Epileptic Seizure Detection in Separate Frequency Bands Using Feature Analysis and Graph Convolutional Neural Network (GCN) from Electroencephalogram (EEG) Signals
A research paper, now withdrawn, proposed a framework for detecting epileptic seizures using Graph Convolutional Neural Networks (GCNs) applied to electroencephalogram (EEG) signals. The method involved decomposing EEG signals into five frequency bands and extracting features before feeding them into a GCN to model spatial dependencies. Experiments on the CHB-MIT dataset showed high accuracy, particularly in mid-frequency bands, suggesting improved interpretability and diagnostic precision over traditional broadband methods. AI