Fuzzy support vector machine for classification of EEG signals using wavelet-based features

被引:97
作者
Xu, Qi [1 ]
Zhou, Hui [1 ]
Wang, Yongji [1 ]
Huang, Jian [1 ]
机构
[1] Huazhong Univ Sci & Technol, Dept Control Sci & Technol, Key Lab Image Proc & Intelligent Control, Wuhan 430074, Peoples R China
关键词
Brain-computer interface; Discrete wavelet transform; Fuzzy support vector machine; Motor imagery; Electroencephalogram; BRAIN-COMPUTER INTERFACE; BCI COMPETITION 2003; MOTOR IMAGERY; FEATURE-EXTRACTION; INFORMATION; PERFORMANCE; PATTERNS;
D O I
10.1016/j.medengphy.2009.04.005
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Translation of electroencephalographic (EEG) recordings into control signals for brain-computer interface (BCI) systems needs to be based on a robust classification of the various types of information. EEG-based BCI features are often noisy and likely to contain outliers. This contribution describes the application of a fuzzy support vector machine (FSVM) with a radial basis function kernel for classifying motor imagery tasks, while the statistical features over the set of the wavelet coefficients were extracted to characterize the time-frequency distribution of EEG signals. In the proposed FSVM classifier, a low fraction of support vectors was used as a criterion for choosing the kernel parameter and the trade-off parameter, together with the membership parameter based solely on training data. FSVM and support vector machine (SVM) classifiers outperformed the winner of the BCI Competition 2003 and other similar studies on the same Graz dataset, in terms of the competition criterion of the mutual information (MI), while the FSVM classifier yielded a better performance than the SVM approach. FSVM and SVM classifiers perform much better than the winner of the BCI Competition 2005 on the same Graz dataset for the subject 03 according to the competition criterion of the maximal MI steepness, while the FSVM classifier outperforms the SVM method. The proposed FSVM model has potential in reducing the effects of noise or outliers in the online classification of EEG signals in BCIs. (C) 2009 IPEM. Published by Elsevier Ltd. All rights reserved.
引用
收藏
页码:858 / 865
页数:8
相关论文
共 50 条
[31]   Classification of Working Memory Load Using Wavelet Complexity Features of EEG Signals [J].
Zarjam, Pega ;
Epps, Julien ;
Chen, Fang ;
Lovell, Nigel H. .
NEURAL INFORMATION PROCESSING, ICONIP 2012, PT II, 2012, 7664 :692-699
[32]   Classification of EEG Signals Recorded During Right/Left Hand Movement Imagery Using Fast Walsh Hadamard Transform Based Features [J].
Saka, Kubra ;
Aydemir, Onder ;
Ozturk, Mehmet .
2016 39TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP), 2016, :413-416
[33]   CGHF: A Computational Decision Support System for Glioma Classification Using Hybrid Radiomics- and Stationary Wavelet-Based Features [J].
Kumar, Rahul ;
Gupta, Ankur ;
Arora, Harkirat Singh ;
Pandian, Ganesh Namasivayam ;
Raman, Balasubramanian .
IEEE ACCESS, 2020, 8 :79440-79458
[34]   EEG Signals Processing Based on Fractal Dimension Features and Classified by Neural Network and Support Vector Machine in Motor Imagery for a BCI [J].
Montalvo Aguilar, J. ;
Castillo, J. ;
Elias, D. .
VI LATIN AMERICAN CONGRESS ON BIOMEDICAL ENGINEERING (CLAIB 2014), 2014, 49 :615-618
[35]   Synovial Sarcoma Classification Technique Using Support Vector Machine and Structure Features [J].
Arunachalam, P. ;
Janakiraman, N. ;
Sivaraman, Arun Kumar ;
Balasundaram, A. ;
Vincent, Rajiv ;
Rani, Sita ;
Dey, Barnali ;
Muralidhar, A. ;
Rajesh, M. .
INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2022, 32 (02) :1241-1259
[36]   Epileptic Seizure Classification from EEG Signals with Support Vector Machines [J].
Tuncer, Erdem ;
Bolat, Emine Dogru .
JOURNAL OF POLYTECHNIC-POLITEKNIK DERGISI, 2022, 25 (01) :239-249
[37]   A fusion wavelet-based binary pattern approach for enhanced electroencephalogram signal classification [J].
Ananthi, A. ;
Subathra, M. S. P. ;
George, S. Thomas ;
Peter, Geno ;
Stonier, Albert Alexander ;
Sairamya, N. J. .
COMPUTERS & ELECTRICAL ENGINEERING, 2025, 123
[38]   BSPKTM-SIFE-WST: bispectrum based channel selection using set-based-integer-coded fuzzy granular evolutionary algorithm and wavelet scattering transform for motor imagery EEG classification [J].
Kardam, Vikram Singh ;
Taran, Sachin ;
Pandey, Anukul .
SIGNAL IMAGE AND VIDEO PROCESSING, 2025, 19 (04)
[39]   Automatic detection of alertness/drowsiness from physiological signals using wavelet-based nonlinear features and machine learning [J].
Chen, Lan-lan ;
Zhao, Yu ;
Zhang, Jian ;
Zou, Jun-zhong .
EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (21) :7344-7355
[40]   EEG-Based Emotion Recognition Using Frequency Domain Features and Support Vector Machines [J].
Wang, Xiao-Wei ;
Nie, Dan ;
Lu, Bao-Liang .
NEURAL INFORMATION PROCESSING, PT I, 2011, 7062 :734-+