Automatic Epileptic Seizure Detection via Attention-Based CNN-BiRNN

Epileptic seizure detection with multi-channel electroencephalography (EEG) signals is a commonly used method, but it is tedious and error-prone to manually detect seizures through EEG signals. In this work, we propose an end-to-end deep neural network called attention-based CNN-BiRNN for automatic seizure detection. Attention-based CNN-BiRNN mainly consists of three parts: the multi-scale convolution model, the attention model, and the multi-stream bidirectional recurrent model. Original signals are firstly sent to the multi-scale convolution model to extract multi-scale features. Then the attention model exploits the differences among channels for seizure detection. Afterwards, the robust temporal features are obtained by the multi-stream bidirectional recurrent model, and are further fed into a fully connected layer for classification. Moreover, a channel dropout method is proposed, for the model training stage, to obtain inconspicuous characteristics from all the channels of a certain EEG signal. The results on the dataset of CHB-MIT demonstrate that our approach outperforms state-of-the-art approaches in terms of both sensitivity and specificity. Furthermore, with the channel dropout method, our approach is shown to have a powerful ability of handling EEG signals with missing channels and different channels.