MuGEP: Multiplex Graph-Based Brain Network Modeling for Epileptic Seizure Prediction Using Intracranial EEG

This research proposes MuGEP, a graph neural network framework that models diverse brain network relationships from intracranial EEG signals to improve seizure prediction accuracy. The method represents frequency band interactions across channels using multiplex graphs inspired by cross-frequency coupling in neuroscience, enabling more comprehensive analysis of epileptogenic brain networks.