APPLICATION OF BACK PROPAGATION NEURAL NETWORK IN SPORTS FATIGUE INDICATORS

ABSTRACT Introduction High-intensity rehabilitation training will produce exercise fatigue. Objective A backpropagation (BP) network neural algorithm is proposed to predict sports fatigue based on electromyography (EMG) signal images. Methods The principal component analysis used reduce the dimension of EMG features. knee joint angle estimated by regularized over-limit learning machine and BP algorithm. Results RMSE value lower than that At same time, ρ closer 1, indicating its higher accuracy. Conclusions model time has been greatly reduced, which improves efficiency. Level evidence II; Therapeutic studies - investigation treatment results.