Feature extraction of wavelet transform coefficients for sEMG classification

Considering the vast variety of EMG signal applications such as rehabilitation of people suffering from some mobility limitations, scientists have done much research on EMG control system. In this regard, feature extraction of EMG signal has been highly valued as a significant technique to extract the desired information of EMG signal and remove unnecessary parts. This proposed method is based on discrete wavelet transform (DWT). This method consists of 2 main processes; feature extraction and classification. Feature extraction is implemented from the EMG signals, and different level of wavelet decomposition (cA3, cD3, cD2 and cDl) using root mean square (RMS) and cepstrum coefficient (CC). Then, the feature vector is classified based on decision functions obtained by PCA. Experimental results showed that our method using DWT can improve motion recognition accuracy compared to when using raw EMG signals.