표면 근전도 신호를 사용한 부분 손 절단 환자의 동작 분류

Abstract

In this study, in order to recognize the intention of motion of the amputated hand for the use of a prosthetic hand in a patient with a partial amputation of the finger, the SVM model was trained using sEMG signals of three movements of motion when no movement was performed, rock and paper. An experiment for accuracy was conducted using three motion data in various limb positions. When looking at the results obtained, it was not possible to distinguish the exact intention that the patient could use the prosthetic hand. The result showed that it was not possible to accurately distinguish the intention that the patient could use the prosthetic hand. This is assumed that due to the fact that the sEMG signal when not in motion in other limb position is similar to the sEMG signal of rock and paper motion in the patient's comfortable limb position.