Research on Autonomous Foot Movement Recognition Based on SVM

In order to improve the effectiveness of rehabilitation of stroke patients, active training can be used to treat and recover the patient's foot dyskinesia. Recognizing the different movement characteristics of the feet is an important part of the active rehabilitation of stroke patients. In this paper, the EMG signals of different movements of the right foot are classified and studied. The EMG signals of three different movement states of the foot resting state, foot stretched 15° and foot stretched 45° are collected, absolute mean and filter common space mode were used for feature extraction of EMG signal, and support vector machine (SVM) was used for classification and recognition after extraction. The experimental results show that the classification accuracy rate of resting state-foot-stretched 45° is 89.9%, which exceeds the classification accuracy rate of resting state-foot-stretched 15° of 86.8%. It shows that when the subjects stretch the foot at 45°, more motion units are activated and the characteristics are more obvious than when the feet are stretched at 15°. Therefore, by classifying the characteristics of EMG signals and identifying different autonomic movements of feet, it can be used as the basis for rehabilitation treatment of stroke patients. At the same time, the average classification accuracy of 15° -45 ° and the resting state -15 ° -45 ° is above 80%, which confirms the feasibility of the signal processing method and support vector machine classification algorithm used in this paper for the study of automatic foot motion recognition.