Using Higher Order Nonlinear Operators for SVM Classification of EEG Data

  • I. Martisius Kaunas University of Technology
  • R. Damasevicius Kaunas University of Technology
  • V. Jusas Kaunas University of Technology
  • D. Birvinskas Kaunas University of Technology


Brain-Computer Interface (BCI) systems require application of complex analysis, signal processing, denoising, feature extraction, dimensionality reduction and classification methods on acquired raw electroencephalogram (EEG) data to allow for useful operation. In this paper, we consider application of nonlinear operators such as Taeger-Kaiser Energy Operator (TKEO) and its multiple generalizations on the EEG signals and evaluate the efficiency of the operators using a Support Vector Machine (SVM) classifier with linear kernel. We propose a new generalization of TKEO, called Homogeneous Multivariate Polynomial Operator (HMPO), and compare the efficiency of the 3rd order HMPO with other nonlinear operators. Experimental results show that the 3rd order HMPO operator allows for better identification of significant features representing slow cortical potentials in the EEG data. Ill. 1, bibl. 18, tabl. 1 (in English; abstracts in English and Lithuanian).


How to Cite
Martisius, I., Damasevicius, R., Jusas, V., & Birvinskas, D. (2012). Using Higher Order Nonlinear Operators for SVM Classification of EEG Data. Elektronika Ir Elektrotechnika, 119(3), 99-102.