Epilepsy seizure diagnosis using Electroencephalogram (EEG) signals

Abstract

Electroencephalogram (EEG) signals are valuable source of information for detecting Epileptic seizures. However, monitoring EEG for long periods of time is very exhausting and time consuming. Thus, detecting epilepsy in EEG signals automatically is highly appreciated.

In this study, three classes namely normal, interictal (out of seizure time) and ictal (during seizure) are considered. Digital wavelet transform (DWT) and Digital Filter (DF) are examined for EEG sub-bands extraction and SoftMax and Support vector Machine (SVM) classifiers are examined for classification. Moreover, a comparative study is provided for the efficient features in literature resulting in a suggested combination of only three discriminative features namely R’enyi entropy, line length and energy. These features are calculated from each of the EEG sub-bands which are extracted by (DWT). Finally, SVM classifier optimized using BAT algorithm (BAT-SVM) is introduced by this study for discriminating between the three classes.