Classification of focal and non-focal electroencephalogram signals using recurrence plot methods

Abstract

The classification of focal and non-focal EEG signals is very useful for diagnosis of epilepsy. In this work, we propose a new approach for classifying focal and non-focal EEG signals using cross recurrence plot (CRP) and joint recurrence plot (JRP) methods. In our approach, EEG signals are decomposed into intrinsic mode functions (IMFs) using empirical mode decomposition (EMD) then CRP and JRP methods are applied on each IMF to form a feature vector. Finally, a binary classifier, least squares support vector machine (LS-SVM), is employed to discriminate focal and non-focal EEG signals. The proposed technique achieves 86% classification accuracy using CRP with linear and radial basis function (RBF) as kernels in LS-SVM classifier.