Analysis of epileptic seizure EEG signals using reconstructed phase space of intrinsic mode functions

Epilepsy is a neurological disorder of the brain. The electroencephalogram (EEG) signals are commonly used to detect the epileptic seizures which are the result of abnormal electrical activity in the brain. In this paper, a new method has been proposed for the analysis of the epileptic seizure EEG signals. The proposed method is based on the empirical mode decomposition (EMD) and the reconstructed phase space (RPS). The EMD method decomposes an EEG signal into a finite number of symmetric, amplitude and frequency modulated (AM-FM) components, termed as intrinsic mode functions (IMFs). The radius corresponding to 95% central tendency measure (CTM) has been computed from the two-dimensional (2D) projection of RPS for first four IMFs of EEG signals. This computed radius has been used as a feature for discrimination of epileptic seizure EEG signals from normal, seizure-free, and non-seizure EEG signals. The experimental results on publicly available EEG dataset are included to show the effectiveness of the proposed method for the analysis of epileptic seizure EEG signals.