MIXTURES OF COMMON SPATIAL PATTERNS FOR FEATURE EXTRACTION OF EEG SIGNALS

摘要：

The method of common spatial patterns (CSP) is an effective feature extractor for representing electroencephalogram (EEG) signals with the purpose of classification in brain computer interfaces (BCIs). However, it has two apparent demerits mainly about the estimation of covariance matrices which sacrifice its performance. First, the estimator of sample covariance is non-robust; Second, the possible high dimension of the covariance matrices makes exact parameter estimation difficult. In this paper, we propose the approach of mixtures of CSP (MCSP) to conquer this problem. MCSP constructs multiple CSP feature extractors by the bootstrap sampling method, and has the potential to improve the performance of one single feature extractor. The classification result of a new EEG sample is obtained by combining several classifier outputs corresponding to the multiple feature extractors. Experimental comparisons with the state-of-the-art method for classifying real EEG signals of motor imagery tasks show the effectiveness of the proposed MCSP method.

关键词： Bootstrap Brain computer interface (BCI) Common spatial patterns (CSP) EEG signal classification Feature eztraction

作者: SHI-LIANG SUN JIN-HUA XU LI-YANG YU YOU-GUANG CHEN AI-LIAN FANG

作者单位: Department of Computer Science and Technology, East China Normal University, Shanghai 200241, China Computer Center, East China Normal University, Shanghai 200241, China

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 2923-2926

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）