SEMG signal optimal channel selection method based on gradient boosting tree

Abstract

The invention relates to an sEMG signal optimal channel selection method based on a gradient boosting tree. The method comprises the steps: pasting a plurality of electrodes at each group of muscles which are driven to form a to-be-recognized action, acquiring an sEMG signal of each electrode channel, adding a label, and carrying out the filtering preprocessing of the labeled sEMG signal; featurevalue extraction is performed on the sEMG signals after filtering preprocessing, so that feature vectors can be obtained; training a first gradient boosting tree model to generate a new feature value;combining the feature vector with the new feature value to generate a combined feature; and training the second gradient boosting tree model, outputting the recognition accuracy of the to-be-recognized action, and obtaining a recognition accuracy sequence, the channel combination with the highest accuracy being the optimal channel combination. According to the method, excessive noise introduced in the sEMG collection process can be reduced, and the robustness of the system is ensured; useless data and redundant data are removed, so that the data processing period is shortened, time delay caused by data accumulation is avoided, and the real-time performance of the system is guaranteed.

Description

technical field [0001] The invention relates to the technical field of biological signal recognition, in particular to a method for selecting an optimal channel of an sEMG signal based on a gradient boosting tree. Background technique [0002] Human surface electromyography (sEMG, surface electromyography) signal is the result of the action potential sequence emitted by multiple active motor units during muscle contraction, which is filtered by the volume of adipose tissue and superimposed on the skin surface, which directly reflects the movement intention of the human body. Action recognition based on sEMG is an important part of human-computer interaction, and has been widely used in various fields such as rehabilitation exoskeleton robots, intelligent prosthetics, and game entertainment. [0003] When performing human-computer interaction based on sEMG recognition, the main process includes: [0004] (1) According to the type of action to be identified, according to the ...

AI Technical Summary

Problems solved by technology

[0009] Aiming at the deficiencies of the prior art, the present invention provides an optimal channel selection method for sEMG signals based on a gradient boosting tree, which solves the problem of channel redundancy caused by more pasted electrodes in sEMG action recognition

Images