文献类型：期刊文献

英文题名：AGGREGATION OF SPARSE LINEAR DISCRIMINANT ANALYSES FOR EVENT-RELATED POTENTIAL CLASSIFICATION IN BRAIN-COMPUTER INTERFACE

作者：Zhang, Yu[1];Zhou, Guoxu[2];Jin, Jing[1];Zhao, Qibin[2];Wang, Xingyu[1];Cichocki, Andrzej[2,3]

机构：[1]E China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Shanghai 200237, Peoples R China;[2]RIKEN Brain Sci Inst, Lab Adv Brain Signal Proc, Wako, Saitama, Japan;[3]Polish Acad Sci, Syst Res Inst, PL-01447 Warsaw, Poland

年份：2014

卷号：24

期号：1

外文期刊名：INTERNATIONAL JOURNAL OF NEURAL SYSTEMS

收录：;EI(收录号：20135217140218);WOS:【SCI-EXPANDED(收录号:WOS:000328945600001)】；

基金：The authors sincerely thank the editor and the anonymous reviewers for their insightful comments and suggestions that helped improve the paper. This study was supported in part by the Nation Nature Science Foundation of China under Grant 61305028, Grant 61074113, Grant 61203127, Grant 61103122, Grant 61202155, Fundamental Research Funds for the Central Universities Grant WH1314023, Grant WH1114038, Shanghai Leading Academic Discipline Project B504, and JSPS KAKENHI Grant 24700154.

语种：英文

外文关键词：Aggregation; brain-computer interface (BCI); electroencephalogram (EEG); event-related potential (ERP); sparse linear discriminant analysis

摘要：Two main issues for event-related potential (ERP) classification in brain-computer interface (BCI) application are curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classification performance, especially with insufficient training samples resulted from limited calibration time. This study introduces an aggregation of sparse linear discriminant analyses (ASLDA) to overcome these problems. In the ASLDA, multiple sparse discriminant vectors are learned from differently l(1)-regularized least-squares regressions by exploiting the equivalence between LDA and least-squares regression, and are subsequently aggregated to form an ensemble classifier, which could not only implement automatic feature selection for dimensionality reduction to alleviate curse-of-dimensionality, but also decrease the variance to improve generalization capacity for new test samples. Extensive investigation and comparison are carried out among the ASLDA, the ordinary LDA and other competing ERP classification algorithms, based on different three ERP datasets. Experimental results indicate that the ASLDA yields better overall performance for single-trial ERP classification when insufficient training samples are available. This suggests the proposed ASLDA is promising for ERP classification in small sample size scenario to improve the practicability of BCI.