Features extraction and classification for Ictal and Interictal EEG signals using EMD and DCT

Abstract

Electroencephalogram (EEG) is a record of electrical signal to represent the human brain activity. Many researchers are working on human brain as they are fascinated by the idea of secret, thought and feeling from the external and internal stimuli. Feature extraction, analysis, and classification of EEG signals are still challenging issues for researchers due to the variations of the brain signals. Different features are used to identify epilepsy, coma, encephalopathies, and brain death, etc. However, we have observed that extracted features from same kinds of signal transformations are not effective to differentiate the epilepsy periods including Ictal (active seizure period) and Interictal (interval between seizures) of EEG signals. In this paper we present a new approach for feature extraction using high frequency components from DCT transformation. We also combine the new feature with the bandwidth feature extracted from the empirical mode decomposition (EMD). These features are then used as an input to least squares support vector machine (LS-SVM) to classify Ictal and Interictal period of epileptic EEG signals from different brain locations. Experimental results show that the proposed method outperforms the existing state-of-the-art method for better classification of Ictal and Interictal period of epilepsy for benchmark dataset.