DATA COLLECTION AND PERFORMANCE EVALUATION OF RUNNING TRAINING SPORT USING DIFFERENT NEURAL NETWORK TECHNIQUES

Abstract

With the increasing engagement of human beings in the pursuit of healthcare, running as a sport has become a fashionable and healthcare first choice. This research uses artificial intelligence technology to carry out intelligent analysis when conducting running training. Artificial intelligence technology can accurately analyze and predict the application requirements of sports training postures. We proposed an analysis of sports posture and a prediction system, which uses running training data in the form of a heart rate, recorded on a GPS smart sports watch, as well as using the recurrent neural network (RNN), long and short-term memory (LSTM) and the gate recursive unit (GRU). These three types of neural network methods can predict which method is best suited for a road race and can confirm that it will be completed within the scheduled finish time; these models will also perform an intelligent analysis of physical fitness (heart rate, pace) and running technology (cadence, pace). The training and test data are collected from the running training records (running distance, time, heart rate, stride frequency, stride length, pace, calories, altitude and other characteristic values) as input parameters, to test and compare the running completion time trends of the RNN, LSTM and GRU neural network methods in the exercise table, so as to evaluate their predictive abilities. The results show that the GRU method has the best predictive accuracy, and the least accurate is the LSTM method. After the hidden layers are added to the three predictive methods, the RNN is slightly regressive, the LSTM indicates a trend of significant improvement and the GRU exhibits less obvious changes.