Classification of Hand Manipulation Using BP Neural Network and Support Vector Machine Based on Surface Electromyography Signal

摘要

In this paper, we focus on the method of classifying the surface electromyography (sEMG) signals based on hand manipulations via time series of the measured data. In order to represent dynamical characteristics of sEMG, a stochastic dynamic process is included in it based on the maximum likelihood estimation (MLE) principle. By using the EM algorithm, the RMS, WAMP, AR, Wavelet, GMM and HMM feature of the signal can be identified easily. Ten people of different time series data sets of different hand grasps and in-hand manipulations captured from different subjects are collected. The BP and SVM classifiers were used to recognize these hand manipulation signal, compared with the independent probabilistic model, the proposed algorithm for the inferred model gain better performance and demonstrate the effectiveness.