Abstract
BACKGROUND: Epilepsy is a chronic neurological disorder that affects individuals across all age groups. Early detection and intervention are crucial for minimizing both physical and psychological distress. However, the unpredictable nature of seizures presents considerable challenges for timely detection and accurate diagnosis. METHOD: To address the challenge of low recognition accuracy in small-sample, single-channel epileptic electroencephalogram (EEG) signals, this study proposes an automated seizure detection method using a micro-capsule network. First, we propose a dimensionality-increasing transformation technique for single-channel EEG signals to meet the network's input requirements. Second, a streamlined micro-capsule network is designed by optimizing and simplifying the framework's architecture. Finally, EEG features are encoded as feature vectors to better represent spatial hierarchical relationships between seizure patterns, enhancing the framework's adaptability and improving detection accuracy. RESULT: Compared to existing EEG-based detection methods, our approach achieves higher accuracy on small-sample datasets while maintaining a reduction in computational complexity. CONCLUSIONS: By leveraging its micro-capsule network architecture, the framework demonstrates superior classification accuracy when analyzing single-channel epileptiform EEG signals, significantly outperforming both convolutional neural network-based implementations and established machine learning methodologies.