SeizureGuard: an adaptive fusion converter model for seizure prediction

The majority of studies on seizure prediction have concentrated on temporal and frequency features, which may result in inconsistencies when evaluating the accuracy of pre-dictions. To address this issue, we propose an innovative seizure prediction model that incorporates channel features as one of the key component. The model effectively integrates time, frequency and channel features by combining three convolutional neural networks (CNNs) and three transformer encoders. We validated our method on the CHB-MIT dataset, obtaining 99.00% accuracy, 99.10% sensitivity and 0.011/h false prediction rate (FPR). The experimental results demonstrate the efficient performance of our method in EEG signal classification and prediction, or comparable to state-of-the-art models.