中国邮电高校学报(英文) ›› 2014, Vol. 21 ›› Issue (3): 98-105.doi: 10.1016/S1005-8885(14)60306-X

• Artificial Intelligence • 上一篇    下一篇

Forehead sEMG signal based HMI for hands-free control

张毅, 祝翔, 代凌凌, 罗元   

  1. National Engineering Research and Development Center for Information Accessibility, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • 出版日期:2014-06-30
  • 通讯作者: ZHU Xiang E-mail:125751366@qq.com
  • 基金资助:

    This work was supported by the International Cooperation Project of Ministry of Science and Technology (2010DFA12160).

Forehead sEMG signal based HMI for hands-free control

张毅, 祝翔, 代凌凌, 罗元   

  1. National Engineering Research and Development Center for Information Accessibility, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Online:2014-06-30
  • Supported by:

    This work was supported by the International Cooperation Project of Ministry of Science and Technology (2010DFA12160).

摘要:

A hands-free method is proposed to control an electric powered wheelchair (EPW) based on surface electromyography (sEMG) signals. A CyberLink device is deployed to obtain and analyze forehead sEMG signals generated by the facial movements. The autoregressive (AR) model is used to extract sEMG features. Then, the back-propagation artificial neural network (BPANN) is proposed to recognize different facial movement patterns and improved by Bayesian regularization and Levenberg-Marquardt (LM) algorithm. A sEMG based human-machine interface (HMI) is designed to map facial movement patterns into corresponding control commands. The experimental results show that the method is simple, real-time and have a high recognition rate.

关键词:

intelligent wheelchair, sEMG, HMI, AR model, BP artificial neural network

Abstract:

A hands-free method is proposed to control an electric powered wheelchair (EPW) based on surface electromyography (sEMG) signals. A CyberLink device is deployed to obtain and analyze forehead sEMG signals generated by the facial movements. The autoregressive (AR) model is used to extract sEMG features. Then, the back-propagation artificial neural network (BPANN) is proposed to recognize different facial movement patterns and improved by Bayesian regularization and Levenberg-Marquardt (LM) algorithm. A sEMG based human-machine interface (HMI) is designed to map facial movement patterns into corresponding control commands. The experimental results show that the method is simple, real-time and have a high recognition rate.

Key words:

intelligent wheelchair, sEMG, HMI, AR model, BP artificial neural network