Epileptic Seizures Detection Using iEEG Signals and Deep Learning Models

Epilepsy is a common neurological disorder that affects millions of people worldwide, and many patients do not respond well to traditional anti-epileptic drugs. To improve the lives of these patients, there is a need to develop accurate methods for predicting epileptic seizures. Seizure prediction involves classifying preictal and interictal states, which is a challenging classification problem. Deep learning techniques, such as convolutional neural networks (CNNs), have shown great promise in analyzing and classifying EEG signals related to epilepsy. In this study, we proposed four deep learning models (S-CNN, Modif-CNN, CNN-SVM, and Comb-2CNN) to classify epilepsy states, which we evaluated on an iEEG dataset from the American Epilepsy Society database. Our models achieved high accuracy rates, with the S-CNN and Comb-2CNN models achieving 96.53%, CNN-SVM achieving 96.99%, and the Modif-CNN model achieving 97.96% in our experiments. These findings suggest that deep learning models could be an effective approach for classifying epilepsy states and could potentially improve seizure prediction methods, ultimately enhancing the quality of life for people with epilepsy.