Research On Surface EMG Classification Using Support Vector Machines

The electromyographic(EMG) signal is the electrical manifestation of neuromuscular activation associated with a contracting muscle. It is an exceedingly complicated signal which is affected by the anatomical and physiological properties of muscles. EMG was picked up from the intact musculature during volitional motion have been suggested and utilized as an effective method to provide control commands for artificial limbs and functional neuromuscular stimulation. A lot of researches domestic were focused on the mode recognition of EMG to realize multifunctional control of artificial limbs. Effective signal feature extraction and accurate function identification are the crucial problem involved in practical prosthesis control. These problems were discussed theoretically and practically in this dissertation.The main research can be classed as follows:feature extraction of sEMG. multi-classification algorithm of SVM and support Vector Machine algorithm for multi-classification of sEMG Pattern Recognition.(1) In this dissertation, surface electromyographic signal is analyzed by wavelet transform. The feature vectors are built by extracting the singular value of the wavelet coefficients.(2) The multi-class support vector machine classifier is designed by using four kinds of multi-class classification approach, and completed the eight class surface EMG pattern classification. The SVM classifier is applied to the classification of eight movements with recording of the surface EMG. Experimental results show that the average recognition rate is over 90%. The classification accuracy of SVM classifier is significantly better than RBF neural network classifier.