310 Design and Evaluation of Motion Path for Increasing Specified Muscle Strength Using Neural Network

Abstract

In recent years, ageing of the population has been emerged as a social issue in Japan. Therefore, it is important to regain and maintain muscle strength for care prevention. We are researching specified muscle training for efficient strengthening. In the present study, design of a motion path is proposed for the specified muscle training using neural network. For training, the load is applied by using a 2-link arm. By using the proposed method to estimate muscle activity level, it is possible to design a motion path that maximizes the activity of agonist muscles and minimizes the activity of other muscles. EMG signal is measured during a training experiment and the degree of muscular revitalization is evaluated by the amplitude of EMG signal. Finally, the effectiveness of proposed approach is demonstrated through experiments.