Training Study Approaches for a SVM-Based BCI: Adaptation to the Model vs Adaptation to the User
Support Vector Machine (SVM) is extensively used in BCI classification. In this paper this classifier is used to differentiate between two mental tasks related to motor imaginary in order to check the possibility of improvement with two alternative adaptation (user’s adaptation and model adaptation). Two kind of training have been done by 4 subjects. In the first test (user’s adaptation to the model), each subject use a personalized model and 7 sessions are registered to compare the evolution of the results due to the user’s training. This initial model is done with a preliminary session which include register of 6 different motor imaginary tasks to select the best combination of them. The second test (model’s adaptation to the user) tries to evaluate the benefits of the updating of the model with new registers. The results show that, at least for this kind of imaginary tasks, these methods of adaptation with a SVM-based system have not a meaningful increase of the success rate.
KeywordsBCI adaptation SVM motor imaginary task training
Unable to display preview. Download preview PDF.
- 2.Galán, F., Nuttin, M., Lew, E., Ferrez, P.W., Vanacker, G., Philips, J., del Millan, J.R.: A Brain-Actuated Wheelchair: Asyncronous and Non-invasive Brain-Computer Interface for Continuous Control of Robots. Clinical Neurophysiological 119, 2159–2169Google Scholar
- 6.Wang, C., Phua, K., Ang, K.K., Guan, C., Zhang, H., Lin, R., Chau, K.S.G., Ang, B.T., Kuah, C.W.K.: A feasibility study of non-invasive motor imagery BCI-based robotic rehabilitation for Stroke patients. In: 4th International IEEE/EMBS Conference on Neural Engineering, Ner 2009 (2009)Google Scholar
- 8.Carmena, J.M., Lebedev, M.A., Crist, R.E., O’Doherty, J.E., Santucci, D.M.: Learning to Control a Brain-Machine Interface for Reaching and Grasping by Primates. PLoS Biology 1(2), E42 (2003)Google Scholar
- 10.Millán, J.R., Ferrez, P.W., Buttfield, A.: Non-Invasive Brain-Machine Interfaces - Final Report. IDIAP Research Institute - ESA (2005)Google Scholar
- 12.Chavarriaga, R., del Millán, J.R.: Learning from EEG Error-related Potentials in Non-Invasive Brain-Computer Interfaces. IEEE Transactions on Neural Systems and Rehabilitation Engineering 18, 381–388 (2010)Google Scholar
- 13.American Electroencephalographic Society. American Electroencephalographic Society guidelines for standard electrode position nomenclature. Journal of Clinical Neurophysiology, 8(2), 200–202 (1991)Google Scholar
- 14.Hsu, C.W., Chang, C.C., Lin, C.J.: A Practical Guide to Support Vector Classification (2003), http://www.csie.ntu.edu.tw/cjlin/libsvm/ (updated April 2012) (accessed October 11, 2012]
- 15.Lotte, F., Congedo, M., Lécuyer, A., Lamarche, F., Arnaldi, B.: A Review of Classification Algorithms for EEG-based Brain-computer Interfaces. Journal of Neural Engineering 4, R1–R13 (2007)Google Scholar
- 16.Flórez, F., Azorín, J.M., Iáñez, E., Úbeda, A., Fernández, E.: Development of a Low-cost SVM-based Spontaneous Brain-computer Interface. In: IJCCI (NCTA), pp. 415–421 (2011)Google Scholar