The research on sports injury has long relied on traditional statistical methods, which often have obvious limitations when dealing with high-dimensional, nonlinear and multi-modal data. With the development of artificial intelligence technology, machine learning provides a new way to solve these complex problems. This paper systematically reviews the progress and application of machine learning in sports injury research. Firstly, the development of different machine learning methods in sports injury research was summarized. Secondly, we focus on five core applications of machine learning in the field of sports injury: data feature selection and dimensionality reduction, injury risk prediction, injury symptoms and signs classification, risk monitoring based on wearable devices, and imaging data analysis. Research shows that machine learning models show significant advantages in dealing with complex data patterns, improving prediction accuracy and achieving real-time dynamic intervention. However, research in related fields still faces challenges such as insufficient data quality and quantity, poor model interpretability, and barriers to multidisciplinary cooperation. Through the summary, it can be seen that future research in this field should focus on constructing standardized shared datasets, developing more interpretable models, and strengthening the cooperation and communication between multi-disciplines, and finally promoting the application of machine learning in sports injury prevention, diagnosis and rehabilitation.
With the rapid improvement of the perception and computing capacity of mobile devices such as smart phones, human activity recognition using mobile devices as the carrier has been a new research hot-spot. The inertial information collected by the acceleration sensor in the smart mobile device is used for human activity recognition. Compared with the common computer vision recognition, it has the following advantages: convenience, low cost, and better reflection of the essence of human motion. Based on the WISDM data set collected by smart phones, the inertial navigation information and the deep learning algorithm-convolutional neural network (CNN) were adopted to build a human activity recognition model in this paper. The K nearest neighbor algorithm (KNN) and the random forest algorithm were compared with the CNN network in the recognition accuracy to evaluate the performance of the CNN network. The classification accuracy of CNN model reached 92.73%, which was much higher than KNN and random forest. Experimental results show that the CNN algorithm model can achieve more accurate human activity recognition and has broad application prospects in predicting and promoting human health.