文献类型：期刊文献

英文题名：Sparse Group Representation Model for Motor Imagery EEG Classification

作者：Jiao, Yong[1];Zhang, Yu[2];Chen, Xun[3];Yin, Erwei[4];Jin, Jing[1];Wang, Xingyu[1];Cichocki, Andrzej[5,6,7]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Stanford Univ, Dept Psychiat & Behav Sci, Stanford, CA 94305 USA;[3]Univ Sci & Technol China, Dept Elect Sci & Technol, Hefei 230027, Anhui, Peoples R China;[4]Acad Mil Sci China, Unmanned Syst Res Ctr, Natl Inst Def Technol Innovat, Beijing 100081, Peoples R China;[5]Skolkowo Inst Sci & Technol, Moscow, Russia;[6]Nicolaus Copernicus Univ, PL-87100 Torun, Poland;[7]RIKEN Brain Sci Inst, Wako, Saitama 3510106, Japan

年份：2019

卷号：23

期号：2

起止页码：631

外文期刊名：IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS

收录：;EI(收录号：20181905146633);WOS:【SCI-EXPANDED(收录号:WOS:000460666400019)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grants 91420302, 61573142, 61501164, and 61703407, in part by the Fundamental Research Funds for the Central Universities under Grants WH1516018 and 222201717006, in part by the Programme of Introducing Talents of Discipline to Universities (the 111 Project) under Grant B17017, in part by the Ministry of Education and Science of the Russian Federation under Grant 14.756.31.0001, and in part by the Polish National Science Center under Grant 2016/20/W/N24/00354. The work of E. Yin was supported by the Foundation of Key Laboratory of Science and Technology for National Defense (No. 6142222030301).

语种：英文

外文关键词：Brain-computer interface (BCI); electroencephalogram (EEG); motor imagery (MI); sparse group representation model (SGRM); common spatial pattern (CSP)

摘要：A potential limitation of a motor imagery (MI) based brain-computer interface (BCI) is that it usually requires a relatively long time to record sufficient electroencephalogram (EEG) data for robust classifier training. The calibration burden during data acquisition phase will most probably cause a subject to be reluctant to use a BCI system. To alleviate this issue, we propose a novel sparse group representation model (SGRM) for improving the efficiency of MI-based BCI by exploiting the intersubject information. Specifically, preceded by feature extraction using common spatial pattern, a composite dictionary matrix is constructed with training samples from both the target subject and other subjects. By explicitly exploiting within-group sparse and group-wise sparse constraints, the most compact representation of a test sample of the target subject is then estimated as a linear combination of columns in the dictionary matrix. Classification is implemented by calculating the classspecific representation residual based on the significant training samples corresponding to the nonzero representation coefficients. Accordingly, the proposed SGRM method effectively reduces the required training samples from the target subject due to auxiliary data available from other subjects. With two public EEG data sets, extensive experimental comparisons are carried out between SGRM and other stateof-the-art approaches. Superior classification performance of our method using 40 trials of the target subject for model calibration (Averaged accuracy = 78.2%, Kappa = 0.57 and Averaged accuracy = 77.7%, Kappa = 0.55 for the two data sets, respectively) indicates its promising potential for improving the practicality of MI-based BCI.