Surface electromyography (sEMG) feature extraction based on Daubechies wavelets

Wavelet transform feature extraction has become one of the most powerful techniques to improve the classification accuracy. In this paper, we are investigating the multi-level Daubechies wavelet reconstruction parameters. The EMG signal after performing the Daubechies wavelet was further processed by using one of the most successful features which is MAV. RES index statistical measurement was used to evaluate the class reparability of the features. The optimal results are obtained by using the seventh order of Daubechies with the level 1 and level 2 details components after performing wavelet reconstruction.