Abstract

Basketball has always been a relatively hot sport. However, the level of basketball in China does not maintain the synchronous development trend with competitive sports, which can be seen from the achievements of various international competitions. Many basketball players have retired due to sports injuries. How to avoid and delay the occurrence of injuries to the maximum extent, and make the best competitive state to get the longest time is an urgent problem to be solved in the current basketball training and competition process. Therefore, how to reduce sports damage in basketball sports has become a crucial problem. The artificial neural network algorithm is widely used in complex system hardware fault detection, medical diagnosis, medical image processing and other complex task, to classify and forecast, and achieved good results. But in the use of the sports injury risk prevention is very limited, in sports injury risk early warning research, predecessors to sports injury factors made a lot of research and the qualitative model was established, but no quantitative evaluation research, and artificial neural network algorithm has good performance in complex system classification and prediction, so the artificial neural network algorithm is applied to sports injury risk early warning study is a very meaningful work, can carry on the accurate to the athlete sports injury risk assessment. Using RBF neural network to achieve dimensional reduction preprocessing of high-dimensional data not only has sufficient theoretical basis, but also it is more superior. Based on the optimization study of RBF neural network algorithm, we study the data-based feature selection RBF neural network, and apply it in the high-dimensional multi-objective optimization decision space and pare to quality and disadvantages prediction. Through the evaluation of the test sample, the early warning model achieves ideal results, so it is feasible to apply to the sports injury risk warning.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call