sEMG time-frequency features for hand movements classification

Surface Electro-MyoGraphic (sEMG) signals recorded on the forearm can provide information about the hand movement, which can help control a prosthetic implant for disabled people. To do so, the sEMG signals must be accurately classified despite the signals' non-stationarity, noise from sensors, involved muscles, and patient's peculiarities. This study deals with the classification of hand movement using sEMG signals, and focus especially on the use of time-frequency domain for feature extraction and on several linear and non-linear methods for the dimension reduction. Methods as the Discrete Orthonormal Stockwell Transform (DOST) and Multidimensional Scaling (MDS) are applied for the first time on sEMG signals, and an extensive comparison study is performed on the combinations of the proposed methods. Classical classifiers are then used on a public dataset in order to evaluate the applied methods. Short-time Fourier transform, continuous wavelet transform and Stockwell transform performed well, with respectively 90.05%, 89.92 and 90.96% accuracy, but the average calculation times per window were 1.75ms, 2.30ms, and 1.60ms respectively. Promising results were obtained using DOST and MDS with classification rate 87.13% and significant improvement in feature extraction computation time as the average was 0.13ms per window.