Research on the Application of Intelligent Motion Data Analysis Algorithm in High-Performance Sports Training Platform

The incorporation of smart motion data analysis in sports training has transformed the way athletes maximize their performance while reducing the risk of injury. The evolution of motion capture technologies and wearable sensors has made real-time data analysis a valuable resource for both coaches and athletes. This paper introduces a new sports motion analysis approach based on a hybrid model that integrates the AlexNet and TabNet architectures. The method utilizes high-performance motion capture data, including joint angles, acceleration, and body posture, acquired via wearable sensors and processed using sophisticated feature extraction methods, such as wavelet transforms. The Lyrebird Optimization Algorithm (LOA) is used to select features, ensuring that only the most relevant data are utilized in the analysis. Our experimental outcomes demonstrate that our hybrid AlexNet-TabNet model achieves 98.85% accuracy, accompanied by equally high precision (98.60%) and sensitivity (98.61%), making it highly efficient for assessing sports performance. This study is significant in that it demonstrates the capabilities of integrating artificial intelligence, motion capture technology, and wearable sensors to provide athletes with accurate, actionable information, which can be used to create customized training programs that enhance performance and reduce injuries.