Classification of EEG Using Adaptive SVM Classifier with CSP and Online Recursive Independent Component Analysis

被引:27
作者
Antony, Mary Judith [1 ]
Sankaralingam, Baghavathi Priya [2 ]
Mahendran, Rakesh Kumar [3 ]
Gardezi, Akber Abid [4 ]
Shafiq, Muhammad [5 ]
Choi, Jin-Ghoo [5 ]
Hamam, Habib [6 ,7 ,8 ,9 ]
机构
[1] Loyola ICAM Coll Engn & Technol, Dept Comp Sci & Engn, Chennai 600034, Tamil Nadu, India
[2] Rajalakshmi Engn Coll, Dept Comp Sci & Engn, Chennai 602105, Tamil Nadu, India
[3] Veltech Multitech Dr Rangarajan Dr Sakunthala Eng, Dept Elect & Commun Engn, Chennai 600062, Tamil Nadu, India
[4] COMSATS Univ Islamabad, Dept Comp Sci, Islamabad 45550, Pakistan
[5] Yeungnam Univ, Dept Informat & Commun Engn, Gyongsan 38541, South Korea
[6] Univ Moncton, Fac Engn, Moncton, NB E1A 3E9, Canada
[7] Int Inst Technol & Management, Libreville 1989, Gabon
[8] Univ Johannesburg, Sch Elect & Elect Engn Sci, Dept Elect Engn, ZA-2006 Johannesburg, South Africa
[9] Spectrum Knowledge Prod & Skills Dev, Sfax 3027, Tunisia
基金
加拿大自然科学与工程研究理事会;
关键词
electroencephalogram; adaptive classifier; support vector machine; common spatial pattern; online recursive independent component analysis; SPATIAL-PATTERNS; COMPUTER; FILTERS;
D O I
10.3390/s22197596
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
An efficient feature extraction method for two classes of electroencephalography (EEG) is demonstrated using Common Spatial Patterns (CSP) with optimal spatial filters. However, the effects of artifacts and non-stationary uncertainty are more pronounced when CSP filtering is used. Furthermore, traditional CSP methods lack frequency domain information and require many input channels. Therefore, to overcome this shortcoming, a feature extraction method based on Online Recursive Independent Component Analysis (ORICA)-CSP is proposed. For EEG-based brain-computer interfaces (BCIs), especially online and real-time BCIs, the most widely used classifiers used to be linear discriminant analysis (LDA) and support vector machines (SVM). Previous evaluations clearly show that SVMs generally outperform other classifiers in terms of performance. In this case, Adaptive Support Vector Machine (A-SVM) is used for classification together with the ORICA-CSP method. The results are promising, and the experiments are performed on EEG data of 4 classes' motor images, namely Dataset 2a of BCI Competition IV.
引用
收藏
页数:17
相关论文
共 26 条
[1]  
Ang KK, 2008, IEEE IJCNN, P2390, DOI 10.1109/IJCNN.2008.4634130
[2]   Studying the Influence of Requesters in Posted-price Crowdsourcing [J].
Bhattacharyya, Malay ;
Mridha, Sankar Kumar .
PROCEEDINGS OF THE ACM INDIA JOINT INTERNATIONAL CONFERENCE ON DATA SCIENCE AND MANAGEMENT OF DATA (CODS-COMAD'18), 2018, :1-10
[3]   SVM Classification of EEG Signals for Brain Computer Interface [J].
Costantini, G. ;
Todisco, M. ;
Casali, D. ;
Carota, M. ;
Saggio, G. ;
Bianchi, L. ;
Abbafati, M. ;
Quitadamo, L. .
NEURAL NETS WIRN09, 2009, 204 :229-233
[4]   Correlation-based common spatial pattern (CCSP): A novel extension of CSP for classification of motor imagery signal [J].
Darvish Ghanbar, Khatereh ;
Yousefi Rezaii, Tohid ;
Farzamnia, Ali ;
Saad, Ismail .
PLOS ONE, 2021, 16 (03)
[5]   Combined optimization of spatial and temporal filters for improving brain-computer interfacing [J].
Dornhege, Guido ;
Blankertz, Benjamin ;
Krauledat, Matthias ;
Losch, Florian ;
Curio, Gabriel ;
Mueller, Klaus-Robert .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2006, 53 (11) :2274-2281
[6]  
Feng MQ, 2013, PROCEEDINGS OF THE 2013 FOURTH INTERNATIONAL CONFERENCE ON INTELLIGENT CONTROL AND INFORMATION PROCESSING (ICICIP), P225
[7]   Simultaneous Design of FIR Filter Banks and Spatial Patterns for EEG Signal Classification [J].
Higashi, Hiroshi ;
Tanaka, Toshihisa .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2013, 60 (04) :1100-1110
[8]   Artifact Removal from EEG signals using Regenerative Multi-Dimensional Singular Value Decomposition and Independent Component Analysis [J].
Judith, A. Mary ;
Priya, S. Baghavathi ;
Mahendran, Rakesh Kumar .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2022, 74
[9]   Motor Imagery Based EEG Classification by Using Common Spatial Patterns and Convolutional Neural Networks [J].
Korhan, Nuri ;
Dokur, Zumray ;
Olmez, Tamer .
2019 SCIENTIFIC MEETING ON ELECTRICAL-ELECTRONICS & BIOMEDICAL ENGINEERING AND COMPUTER SCIENCE (EBBT), 2019,
[10]   An intelligent epilepsy seizure detection system using adaptive mode decomposition of EEG signals [J].
Kumar, Gulshan ;
Chander, Subhash ;
Almadhor, Ahmad .
PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE, 2022, 45 (01) :261-272