Short-term hand gestures recognition based on electromyography signals

Abstract

Electromyography pattern recognition to predict limb movements can
significantly enhance the control of the prosthesis. However, this technique
has not yet been widely used in clinical practice. Improvements in the
myoelectric pattern recognition (MPR) system can improve the functionality
of the prosthesis. This study proposes new sets of time domain features to
enhance the MPR control system. Three groups of features are evaluated, time
domain with auto regression (TD-AR), frequency domain (FD), and timefrequency domain (TFD). The electromyography signals (EMG) are obtained from the Ninapro database-5 (DB5), a publicly available dataset for hand prosthetics. The long-term signals of DB5 are divided into short-term signals to perform short-term signals recognition. The three feature sets are extracted from the short-term signals. The results showed that the performance of the proposed TD-AR features outperformed that of the FD and TFD feature sets. The TD-AR-based discrimination performance of 40 gestures achieved a precision of 88.8% and a sensitivity of 82.6%. The integration of short-term identification with reliable features can improve classification accuracy even for a large number of gestures. A comparison with the latest works shows the reliability of the proposed work.