Open Access Open Access  Restricted Access Subscription or Fee Access

Fusion of Direct Probabilistic Multi-Class Support Vector Machines to Enhance Mental Tasks Recognition Performance in BCI Systems

(*) Corresponding author

Authors' affiliations



Support vector machines (SVM) are powerful discriminate models that were originally created only to solve dichotomous problems. Their extension to multi-category problems is always an active research issue. The proposed methods can roughly be classified into two strategies: the indirect strategy which subdivides the multiclass problem into a set of bi-class sub-problems, and the direct strategy which attempts to build a multi-class SVM (M-SVM) by resolving a global optimization problem. In this study, we firstly implement and compare four M-SVM models: Weston and Watkins, Crammer and Singer, Lee Lin and wahba, and Quadratic Loss M-SVM. The four models work separately, the outputs of each one are calibrated confidence measures and aim to output probability estimates of five disctinct mental tasks. We secondly propose to average the outputs of the four M-SVM to exploit the advantages of each model and consequently approve the classification decision. The study demonstrates that all M-SVM produce approximately a similar accuracy. However Crammer and Singer model appears more accurate for mental tasks recognition with an average accuracy between 74.95% and 93.3%. Also, a significant improvement in the classification accuracy is obtained by the fusion of M-SVM outputs.
Copyright © 2018 Praise Worthy Prize - All rights reserved.


Brain Computer Interface (BCI); ElectroEncephaloGram (EEG); Mental Tasks Multi-class Support Vector Machines (M-SVM); Fusion; Discrete Wavelet Transform (DWT)

Full Text:



R. S. Vaid, P. Singh, C. Kaur, EEG signal analysis for BCI interface: a review. IEEE Trans. advanced computing and communication technologies, 2015, Pages 143-147.

P. Prashant, A. Joshi, V. Gandhi. Brain computer interface: A review, IEEE Trans. Engineering, 2015.

C. Im, J. M. Seo, A review of electrodes for the electrical brain signal recording, Biomedical Engineering Letters (Springer). volume 6, (Issue 3), 2016, Pages 104-112. doi:10.1007/s13534-016-0235-1

C. Anderson, S. Devulapalli, E. Stolz, EEG signal classification with different signal representation, In: F. Girosi, J. Makhoul, E. Manolakos, E.Wilson (Eds.), IEEE Service Centre. Piscataway, NJ, 1995, Pages 475-483.

P. Diez, V. Mut, E. Laciar, A. Torres, E. Avila, Application of the empirical mode decomposition to the extraction of features from eeg signals for mental task classification. IEEE Trans. engineering in medicine and biology society, 2009, Pages 2579–2582.

K. Sonkin, L. Stankevich, Y. Khomenko, Z. Nagornova, N. Shemyakina, A. Koval, D. Perets, Neurological Classifier Committee Based on Artificial Neural Networks and Support Vector Machine for Single-Trial EEG Signal Decoding. Advances in Neural Networks (Springer), Volume 9719, 2017, Pages 100-107.

V. K. Benzy, A. Jasmin. A Combined Wavelet and Neural Network Based Model for Classifying Depth of Anaesthesia. Procedia Computer Science (Elsevier), Volume 46, 2015, Pages 1610-1617.

N. Liang, P. Saratchandran, G. Huang, N. Sundararajan, Classification of mental tasks from eeg signals using extreme learning machine, International Journal of Neural Systems, Volume 16, (Issue 1), 2006, Page 29-38.

Salguero, J., Avilés Sánchez, O., Mauledoux Monroy, M., Design of a Personal Communication Device, Based in EEG Signals, (2017) International Journal on Communications Antenna and Propagation (IRECAP), 7 (2), pp. 88-94.
Homri, I., Yacoub, S., Ellouze, N., Combined Approaches of Features Selection for EEG Classification, (2015) International Review on Computers and Software (IRECOS), 10 (3), pp. 256-264.

H. Hariharan, V. Vijean, R. Sindhu, P. Divakar, A. Saidatul, and Z. Yaacob, Classification of mental tasks using stockwell transform, Computers and Electrical Engineering (Elsevier), Volume 40,2014, Pages. 1741-1749.

Gupta, R. K. Agrawal, B. Kaur. Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods. Soft computing (Springer), Volume 19,2015, Pages 2799-2812.

M. Hendel, A. Benyettou, F. Hendel. Hybrid self organizing map and probabilistic quadratic loss multi-class support vector machine for mental tasks classification. Informatics in medicine unlocked (Elsevier), Volume 4,2016, Pages 1-9.

Gupta, J.S.Kirar. A novel approach for extracting feature from EEG signal for Mental Task Classification. IEEE Trans. Computing and Network Communications, 2015, Pages 829-832.

A. Gupta . D. Kumar. Fuzzy clustering-based feature extraction method for mental task classification. Brain Informatics (Springer), 2016.

M. M. El Bahy, M. Hosny, W. A. Mohamed, M. Ibrahim. EEG Signal Classification Using Neural Network and Support Vector Machine in Brain Computer Interface. Advances in Intelligent Systems and Computing (Springer), Volume 533, 2017, Pages 246-256.

Sarno, R., Munawar, M., Nugraha, B., Real-Time Electroencephalography-Based Emotion Recognition System, (2016) International Review on Computers and Software (IRECOS), 11 (5), pp. 456-465.

Z. Keirn, J. Aunon, A new mode of communication between man and his surroundings. IEEE Trans. biomedical engineering, Volume 12, 1990, Pages 1209-1214.

Werteni, H., Yacoub, S., Ellouze, N., Classification of Sleep Stages Based on EEG Signals, (2015) International Review on Computers and Software (IRECOS), 10 (2), pp. 174-181.

J. Weston, and C. Watkins, Multi-class support vector machines. Royal Holloway, University of London, Department of Computer Science, Technical Report CSD-TR-98-04.1998.

K. Crammer, and Y. Singer, On the algorithmic implementation of multiclass kernelbased vector machines. Journal of Machine Learning Research, Volume 2, 2001, Pages 265-292.

Y. Lee, Y. Lin, and G. Wahba, Multicategory support vector machines: Theory and application to the classification of microarray data and satellite radiance data. Journal of the American Statistical Association, Volume 99, (Issue 465), 2004, Pages 67-81.

Y. Guermeur, and E. Monfrini, A quadratic loss multi-class svm for which a radiusmargin bound applies. INFORMATICA, Volume 22, (Issue 1), 2011, Pages 73-96.

Z. Keirn, Alternative modes of communication between man and machines. master's dissertation, Dept. Elect. Eng., Purdue Univ., USA, 1988.

M.Tavakolan, X.Yong, X.Zhang, C.Menon. Classification Scheme for Arm Motor Imagery. Journal of Medical and Biological Engineering (Springer). Volume 36, (Issue 1), 2016, Pages 12-21

Y. Guermeur, A generic model of multi-class support vector machine. International Journal of Intelligent Information and Database Systems, Volume 6, (Issue 6), 2012, Pages 555-577.

F. Lauer and Y. Guermeur. MSVMpack: a multi-class support vector machine package. Journal of Machine Learning Research, Volume 12, 2012, Pages 2269-2272.

J. C. Platt, Probabilities for SV machines. In A.J. Smola, P.L. Bartlett, B. Schölkopf, and D. Schuurmans editors, Advances in Large Margin Classifiers, 2005,chapter 5, pages 61-73. The MIT Press, Cambridge, MA.

Y. Bennani and F. Bossaert. Predictive neural net-works for traffic disturbance detection in the tele-phonenetwork. IEEE Trans. Computational Engineering in System Applications,


  • There are currently no refbacks.

Please send any question about this web site to
Copyright © 2005-2023 Praise Worthy Prize