Support vector EEG classification in the Fourier and time-frequency correlation domains

被引：44

作者：

Garcia, GN ^{[1
]}

Ebrahimi, T ^{[1
]}

Vesin, JM ^{[1
]}

机构：

[1] Swiss Fed Inst Technol, EPFL, CH-1015 Lausanne, Switzerland

来源：

1ST INTERNATIONAL IEEE EMBS CONFERENCE ON NEURAL ENGINEERING 2003, CONFERENCE PROCEEDINGS | 2003年

关键词：

direct brain-computer communication; EEG classification; SVM; optimal SVM parameter choice; time-frequency correlation;

D O I：

10.1109/CNE.2003.1196897

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we use support vector machines (SVM) for classifying EEG signals corresponding to imagined motor movements. The parameters of an SVM Kernel are optimized for minimizing a theoretical error bound. Fourier features and correlative time-frequency based features are extracted from EEG signals and compared with respect to their discriminatory power.

引用

页码：591 / 594

页数：4

共 9 条

[1]

[Anonymous], 1998, Encyclopedia of Biostatistics

[2] A tutorial on Support Vector Machines for pattern recognition [J].

Burges, CJC .

DATA MINING AND KNOWLEDGE DISCOVERY, 1998, 2 (02) :121-167

[3] Choosing multiple parameters for support vector machines [J].

Chapelle, O ;

Vapnik, V ;

Bousquet, O ;

Mukherjee, S .

MACHINE LEARNING, 2002, 46 (1-3) :131-159

[4]

GARCIA G, 2002, IEEE INT C DIG SIG P, V1, P301

[5]

Klem G H, 1999, Electroencephalogr Clin Neurophysiol Suppl, V52, P3

[6] Enhancement of left-right sensorimotor EEG differences during feedback-regulated motor imagery [J].

Neuper, C ;

Schlögl, A ;

Pfurtscheller, G .

JOURNAL OF CLINICAL NEUROPHYSIOLOGY, 1999, 16 (04) :373-382

[7]

Vapnik V., 1998, STAT LEARNING THEORY, V1, P2

[8]

Vapnik V., 2013, NATURE STAT LEARNING

[9] Brain-computer interfaces for communication and control [J].

Wolpaw, JR ;

Birbaumer, N ;

McFarland, DJ ;

Pfurtscheller, G ;

Vaughan, TM .

CLINICAL NEUROPHYSIOLOGY, 2002, 113 (06) :767-791

← 1 →