Vol. 117, Issue 6, June 2010, pp.50-61

Surface Electromyographic Sensor for Human Motion Estimation Based on Arm Wrestling Robot

Zhen GAO and Dan ZHANG

Faculty of Engineering and Applied Science,

University of Ontario Institute of Technology, Oshawa, Ontario, L1H 7K4 Canada

Tel.: 1-905-721-8668 ext. 3504, fax: 1-905-721-3370

E-mail: Zhen.Gao@uoit.ca

Received: 19 April 2010   /Accepted: 21 June 2010   /Published: 25 June 2010

Abstract: In this paper, the surface electromyographic (EMG) sensor is developed to acquire the EMG signals from the upper limb when the participants compete with the arm wrestling robot (AWR) which is fabricated to play arm wrestling game with human on a table with pegs for entertainment and human motion modeling of upper limbs muscle. As the EMG signal is a measurement of the anatomical and physiological characteristic of the specific muscle, the macroscopical movement patterns of the human body can be classified and recognized. The high-frequency noises are eliminated effectively and the characteristics of EMG signals can be extracted through wavelet packet transformation. Auto-regressive model of EMG is conducted to effectively simulate the stochastic time sequences with a series of auto-regressive coefficients. The win/lose pattern is recognized by neural network based on extracted characteristics of surface EMG signal.

Keywords: Arm wrestling robot, Electromyographic signal, Auto-regressive model, Wavelet packet transformation

Click <here> or title of paper to download the full pages article (1.31 Mb)

1999 - 2010 Copyright ©, International Frequency Sensor Association (IFSA). All Rights Reserved.

Home - News - Links - Archives - Tools - Standardization - Patents - Marketplace - Projects - Wish List - Subscribe - Search - Membership - Submit Press Release

 Members Area -Sensors Portal -Training Courses - S&T Digest - For advertisers - Bookstore - Forums - Polls - Sensor Jobs - e-Shop - Site Map