Lower limb prosthesis road condition recognition method based on surface electromyogram signals

Abstract

The invention provides a lower limb prosthesis road condition recognition method based on surface electromyogram signals. The method comprises the following steps of 1, collecting and preprocessing the lower limb surface electromyogram signals of a thigh amputation patient under different road conditions; 2, extracting a characteristic value sample set of road condition recognition of the preprocessed lower limb surface electromyogram signals; 3, optimizing classification parameters of the extreme learning machine through a backbone particle swarm algorithm to obtain an optimal ELM classifier,and realizing lower limb prosthesis road condition identification and classification. According to the lower limb prosthesis road condition recognition method based on surface electromyogram signals,an extreme learning machine classifier is constructed by using the optimal hidden layer node number and the kernel function parameters. The road condition recognition accuracy is high. The backbone particle swarm algorithm has global search capability, is easy to implement and high in search speed. The premature phenomenon can be effectively avoided on the premise of ensuring the accuracy. The road condition recognition accuracy is effectively improved.

Description

Technical field: [0001] The invention belongs to the field of pattern recognition, and relates to a road condition recognition method for a lower limb prosthesis based on a surface electromyography signal, in particular to a road condition recognition method for a lower limb prosthesis based on a backbone particle swarm algorithm evolution extreme learning machine. Background technique: [0002] Lower limb prosthetics are the only means for lower limb amputees to restore walking function. Lower limb prosthetics can basically compensate for the missing functions of the human body, enabling patients to take care of themselves, and even participate in work and return to society. [0003] The road condition recognition method for lower limb amputees originated from the research on the recognition of action intentions of upper limb amputees, and its development lags behind that of the upper limbs; road condition recognition is to build a control interface between the lower limb am...

AI Technical Summary

Problems solved by technology

[0008] 3. Neural networks have done a lot of research on EMG pattern classification and EMG signal processing, and obtained very valuable results, but neural networks often face the disadvantages of cumbersome manual setting of weight parameters and slow training speed;

Images