SVM classification of epileptic EEG recordings through multiscale permutation entropy

Electroencephalogram (EEG) is a non-invasive diagnostic tool in clinical neurophysiology, especially with respect to epilepsy. The epileptic status is characterized by reduced complexity. New markers, based on nonlinear dynamics, like Permutation Entropy (PE) have been developed to measure EEG complexity. In this paper, Multiscale Permutation Entropy (MPE) complexity measure is proposed as a potentially useful framework for detecting epileptic events in EEG data and to distinguish healthy controls from patients. The achieved results show that: 1) MPE is able to discriminate between the two categories; 2) the use of multiple scales may substantially improve the specificity of the diagnosis. This is shown through an SVM-based classification network with three different kernels. The use of the SVM approach is also useful to infer clues about the extracted features.