with kinematic modeling. This method employs self-attention mechanisms and machine learning techniques to precisely capture the complexity of human motion. Our core technology includes a self-attention-based pose estimation system capable of accurately tracking 3D joint positions in various environments, and a detailed kinematic model for biomechanical analysis, including the calculation of joint angles, velocities, and accelerations. Our model was validated using a custom aerobic exercise dataset, demonstrating superior accuracy and adaptability compared to existing models. Comparative analyses with other models highlight the advanced capabilities of our model in accurately interpreting and analyzing human motion. Our experiments confirm that the model excels in precision, robustness to environmental changes, real-time feedback, and injury prevention. Notably, it significantly reduces injury risks by identifying potential stress points and facilitates the generation of personalized training plans.