计算机与现代化

• 数据库与数据挖掘 • 上一篇    下一篇

基于RCE的空间滤波方法在运动想象#br#  电位识别中的应用

  

  1. 1.中国人民解放军91604部队,山东龙口265700; 2.大连民族学院信息与通信工程学院,辽宁大连116600
  • 收稿日期:2014-06-24 出版日期:2014-10-10 发布日期:2014-11-04
  • 作者简介:张守中(1976),男,山东日照人,中国人民解放军91604部队工程师,硕士,研究方向:计算机应用技术,信息处理技术; 肖瑛(1979),女(蒙古族),河北隆化人,大连民族学院信息 与通信工程学院副教授,博士,研究方向:通信信号处理。
  • 基金资助:
    国家自然科学基金资助项目(61201418); 中央高校基本科研业务费专项资金资助项目(DC12010218); 辽宁省高等学校优秀人才支持计划(LJQ2013126)

RCEbased Spatial Filtering Method for Recognition of Motor Imagery Potential

  1. 1. PLA 91604 Unit, Longkou 265700, China;
     2. College of Information and Communication Engineering, Dalian Nationality University, Dalian 116600, China
  • Received:2014-06-24 Online:2014-10-10 Published:2014-11-04

摘要:

在对运动想象电位进行模式识别时,需要对原始信号进行滤波以提取信号中区分度较高的成分用于分类,而在噪声较为严重时,滤波方法会导致有用信息的丢失,从而降低分类正确率。针对该问
题,本文提出节律成分提取(Rhythmic Component Extraction, RCE)与共空子空间分解(The Common Spatial Subspace Decomposition, CSSD)相结合的特征提取方法,对提取的特征信息使用线性
分类器进行分类。采用该方法对2003年国际BCI竞赛数据进行识别,测试数据的分类正确率达到87.23%,比使用传统空间滤波方法进行特征提取时的分类正确率提高了6.8%,表明该方法可有效地应用于左
右手运动想象电位的识别。

关键词: 运动想象电位, 脑电信号, 共空子空间分解, 节律成分提取

Abstract:

The original signal usually needs filtering to extract the components with higher degree of distinction before the motor imagery potential classification, which
results in loss of the useful information under the serious noise interference, as the result, the classification correct rate will be degraded. To solve this problem, hereby a
rhythmic component extraction (RCE) combined with common spatial subspace decomposition (CSSD) for feature extraction while using the linear classifier was proposed. The
identification accuracy reached 87.22% by using the method for the international BCI Competition 2003 data, classification accuracy improved by 6.8% compared with traditional
methods of spatial filtering, which show that the method can be effectively applied to the identification of left and right hand motor imagery potential.

Key words: motor imagery potential, electroencephalography, common spatial subspace decomposition, rhythmic component extraction

中图分类号: