Classification of single-channel EEG signals for epileptic seizures detection based on hybrid features.

<bold>Background: </bold>Epilepsy is a common chronic neurological disorder of the brain. Clinically, epileptic seizures are usually detected via the continuous monitoring of electroencephalogram (EEG) signals by experienced neurophysiologists.<bold>Objective: </bold>In order to detect epileptic seizures automatically with a satisfactory precision, a new method is proposed which defines hybrid features that could characterize the epileptiform waves and classify single-channel EEG signals.<bold>Methods: </bold>The hybrid features consist of both the ones usually used in EEG signal analysis and the Kraskov entropy based on Hilbert-Huang Transform which is proposed for the first time. With the hybrid features, EEG signals are classified and the epileptic seizures are detected.<bold>Results: </bold>Three datasets are used for test on three binary-classification problems defined by clinical requirements for epileptic seizures detection. Experimental results show that the accuracy, sensitivity and specificity of the proposed methods outperform two state-of-the-art methods, especially on the databases containing signals from different sources.<bold>Conclusions: </bold>The proposed method provides a new avenue to assist neurophysiologists in diagnosing epileptic seizures automatically and accurately. [ABSTRACT FROM AUTHOR]