文献类型：期刊文献

英文题名：Sparse Bayesian multiway canonical correlation analysis for EEG pattern recognition

作者：Zhang, Yu[1];Zhou, Guoxu[2];Jin, Jing[1];Zhang, Yangsong[3];Wang, Xingyu[1];Cichocki, Andrzej[4]

机构：[1]East China Univ Sci & Technol, Minist Educ, Key Lab Adv Control & Optimizat Chem Proc, Shanghai 200237, Peoples R China;[2]Guangdong Univ Technol, Sch Automat, Guangzhou 510006, Guangdong, Peoples R China;[3]Southwest Univ Sci & Technol, Sch Comp Sci & Technol, Mianyang 621010, Peoples R China;[4]RIKEN Brain Sci Inst, Lab Adv Brain Signal Proc, Wako, Saitama 3510198, Japan

年份：2017

卷号：225

起止页码：103

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20165203175223);WOS:【SCI-EXPANDED(收录号:WOS:000392164400010)】；

基金：This study was supported in part by the Nation Nature Science Foundation of China under Grants 61305028, 91420302, 61573142, 61673124, 81401484, Fundamental Research Funds for the Central Universities under Grants WH1314023, WG1414005, WH1516018, WH1414022, Shanghai Chenguang Program No. 14CG31, Guangdong Province Natural Science Foundation under Grant 2014A030308009, Jinan Youth Star of Science and Technology Plan No. 201406002.

语种：英文

外文关键词：Brain-computer interface (BCI); Electroencephalogram (EEG); Multiway canonical correlation analysis (MCCA); Sparse Bayesian learning; Steady-state visual evoked potential (SSVEP)

摘要：L1-regularized multiway canonical correlation analysis (L1-MCCA) has been introduced to reference signal optimization in steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI). The effectiveness of L1-regularization on significant trial selection highly depends on the regularization parameter setting, which can be typically determined by cross-validation (CV). However, CV will substantially reduce the practicability of BCI system due to additional data requirement for the parameter validation and relatively high computational cost. To solve the problem, this study proposes a Bayesian version of L1-MCCA (called SBMCCA) by exploiting sparse Bayesian learning. The SBMCCA method avoids CV and can efficiently estimate the model parameters under the Bayesian evidence framework. Experimental results show that the SBMCCA method achieved comparable recognition accuracy but much higher computational efficiency in contrast to the L1-MCCA method.