A New EEG Signal Processing Method Based on Low-Rank and Sparse Decomposition

被引：1

作者：

Kong, Wanzeng ^{[1
]}

Liu, Yan ^{[1
]}

Jiang, Bei ^{[1
]}

Dai, Guojun ^{[1
]}

Xu, Lin ^{[2
]}

机构：

[1] Hangzhou Dianzi Univ, Minist Educ, Key Lab Complex Syst Modeling & Simulat, Hangzhou, Zhejiang, Peoples R China

[2] Hangzhou Dianzi Univ, Sch Humanities & Law, Hangzhou, Zhejiang, Peoples R China

来源：

COGNITIVE SYSTEMS AND SIGNAL PROCESSING, ICCSIP 2016 | 2017年 / 710卷

基金：

对外科技合作项目（国际科技项目）; 中国博士后科学基金; 中国国家自然科学基金;

关键词：

EEG; Signal processing; Motor imagery; Low-rank and sparse decomposition; FLUCTUATIONS; VARIABILITY; ALGORITHMS;

D O I：

10.1007/978-981-10-5230-9_54

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Electroencephalography (EEG) signal processing is one of the critical parts in Brain-Computer Interface (BCI) applications. In this paper, we propose a hypothesis that EEG signal is composed by spontaneous background signals and mental task signals. Then, we introduce a new EEG signal processing method based on low rank and sparse decomposition. EEG signals can be decomposed as the sum of a low-rank signal matrix and a sparse signal matrix. BCI competition dataset of motor imagery is applied to compare the accuracy of the sparse EEG signal and the original EEG signal. The results show that the sparse part outperforms original data and the accuracy is improved by 3% to 5%.

引用

页码：556 / 564

页数：9

共 22 条

[1]

[Anonymous], INT C MACH LEARN

[2]

[Anonymous], UILUENG092214 UIUC

[3]

[Anonymous], 2012, ACM T KNOWL DISCOV D, DOI DOI 10.1145/2086737.2086742

[4] Dynamics of ongoing activity: Explanation of the large variability in evoked cortical responses [J].

Arieli, A ;

Sterkin, A ;

Grinvald, A ;

Aertsen, A .

SCIENCE, 1996, 273 (5283) :1868-1871

[5] Spontaneous Neural Fluctuations Predict Decisions to Attend [J].

Bengson, Jesse J. ;

Kelley, Todd A. ;

Zhang, Xiaoke ;

Wang, Jane-Ling ;

Mangun, George R. .

JOURNAL OF COGNITIVE NEUROSCIENCE, 2014, 26 (11) :2578-2584

[6] Optimizing spatial filters for robust EEG single-trial analysis [J].

Blankertz, Benjamin ;

Tomioka, Ryota ;

Lemm, Steven ;

Kawanabe, Motoaki ;

Mueller, Klaus-Robert .

IEEE SIGNAL PROCESSING MAGAZINE, 2008, 25 (01) :41-56

[7] Robust Principal Component Analysis? [J].

Candes, Emmanuel J. ;

Li, Xiaodong ;

Ma, Yi ;

Wright, John .

JOURNAL OF THE ACM, 2011, 58 (03)

[8] RANK-SPARSITY INCOHERENCE FOR MATRIX DECOMPOSITION [J].

Chandrasekaran, Venkat ;

Sanghavi, Sujay ;

Parrilo, Pablo A. ;

Willsky, Alan S. .

SIAM JOURNAL ON OPTIMIZATION, 2011, 21 (02) :572-596

[9] When Attention Wanders: How Uncontrolled Fluctuations in Attention Affect Performance [J].

Cohen, Marlene R. ;

Maunsell, John H. R. .

JOURNAL OF NEUROSCIENCE, 2011, 31 (44) :15802-15806

[10] Canonical correlation analysis applied to remove muscle artifacts from the electroencephalogram [J].

De Clercq, Wim ;

Vergult, Anneleen ;

Vanrumste, Bart ;

Van Paesschen, Wim ;

Van Huffel, Sabine .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2006, 53 (12) :2583-2587

← 1 2 3 →