Motion state identification method, device and terminal equipment

Abstract

The invention discloses a motion state identification method, which is applied to the technical field of data processing. The motion state identification method comprises the following steps of: acquiring data collected by a motion sensor, and calculating a kurtosis value by using data when determining that the motion state is a walking state or a riding state according to the data; when the kurtosis value is greater than a first kurtosis threshold and less than a second kurtosis threshold, calculating the sample entropy by using the data; when the sample entropy is greater than the sample entropy threshold, the motion state is the riding state; when the sample entropy is less than the sample entropy threshold, the motion state is the walking state. The method fully combines the advantagesof both the kurtosis and the sample entropy, and improves the computational efficiency on the basis of ensuring the accuracy of the motion state recognition. The invention also discloses an identification device for motion state, terminal equipment and a computer readable storage medium, which have the above beneficial effects.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a motion state recognition method, device, terminal equipment and computer-readable storage medium. Background technique [0002] The identification of the motion state in the prior art comprehensively uses features such as Fourier transform, wavelet transform, kurtosis and sample entropy. But these are only applicable to theoretical research, and in practical applications, in addition to ensuring the accuracy of motion state classification, the algorithm running speed and memory usage must also be considered. In the existing hardware, either the accuracy is guaranteed but the computing speed is sacrificed (that is, the speed of obtaining the motion state recognition result is slow), or the computing speed is guaranteed and the accuracy is discarded (that is, the motion state recognition result is not accurate), and neither is possible. Therefore, it is necessary...

AI Technical Summary

Problems solved by technology

But these are only suitable for theoretical research, and in practical applications, in addition to ensuring the accuracy of motion state classification, the algorithm running speed and memory usage must also be considered

In the existing hardware, either the accuracy is guaranteed but the calculation speed is discarded (that is, the speed of obtaining the motion state recognition result is slow), or the computing speed is guaranteed and the accuracy is discarded (that is, the motion state recognition result is not accurate), and neither is both.

Images