The comprehensive progress of mental and physical quality is majorly influenced by the college physical education, which is considered a part of the educational system. Developing a scientific and efficient evaluation index is significant to compute physical education teaching quality. The traditional methods of assessing performance in physical education often rely on subjective evaluations or delayed feedback from manual data collection. To overcome these challenges, a design based on a real-time monitoring system is introduced that leverages wearable biosensor technology to improve physical education teaching and training. Initially, some physiological indicators, namely heart rate, respiration rate, body temperature, and motion activity, were recorded and analysed to provide individualized insights into physical performance. Data pre-processing is performed using a median filter to reduce noise and Z-score normalization to standardize the input dataset. Key features are extracted using Fast Fourier Transform (FFT), enabling the identification of critical performance metrics. A Rat Swarm Optimized Efficient Random Forest (RSO-ERF) algorithm was introduced to enhance classification accuracy and optimize system performance. Experimental results demonstrate the proposed system’s effectiveness in providing real-time feedback, identifying individual fitness levels, and supporting adaptive teaching strategies. The increased system’s analysis tendency allows for customized training regimens, ongoing feedback, and improved physical health metrics monitoring. It also gives educators the ability to make data-driven decisions, encourage safety, and improve the educational experience for athletes and students. The findings underscore the potential of wearable biosensor technology combined with advanced algorithms in transforming physical education methodologies for improved engagement and performance outcomes.
Read full abstract