Epileptic EEG classification via deep learning-based strange attractor

Abstract

Electroencephalography is commonly exploited in recording brains’ electrical activities for revealing the symptoms of various neurological diseases, e.g., epileptic seizures. We hypothesize that its capability primarily comes from the information it captures from the brain, which is supposed to be a chaotic dynamical system. Therefore, seizure detection in clinical practice could benefit from strange attractor reconstruction from time series in classifying non-ictal and ictal epileptic seizures. We propose a deep learning architecture and the loss function in a latent space to implement the reconstruction. By leveraging the proposed deep model, the hidden coordinates can be derived from a low-dimensional time series or univariate time series (e.g., Electroencephalography). Furthermore, added variables can extract more features from the reconstructed dynamical system. The proposed pipeline is evaluated by using a publicly available epileptic seizure database. Experimental results demonstrated the promising outcome of the proposed approach.