Automatic epileptic seizure detection based on empirical mode decomposition and deep neural network

Electroencephalogram (EEG) used to record the electrical activity of the brain is a standout amongst the most helpful tools which are utilized in the diagnosis of neurological disorders. In this paper, we propose two classification methods for automatic epileptic seizure detection based on EEG recordings. The proposed methods use Empirical Mode Decomposition (EMD) for feature extraction and Deep Neural Networks (DNNs) for classification. Multilayer perceptron is used in the first classification method to classify between normal and seizure cases by reducing features' dimension which speeds up the task. The classification accuracy achieved using this method is 100%. Deep Convolutional Neural Network (DCNN) is utilized in the second classification method to accomplish a high accuracy in multiclass classification task. The classification accuracy obtained using DCNN for classifying between the normal, interictal and ictal cases is 98.6%. The evaluation of the proposed methods is conducted using the 10-fold cross-validation methodology to ensure the robustness of the system.