Method and system for identifying exercise intensity

Abstract

The embodiment of the invention provides a method for training an exercise intensity recognition system. The method comprises the following steps of: A1, constructing an exercise intensity recognition system which comprises a data preprocessing module, a parallel convolution processing stream, a bilinear pooling module and a multi-task learning module which are connected in sequence, wherein the parallel convolution processing stream comprises two parallel convolution processing streams; A2, preprocessing motion data marked with labels through the data preprocessing module, and obtaining a training set composed of motion information and the corresponding labels, wherein the motion data are acquired by an inertial sensor, and the labels marked for the motion data comprise multiple different motion intensity labels and multiple different motion behavior labels; A3, training the exercise intensity recognition system by using the training set; according to the method, features extracted from a convolutional layer are optimized from the channel dimension and the space dimension, important features are concerned, unnecessary features are inhibited, and the recognition precision of the exercise intensity can be improved.

Description

technical field [0001] The present invention relates to the fields of pervasive computing and exercise health monitoring, specifically relates to the field of exercise intensity identification, and more specifically relates to a method and system for identifying exercise intensity. Background technique [0002] The "Physical Activity Guidelines for Chinese Adults" recommends that adults should spend more than 150 minutes of moderate-to-high-intensity physical activity per week to help their health. At the same time, children's exercise health includes many aspects such as exercise time, exercise intensity, exercise pattern and energy consumption level. As an important area of ​​research in children's physical health, studies have shown that increasing physical activity time in children with high-level exercise intensity has positive effects to varying degrees on the improvement of children's motor skills, obesity prevention interventions, psychosocial health, and cardiovascu...

AI Technical Summary

Problems solved by technology

[0007] There are often problems such as rough indicators and poor generalization in detecting exercise intensity based on heart rate and stride frequency;

[0008] When faced with motion intensity detection, traditional machine learning methods can only train models based on existing data, and cannot obtain robust deep learning features and cannot satisfy strong general capability requirements

Images