This repository contains implementations of previously used deep learning models to detect epilepsy, as well as the implementation of a novel transformer architecture named EEGFormer, which was designed specifically for Epilepsy detection task.
Epilepsy detection plays a critical role in improving the quality of life for individuals with epilepsy. EEG signals are valuable sources of information for diagnosing and predicting epileptic seizures. EEGFormer brings together various deep learning models and showcases the application of a cutting-edge Transformer-based architecture in this domain.
-
Transformer-based Model (2023 Paper): This repository includes the implementation of a novel Transformer-based architecture proposed in the research paper EEGformer: A transformer–based brain activity classification method using EEG signal.
-
Deep Learning Models: Beyond the Transformer, I've added code for 3 different deep learning models tailored for EEG-based epilepsy detection. These models are designed to provide a comprehensive toolbox for researchers and practitioners in the field.