Control of a Robot Arm by Electromyogram -Recognition of Arm Motion by Neural Network

Masafumi Uchida; Hideto Ide

doi:10.20965/jrm.1996.p0372

single-rb.php

« previous

JRM Vol.8 No.4 pp. 372-377

doi: 10.20965/jrm.1996.p0372

(1996)

Paper:

Views over last 60 days: 255

Control of a Robot Arm by Electromyogram -Recognition of Arm Motion by Neural Network

Masafumi Uchida, Hideto Ide

College of Science and Engineering, Aoyama Gakuin University, 6-16-1 Chitosedai, Setagaya-ku, Tokyo, 157 Japan

Received:

April 11, 1996

Accepted:

May 10, 1996

Published:

August 20, 1996

Keywords:

EMG, Neural network, Interval-value

Abstract

In this study, 1/3 Octave-analyzed EMG patterns were classified by neural networks which possess learning ability and deal with Interval-Valued data to cope with the position slip of electrodes. Interval-Valued data is a method express an attribute as a dot in the multi-dimension. For example, the attribute is constant and is changing. EMG were measured under following conditions; (1) closing hand, (2) opening hand, (3) bending wrist to the bending side, (4) bending wrist to the stretching side, (5) turning wrist to the inside, (6) turning wrist to the outside.

Cite this article as:

M. Uchida and H. Ide, “Control of a Robot Arm by Electromyogram -Recognition of Arm Motion by Neural Network,” J. Robot. Mechatron., Vol.8, No.4, pp. 372-377, 1996.

Data files:

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.