Common Spatial Pattern Ensemble Classifier and Its Application in Brain-Computer Interface

作     者：Xu Lei Ping Yang Peng Xu Tie-Jun Liu De-Zhong Yao 

作者机构：Key Laboratory for NeuroInformation of Ministry of EducationSchool of Life Science and TechnologyUniversity of Electronic Science and Technology of ChinaChengdu610054China 

出 版 物：《Journal of Electronic Science and Technology》 (Journal of Electronic Science and Technology of China)

年 卷 期：2009年第000卷第1期

页      面：17-21页

学科分类：08[工学] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the national natural science foundation of china under grant no. 30525030  60701015  and 60736029 

主　　题：Brain-computerinterface channelselection classifierensemble commonspatialpattern 

摘      要：Common spatial pattern(CSP) algorithm is a successful tool in feature estimate of brain-computer interface(BCI).However,CSP is sensitive to outlier and may result in poor outcomes since it is based on pooling the covariance matrices of *** this paper,we propose a simple yet effective approach,named common spatial pattern ensemble(CSPE) classifier,to improve CSP *** division of recording channels,multiple CSP filters are *** projection,log-operation,and subtraction on the original signal,an ensemble classifier,majority voting,is achieved and outlier contaminations are *** results demonstrate that the proposed CSPE classifier is robust to various artifacts and can achieve an average accuracy of 83.02%.