A Method of Evaluating Rehabilitation Stage by sEMG Signals for the Upper Limb Rehabilitation Robot

Abstract

Stroke can easily lead to nerve injury, which will bring inconvenience in life. Research shows that this kind of injury can be improved by using rehabilitation robots for rehabilitation training. In this paper, a method of evaluating and classifying rehabilitation stages by sEMG signals are proposed, and the feasibility of this method is verified. Firstly, a method to distinguish the impaired side from the healthy side using sEMG signals are proposed, and its accuracy is verified by simulation experiments. Through this experiment, some better feature are chosen to evaluate the muscle strength. sEMG signals of the upper-limb muscles of the patients are denoised and analyzed in time domain and frequency domain. sEMG signals are then obtained into the training set and the test set, using the training set to make the weighed evaluation for the unknown rehabilitation stage and calculate the final classification results. The experiments are carried out and the result verified the feasibility of using sEMG signals to distinguish the rehabilitation stage.