计算机应用 ›› 2014, Vol. 34 ›› Issue (11): 3357-3360.DOI: 10.11772/j.issn.1001-9081.2014.11.3353

• 行业与领域应用 • 上一篇    下一篇

基于支持向量机多分类的眼电辅助肌电的人机交互

张毅1,刘睿1,罗元2   

  1. 1. 重庆邮电大学 信息无障碍工程研发中心,重庆 400065
    2. 重庆邮电大学 光纤通信技术重点实验室,重庆 400065
  • 收稿日期:2014-05-16 修回日期:2014-07-15 出版日期:2014-11-01 发布日期:2014-12-01
  • 通讯作者: 刘睿
  • 作者简介: 
    张毅(1966-),男,重庆人,教授,博士生导师,主要研究方向:机器人、数据融合、信息无障碍;刘睿(1988-),女,山东昌邑人,硕士研究生,主要研究方向:智能系统、机器人、人机接口、模式识别;罗元(1972-),女,贵州贵阳人,〖BP(〗【:副院长,〖BP)〗教授,博士,主要研究方向:信号与信息处理、数字图像处理。
  • 基金资助:

    国家自然科学基金资助项目;科技部国际合作项目;重庆市科技攻关项目

Electrooculogram assisted electromyography human-machine interface system based on multi-class support vector machine

ZHANG Yi1,LIU Rui1,LUO Yuan2   

  1. 1. Information Accessibility Engineering Research and Development Center,
    2. Key Laboratory of Optical Fiber Communication Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Received:2014-05-16 Revised:2014-07-15 Online:2014-11-01 Published:2014-12-01
  • Contact: LIU Rui

摘要:

针对单一肌电信号在控制系统中正确识别率不高问题,设计并实现了一种基于支持向量机(SVM)多分类的眼电(EOG)辅助肌电(EMG)的人机交互(HCI)系统。该系统采用改进小波包算法和阈值法分别对EMG信号和EOG信号进行特征提取,并对特征向量融合;然后提取特征参数作为SVM的输入来识别EMG信号和EOG信号动作模式,根据分类结果生成控制命令。实验证明,该系统比单一肌电控制系统更便于操作,稳定性好,正确识别率高。

Abstract:

Concerning the low correct recognition rate of the Electromyography (EMG) control system, a new Human-Computer Interaction (HCI) system based on Electrooculogram (EOG) assisted EMG was designed and implemented. The feature vectors of EOG and EMG were extracted by threshold method and improved wavelet transform separately, and the feature vectors were integrated together. Then the features were classified by multi-class Support Vector Machine (SVM), and the different control commands were generated according to the result of pattern recognition. The experimental results prove that, compared with the single EMG control system, the new system has better operability and stability with higher correct recognition rate.

中图分类号: