[A surface EMG signal identification method based on short-time Fourier transform].

A surface EMG signal identification method based on short-time fourier transform is presented in this paper. To fully utilize the nonstationary character of the EMG signal, short-time fourier transform is employed to get the signal's time-frequency representation. Singular value decomposition is then used in the spectrogram to extract feature vector for pattern identification. Four types of movement of forearm, hand grasp, hand extension, wrist pronation and wrist supination can be identified from surface EMG signals. Experimental results show that it is a stable and efficient method for extracting features.