SEMG based classification using wavelet function for around shoulder muscles

Abstract

The wavelet transform is the accurate, efficient and effective method to improve the quality of the myoelectric signal before use in prosthetic device for transhumeral amputees. Classification of the signal from upper limb using Surface Electromyogram (SEMG) signal has been the matter of extensive research. Discrete Wavelet Transform (DWT) coefficients along with the features values were extracted from the given SEMG data. With the appropriate choice of the mother wavelet, different shoulder motions were classified with the wavelet coefficients. In order to improve the class separability, analysis of variance method was used. It was found that the different motion can be identified accurately and provide the fundamental information to develop an efficient prosthetic device.