Feature extraction of wavelet transform for sEMG pattern classification

In this study, we have investigated usefulness of extraction of the surface electromiyogram (sEMG) features from multi-level wavelet decomposition of the yEMG signal. The first step of this method is to analyze sEMG signal detected from the subject's right upper forearm and extract features using the mean absolute value (MAV), MAV of wavelet approximation and details coefficients, MAV of wavelet approximation and details of sEMG which is calculated Inverse Wavelet Transform. The second step is to import the feature values into an ANN to identify the speed of hand open-çlose (SHOC). Finally, based on the results of experiments, feature vectors obtained by wavelet transform is effective in prediction of SHOC.