Mutual Information Driven Representation Learning for Cross-Subject Seizure Detection

• Published in: IEEE signal processing letters Vol. 32; pp. 2434 - 2438
• Main Authors: Hu, Dinghan, Cui, Xiaonan, Jiang, Tiejia, Hu, Wenbin, Cao, Jiuwen
• Format: Journal Article
• Language: English
• Published: New York IEEE 2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Algorithms; Brain modeling; Cognitive tasks; Convulsions & seizures; Decomposition; Electroencephalography; Epilepsy; Feature extraction; individual variability; Machine learning; Mutual information; Representation learning; Representations; Seizure detection; Spatiotemporal phenomena; Temperature measurement; Training; transfer learning
• ISSN: 1070-9908; 1558-2361
• DOI: 10.1109/LSP.2025.3576642

Developing a generalizable model across subjects is crucial for the practical application of Electroencephalogram (EEG) based seizure detection model. However, inter-subject variability poses a challenge to the accurate identification of epileptic EEG, and applications often require recalibration and training of the base model using individual labeled data. To overcome this limitation, we propose a cross-subject transfer learning algorithm based on mutual information decomposition driven representation learning (MIDRL). The algorithm first introduces the structured state space sequence model to capture the long-term dependencies of epileptic EEG, and the residual module is used to mine the deep information between channels. Additionally, the mutual information estimation is employed to decompose the middle layer features of the network into domain-invariant representations and domain-specific representations, with the dynamically learnable weight updating mechanism to adaptively balance the learning tasks associated with the two representations. Finally, to address the problem of target samples being easily confused near the classification boundary, the minimum class confusion loss is introduced to reduce the class correlation predicted by the classifier. Experimental results demonstrate that the proposed algorithm effectively retains patterns of seizure region and exhibits strong performance for cross-subject seizure detection.