Denoising, feature extraction and pattern recognition method for human body surface electromyography signals

Abstract

The invention discloses a denoising, feature extraction and pattern recognition method for human body surface electromyography signals, which comprises the following steps: performing best wavelet packet node denoising on the human body surface electromyography signals; performing wavelet decomposition on the human body surface electromyography signals after denoising, and extracting maximum absolute values of all levels of wavelet high-frequency coefficients as feature vectors; and inputting the extracted feature vectors into a back propagation network for performing training and pattern recognition. With the adoption of the best wavelet packet leaf node denoising method provided by the invention, noise carried in the electromyography signals can be effectively removed, and useful information can be retained; the maximum absolute values of the wavelet high-frequency coefficients can well reflect features of the human body surface electromyography signals, thereby having obvious advantages in comparison with the existing feature value method; and the relatively high recognition effect can be obtained by searching optimal hidden neurons and training errors of the back propagation network.

Description

technical field [0001] The invention belongs to the field of biological signal processing and pattern recognition, and relates to a method for noise elimination and feature extraction of human body surface electromyographic signals. Background technique [0002] Surface electromyography (SEMG) signals are a kind of bioelectrical signals, which are widely used in clinical medicine and sports medicine, especially in the field of human action recognition, due to their advantages of easy acquisition and no damage. Signal is its main research object. The denoising and feature extraction of EMG signals are key issues in human action recognition. [0003] The SEMG signal is the electrical activity of the muscle obtained from the surface of the human skin, which comes from the electrical activity of the nerve fibers that detect the muscle [1]. SEMG signal is a kind of weak electrical signal, the peak-to-peak value is generally only 0-10mV, and the frequency range of useful signal ...

AI Technical Summary

Problems solved by technology

We also found in the research that the recognition effect is closely related to the training error. The selected parameters are different, and the final recognition effect will be very different.

Images