IDENTIFICATION OF FINGER OPERATION USING SUPPORT VECTOR MACHINE AND CONTROL OF MYOELECTRIC PROSTHETIC HAND BASED ON INTEGRATED ELECTROMYOGRAM
菊地 毅, 菊地 毅KIKUCHI, Takeshi
562015-03-24 , 法政大学大学院理工学・工学研究科
In this paper, the identification of finger operation and control of the fingers of a myoelectric prosthetic hand are discussed. Finger operation is classified into the six types of motion. On the basis of integrated electromyography (IEMG), the identification of finger operation is performed using a support vector machine based classifier, and the finger operation is identified as one of the six motions. In addition, a new method for controlling a myoelectric prosthetic hand with IEMG is proposed. It has been reported that the IEMG represents the amount of the activity of a muscle. Therefore, based on the result of the identification of finger operation, the robotic hand for the myoelectric prosthetic hand was controlled on the basis of the magnitude of the IEMG. Thus, the myoelectric prosthetic hand can be controlled according to the grade of muscular activity. Experiments were performed to verify the proposed methods.