Neural network analysis of muscle strength characteristics of men’s volleyball players

Guangzhou University of Science and Technology, Guangzhou 510550, Guangdong Province

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

In this paper, the muscle strength of knee and ankle joints of Chinese men’s volleyball players was tested and analyzed at constant speed to reveal their strength characteristics and provide experimental support for related research. Through the established neural network model, it can be known that the RBF network model can predict the variation of human muscle strength with the relative peak torque of joint flexor muscle group. The analysis of neural network shows that men’s volleyball competition requires very high relative peak torque of the knee and ankle muscle groups. In addition, the relative peak torque of the knee and ankle muscle groups of a few athletes is small, so they should be subjected to targeted strength training. By comparing the RBF network model with BP network and Elman network model, it is shown that the RBF network model has higher accuracy and stronger generalization ability.