Athlete Exercise Intensity Recognition Method based on ECG and Convolutional Neural Network

Abstract

Abstract Unreasonable exercise will cause damage to the body. In physical education, coaches only use physiological indicators such as heart rate and breathing to judge the physiological state of athletes, which is highly subjective and is not conducive to accurately judging the physiological state of athletes. In order to effectively monitor athletes in exercises, a method for identifying athletes' exercise intensity based on ECG and convolutional neural network was proposed. In this method, the more informative ECG signal is used as the physiological indicator of the athlete's exercise intensity, combined with the convolutional neural network for feature extraction, and finally the training model is used to monitor and evaluate the athlete's exercise intensity. The method implements automatic feature extraction and recognition of athletes' ECG signals. The simulation results of the dataset show that the method can effectively judge the exercise intensity, and the accuracy can reach 98.6%. At the same time, the algorithm has a small amount of calculation and a fast convergence speed, in the daily training of athletes has a good auxiliary role.