An explainable multi-view representation fusion learning framework with hybrid MetaFormer for EEG-based epileptic seizure detection

Key Points

• The framework enhances epileptic seizure detection accuracy through feature fusion and multi-view representation.
• Detection accuracy improved by significant margins on standard metrics while processing EEG data during seizures.
• Observational analysis using a hybrid metaformer model incorporates various data representations effectively.
• This approach supports enhanced seizure detection, highlighting the potential for clinical application in EEG monitoring.