Neurological Classifier Committee Based on Artificial Neural Networks and Support Vector Machine for Single-Trial EEG Signal Decoding
This study aimed to finding effective approaches for electroencephalographic (EEG) multiclass classification of imaginary movements. The combined classifier of EEG signals based on artificial neural network (ANN) and support vector machine (SVM) algorithms was applied. Effectiveness of the classifier was shown in 4-class imaginary finger movement classification. Nine right-handed subjects participated in the study. The mean decoding accuracy using combined heterogeneous classifier committee was −60 ± 10 %, max: 77 ± 5 %, while application of homogeneous classifier based on committee of ANNs −52 ± 9 % and 65 ± 5 % correspondingly. This work supports the feasibility of the approach, which is presumed suitable for imaginary movements decoding of four fingers of one hand. These results could be used for development of effective non-invasive BCI with enlarged amount of degrees of freedom.
KeywordsElectroencephalography Classifier committee Artificial neural network Support vector machine Imaginary finger movements
The study was supported by the RFBR foundation grant № 13-01-12059 ofi-m.
- 6.Sonkin, K.M., Stankevich, L.A., Khomenko, Y., Nagornova, Z., Shemyakina, N.V.: Classification of electroencephalographic patterns of imagined and real movements by one hand fingers using the support vectors method. Pac. Med. J. 2, 30–35 (2014)Google Scholar
- 8.Lazurenko, D.M., Shepelev, I.E., Kiroy, V.N., Aslanyan, E.V., Bakhtin, O.M., Minyaeva, N.R.: Ideomotor EEG patterns in the profile of brain-computer interface. In: Ivanova, G.E. (ed.) Selected Topics of Neurorehabilitation: Proceedings of VII International Congress Neurorehabilitation-2015, pp. 246–249 (2015). (Russian)Google Scholar
- 13.Stankevich, L.A., Sonkin, K.M., Nagornova, Z.V., Khomenko, J.G., Shemyakina, N.V: Classification of electroencephalographic patterns of imaginary one-hand finger movements for brain-computer interface development. SPIIRAS Proc. 3(40), 163–182 (2015)Google Scholar
- 15.Xiao, R., Ding, L.: Evaluation of EEG features in decoding individual finger movements from one hand. Comput. Math. Methods Med., 243 (2013)Google Scholar
- 16.Sotnikov, P.I.: Optimal EEG signal frequency ranges selection in brain-computer interface. Sci. Educ., 217–234 (2015)Google Scholar
- 17.Basterrech, S., Bobrov, P., Frolov, A., Húsek, D.: Nature-inspired algorithms for selecting EEG sources for motor imagery based BCI. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2015. LNCS, vol. 9120, pp. 79–90. Springer, Heidelberg (2015)CrossRefGoogle Scholar