Optimizing physical education movements through biomechanical analysis: A new approach to reducing the risk of sports injuries

Abstract

Physical education is crucial for fostering student’s health, fitness, and lifetime active behaviors. However, using inappropriate movement skills during Physical activity may raise the risk of sports injuries. Biomechanical analysis is a scientific approach to studying the movement of students that focuses on the forces and mechanics of physical activity. The study’s goal is to develop physical education motions using biomechanical analysis and a deep learning (DL) method to reduce the risk of sports injury. This study proposed a novel turbulent flow of water-based adjustable long-short-term memory (TFW-ALSTM) to classify and predict the high risk of sports injuries. Using advanced motion capture data and biomechanical modeling techniques, the study identifies improper movement patterns that can lead to injury during common physical education activities. The data was preprocessed using normalization and Kalman filters to reduce noise from the data. Discrete wavelet transforms (DWT) to extract the features from preprocessed data. The system offers beneficial suggestions to enhance movement efficiency through biomechanical data analysis. Experimental results reveal that the suggested model achieves accuracy (98.2%), recall (97%), specificity (98.1%), and an F1-Score (98%), particularly in dynamic activities like running and leaping, reducing the risk of injury considerably to compare existing algorithms. The study emphasizes the significance of integrating biomechanical knowledge and prediction models to enhance injury prevention measures in physical education programs. This approach provides educators and coaches with a dependable and effective tool for ensuring safer and more efficient student engagement.