Exercise fatigue detection method and system based on wearable equipment

Abstract

The invention discloses an exercise fatigue detection method and system based on wearable equipment. The method comprises the following steps: extracting R waves and calculating an RR interval sequence for electrocardiosignals collected by wearable equipment in a movement process; conducting heart rate variability analysis on the RR interval sequence, and extracting heart rate variability time domain features, heart rate variability frequency domain features, heart rate variability time-frequency domain features and heart rate variability nonlinear features; screening out an optimized feature set according to one or more of independence, correlation degree, importance degree and redundancy between the features and the fatigue state; and constructing a training set by using the optimized feature set, training a classifier, obtaining a classification model used for detecting the fatigue state, and each sample of the training set reflecting a corresponding relation between a group of optimized features and fatigue state levels. According to the invention, the efficiency and accuracy of exercise-induced fatigue detection can be improved.

Description

technical field [0001] The present invention relates to the technical field of computer science, and more specifically, to a wearable device-based exercise fatigue detection method and system. Background technique [0002] With the enhancement of people's health awareness, more and more people begin to pay attention to and try to deal with sub-health status. The rise of aerobic sports such as marathons, outdoor hiking, cycling, and yoga in recent years stems from people's increasing emphasis on health. Scientific and reasonable exercise has many benefits to human health, including reducing the risk of depression, improving sleep quality, improving immunity, improving cardiovascular health, reducing obesity, and reducing the occurrence of other lifestyle-related risk factors. However, improper exercise is not only bad for health but also may cause harm to human body. Scientific and reasonable exercise includes scientific exercise time, exercise frequency, exercise intensity...

AI Technical Summary

Problems solved by technology

The features extracted by this method are relatively simple, and only the mean, standard deviation, difference between the maximum value and the minimum value, the mean value of the first-order difference signal, and the standard deviation of the first-order difference signal are extracted in the time domain, and the frequency domain is not considered. and features on nonlinear domains

[0006] To sum up, the existing sports fatigue detection methods are relatively simple, do not comprehensively extract fatigue-related features, and do not consider the correlation between input features and fatigue state, and the accuracy of fatigue detection needs to be improved

Images