{"ID":2829529,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.12273","arxiv_id":"2512.12273","title":"GRC-Net: Gram Residual Co-attention Net for epilepsy prediction","abstract":"Prediction of epilepsy based on electroencephalogram (EEG) signals is a rapidly evolving field. Previous studies have traditionally applied 1D processing to the entire EEG signal. However, we have adopted the Gram Matrix method to transform the signals into a 3D representation, enabling modeling of signal relationships across dimensions while preserving the temporal dependencies of the one-dimensional signals. Additionally, we observed an imbalance between local and global signals within the EEG data. Therefore, we introduced multi-level feature extraction, utilizing coattention for capturing global signal characteristics and an inception structure for processing local signals, achieving multi-granular feature extraction. Our experiments on the BONN dataset demonstrate that for the most challenging five-class classification task, GRC-Net achieved an accuracy of 93.66%, outperforming existing methods.","short_abstract":"Prediction of epilepsy based on electroencephalogram (EEG) signals is a rapidly evolving field. Previous studies have traditionally applied 1D processing to the entire EEG signal. However, we have adopted the Gram Matrix method to transform the signals into a 3D representation, enabling modeling of signal relationships...","url_abs":"https://arxiv.org/abs/2512.12273","url_pdf":"https://arxiv.org/pdf/2512.12273v1","authors":"[\"Bihao You\",\"Jiping Cui\"]","published":"2025-12-13T10:29:28Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}