Feature Extraction of Surface EMG Signal Based on Wavelet Coefficient Entropy

This paper introduces a novel and simple method to extract the general feature of two surface EMG signal patterns: forearm supination (FS) surface EMG signal and forearm pronation (FP) surface EMG signal. The method decomposes surface EMG signal into 16 Frequency bands (FB) by wavelet packet transform (WPT), and then wavelet coefficient entropy (WCE) of two chosen FBs is calculated. The two WCEs were used to distinguish FS surface EMG signals from FP surface EMG signals. The result shows that WCE is an effective method for extracting the feature from surface EMG signal.