Independent Component Ensemble of EEG for Brain-Computer Interface

被引:52
作者
Chuang, Chun-Hsiang [1 ,2 ]
Ko, Li-Wei [2 ,3 ]
Lin, Yuan-Pin [4 ]
Jung, Tzyy-Ping [4 ]
Lin, Chin-Teng [1 ,2 ]
机构
[1] Natl Chiao Tung Univ, Dept Elect & Comp Engn, Hsinchu 30010, Taiwan
[2] Natl Chiao Tung Univ, Brain Res Ctr, Hsinchu 30010, Taiwan
[3] Natl Chiao Tung Univ, Dept Biol Sci & Technol, Hsinchu 30010, Taiwan
[4] Univ Calif San Diego, Inst Neural Computat, Swartz Ctr Computat Neurosci, La Jolla, CA 92093 USA
关键词
Brain-computer interface (BCI); independent component analysis (ICA); multiple classifier system; SINGLE-TRIAL EEG; FEATURE-EXTRACTION; DROWSINESS; DYNAMICS; SLEEP; CLASSIFICATION; ALERTNESS; SYSTEM; ICA;
D O I
10.1109/TNSRE.2013.2293139
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Recently, successful applications of independent component analysis (ICA) to electroencephalographic (EEG) signals have yielded tremendous insights into brain processes that underlie human cognition. Many studies have further established the feasibility of using independent processes to elucidate human cognitive states. However, various technical problems arise in the building of an online brain-computer interface (BCI). These include the lack of an automatic procedure for selecting independent components of interest (ICi) and the potential risk of not obtaining a desired ICi. Therefore, this study proposes an ICi-ensemble method that uses multiple classifiers with ICA processing to improve upon existing algorithms. The mechanisms that are used in this ensemble system include: 1) automatic ICi selection; 2) extraction of features of the resultant ICi; 3) the construction of parallel pipelines for effectively training multiple classifiers; and a 4) simple process that combines the multiple decisions. The proposed ICi-ensemble is demonstrated in a typical BCI application, which is the monitoring of participants' cognitive states in a realistic sustained-attention driving task. The results reveal that the proposed ICi-ensemble outperformed the previous method using a single ICi with (91.6% versus 84.3%) in the cognitive state classification. Additionally, the proposed ICi-ensemble method that characterizes the EEG dynamics of multiple brain areas favors the application of BCI in natural environments.
引用
收藏
页码:230 / 238
页数:9
相关论文
共 48 条
[1]  
[Anonymous], NEURAL COMPUT APPL
[2]  
[Anonymous], CLASSIFICATION PARAM
[3]  
[Anonymous], COMPUTAT INTELL NEUR
[4]   Driver sleepiness - Evaluation of reaction time measurement as a secondary task [J].
Baulk, SD ;
Reyner, LA ;
Horne, JA .
SLEEP, 2001, 24 (06) :695-698
[5]   AN INFORMATION MAXIMIZATION APPROACH TO BLIND SEPARATION AND BLIND DECONVOLUTION [J].
BELL, AJ ;
SEJNOWSKI, TJ .
NEURAL COMPUTATION, 1995, 7 (06) :1129-1159
[6]  
Blankertz B, 2002, ADV NEUR IN, V14, P157
[7]   EEG-based lapse detection with high temporal resolution [J].
Davidson, Paul R. ;
Jones, Richard D. ;
Peiris, Malik T. R. .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2007, 54 (05) :832-839
[8]   EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis [J].
Delorme, A ;
Makeig, S .
JOURNAL OF NEUROSCIENCE METHODS, 2004, 134 (01) :9-21
[9]   Ensemble methods in machine learning [J].
Dietterich, TG .
MULTIPLE CLASSIFIER SYSTEMS, 2000, 1857 :1-15
[10]   Electroencephalographic study of drowsiness in simulated driving with sleep deprivation [J].
Eoh, HJ ;
Chung, MK ;
Kim, SH .
INTERNATIONAL JOURNAL OF INDUSTRIAL ERGONOMICS, 2005, 35 (04) :307-320