计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (20): 159-161.DOI: 10.3778/j.issn.1002-8331.2008.20.048

• 数据库、信号与信息处理 • 上一篇    下一篇

基于公共空间频率模型的脑电数据分类

唐 艳1,汤井田1,龚安栋1,2   

  1. 1.中南大学 信息物理学院,长沙 410083
    2.中南大学 信息科学与工程学院,长沙 410083
  • 收稿日期:2007-10-09 修回日期:2008-01-21 出版日期:2008-07-11 发布日期:2008-07-11
  • 通讯作者: 唐 艳

Classifying EEG signals based on CSSP

TANG Yan1,TANG Jing-tian1,GONG An-dong1,2   

  1. 1.Department of Info-Physics Engineering,Central South University,Changsha 410083,China
    2.Department of Information Science and Engineering,Central South University,Changsha 410083,China
  • Received:2007-10-09 Revised:2008-01-21 Online:2008-07-11 Published:2008-07-11
  • Contact: TANG Yan

摘要: 利用公共空间频率模型算法实现较少训练数据的脑电识别。首先给出公共空间频率模型算法的数学公式和求解过程,然后从数学分析角度说明表达实质含义,以及如何实现空间和频率上的同时滤波;再对于提取出来的特征,如何构造分类器,进行分类;最后用BCI Competition III的Iva数据包为数据源,证明了公共空间频率模型算法在BCI的实用性,能够达到更好的识别效果。

关键词: 脑机接口, 公共空间模型, 公共空间频率模型, 脑电信号

Abstract: The CSSP algorithm is presented to classify EEG signal with small training sets.Firstly,the CSSP algorithm is introduced with an elaborate description,and is illuminated how extract features in space and spectra.We present the method how to form the classifier.After a short description of this algorithm,we will apply it in data set Iva of BCI Competition III to prove the algorithm feasibility.The result illustrates the performance and validity of the algorithm.

Key words: Brain-Computer Interface(BCI), Common Spatial Patterns(CSSP), Common Spatio-Spectral Patterns(CSP), Electroencephalogram