Seizure detection from EEG signals using Multivariate Empirical Mode Decomposition

We present a data driven approach to classify ictal (epileptic seizure) and non-ictal EEG signals using the multivariate empirical mode decomposition (MEMD) algorithm. MEMD is a multivariate extension of empirical mode decomposition (EMD), which is an established method to perform the decomposition and time-frequency (T−F) analysis of non-stationary data sets. We select suitable feature sets based on the multiscale T−F representation of the EEG data via MEMD for the classification purposes. The classification is achieved using the artificial neural networks. The efficacy of the proposed method is verified on extensive publicly available EEG datasets.