A Study on the Pattern Recognition based on Surface Electromyogram

초록

In this paper, classification results of wrist movements were compared by using surface electromyogram (sEMG). The GMM, k-NN, QDA, and LDA was used as classification methods and Difference Absolute Mean Value (DMAV), Difference Absolute Standard Deviation Value (DASDV), Mean Absolute Value (MAV), Root Mean Square (RMS) were used as features which were applied to classification methods. EMG signals were acquired from the two electrodes placed on the forearm of twenty eight healthy subjects and features were extracted from the obtained EMG signals in the time domain. 16 double features were made by combining signals of the two electrodes. The importance of the feature selection in the EMG signal processing was verified by comparing classification accuracy of each double feature, and improvement of the classification accuracy by normalization was also confirmed