An EMG classification method based on wavelet transform [and ANN]

This paper presents the application of an artificial neural network technique together with a feature extraction method, viz., wavelet transform, for the classification of EMG signals. The architecture of ANN used in the classification is a three-layer feedforward network which implements the backpropagation of error learning algorithm. After training, the network with wavelet coefficients was able to classify four forearm motions with an average accuracy of 90%. The wavelet transform thus provides a potentially powerful technique for real time preprocessing of EMG signals prior to classification