Author:
Nishikawa Yoshio, ,Kagawa Yoshihito,Kurabayashi Jun,
Abstract
We propose high-speed motion discrimination method for three types of motions, pronating, flexing, and grasping without any mistake by acquired surface electromyography (EMG) signals from three locations on the right-forearm. To achieve high-speed and accurate method, we introduce motion discrimination method based on a comparison of features extracted by wavelet transform of EMG signals via a database, and also we examine the places on the forearm where the system acquires surface EMG signals. As a final, we discuss whether the discrimination rate was improved by motion training.
Publisher
Fuji Technology Press Ltd.
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Human-Computer Interaction
Reference18 articles.
1. O. Fukuda, K. Tsujimura, T. Tsuji, and A. Otsuka, “Control of a Meal-assistance Manipulator Using EMG Signals,” JJMI, Vol.74, No.5, pp. 229-237, 2004.
2. O. Fukuda, T. Tsuji, and K. Kaneko, “A Human Supporting Manipulator Based on Manual Control Using EMG Signals,” JRSJ, Vol.18, No.3, pp. 387-394, 2000.
3. O. Fukuda, T. Tsuji, and M. Kaneko, “A Human-Assisting Manipulator Teleoperated by EMG Signals and Arm Motions,” IEEE Trans. on Robotics and Automation, Vol.19, No.2, pp. 210-222, 2003.
4. T. Tsuji, K. Ito, and M. Nagamachi, “A limb-function discrimination method using EMG signals for the control of multifunctional powered prostheses,” IEICE Trans., Vol.J70-D, No.1, pp. 207-215, 1987.
5. T. Tsuji, K. Takahashi, O. Fukuda, and M. Kaneko, “Pattern Classification of EMG Signals Using an Event-Driven Task Model,” JRSJ, Vol.20, No.7, pp. 771-777, 2002.