Active Segment Segmentation Method of Surface Electromyography Based on Sample Entropy and Gaussian Model

Abstract

The invention discloses a method for segmenting active segments of surface electromyography signals based on sample entropy and a Gaussian model. The steps include: 1. collecting the potential value of surface electromyography signals from relevant muscles of the human body, and setting the width u and step length of the sliding window f, Sliding segmentation of the data; 2 Set the sample entropy parameters m, r and calculate the sample entropy of each sliding window; 3 Use the DBSCAN clustering method to determine the basic model of Gaussian polynomials, and then initialize the model parameters; 4 Non-linear least squares method Fitting a Gaussian model; 5 determining an energy threshold to segment the active segment according to the Gaussian model. The invention can utilize the feature that the sample entropy can inhibit the noise, overcome the influence of the noise on the signal segmentation, and thus provide a basis for the accuracy and reliability of the further analysis of the surface electromyographic signal.

Description

Technical field [0001] The present invention belongs to the field of surface mymp electromycmon signal processing, particularly a surface electromyophoresis signal activity segment segment. Background technique [0002] The activity segment detection and segmentation method of the current surface electromyography signal mainly has three categories: the first class, is a method of setting a threshold based on signal amplitude, this method is sensitive to noise, and does not apply to a low signal-to-noise ratio; Solving this problem, has proposed a method based on wavelet transform, which can work with the wavelet model with the measured myocardial signal, so it is necessary to find a suitable wavelet function, but in most cases it is difficult Find a relatively ideal wavelet function. The second category is to analyze the maximum likelihood ratio of statistics, which has a complete theoretical derivation, but it is necessary to establish a signal model known and parameter unknown,...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method based on sample entropy and Gaussian in order to overcome the difficulties that the existing method cannot overcome the low signal-to-noise ratio, many restrictive conditions, and limited application range and cannot segment the active segment due to the detection of the active segment of the surface electromyography signal. The method of segmenting the active segment of the surface electromyographic signal of the model is expected to be able to segment the active segment of the surface electromyographic signal under various conditions, and overcome the influence of noise on the analysis of the surface electromyographic signal, so as to improve the accuracy and accuracy of the surface electromyographic signal analysis. Reliability provides the basis

Images