Analysis of Students' Sports Exercise Behavior and Health Education Strategy Using Visual Perception-Motion...

Area of Science:

• Sports Science
• Artificial Intelligence
• Robotics
• Health Education

Background:

• College health education faces challenges in effectively monitoring and analyzing students' sports exercise.
• Existing methods for analyzing physical activity lack precision and efficiency.
• There is a need for innovative approaches to integrate technology into health education.

Purpose of the Study:

• To explore the future development of college health education by analyzing its impact on students' sports exercise.
• To develop and validate a novel system combining AI and intelligent robotics for analyzing sports behaviors.
• To propose a new development model for college health education based on technological integration.

Main Methods:

• Utilized artificial intelligence (AI) algorithms and intelligent robotics with Kinect sensors to capture human skeleton data.
• Developed a visual perception human motion recognition (HMR) algorithm based on the Hidden Markov Model (HMM).
• Applied the HMM-based HMR algorithm to recognize students' sports exercise motions from skeleton images.

Main Results:

• The HMR algorithm demonstrated a maximum reconstruction error of 10 mm and a compression ratio between 5 and 10.
• Achieved a human motion recognition (HMR) rate exceeding 96%.
• The proposed algorithm requires fewer training samples compared to similar methods while maintaining high recognition accuracy.

Conclusions:

• The AI and intelligent robot-enabled HMM-based HMR algorithm effectively identifies student sports exercise behavior characteristics.
• This technology offers a valuable reference for advancing college health education and student well-being.
• The study presents a new, effective model for college health education development through AI integration.