A Convolutional Long Short-Term Memory-Based Neural Network for Epilepsy Detection From EEG
Md. Nurul Ahad Tawhid, Siuly Siuly, Tianning Li
Abstract
Epilepsy is a severe neurological disorder characterized by recurrent seizures, which increases the risk of death three times more than normal. Currently Electroencephalography (EEG) has emerged as a highly promising technique for the diagnosis of epilepsy. The majority of current EEG-based epilepsy detection research have employed a variety of deep learning-based models, but most of the approaches suffer from poor generalizability, optimal design and performance rates. To address these issues, this study aims to develop an efficient framework based on deep spatio-temporal neural network called convolutional long short-term memory (ConvLSTM) for epilepsy detection from EEG signals. In the proposed model, firstly standard 19 channel EEG data are selected and resampled at 256Hz, and then those signals are segmented into three-second time frames. Afterward, the segmented data are fed as input to the ConvLSTM model for identifying epileptic patients from normal subjects. To generalize the proposed model, we have tested it on two different datasets with varying population sizes. We have used the five-fold cross validation and leave-one-out cross validation schemes to eliminate the experiment’s biases. To further validate the proposed framework, we have carried out various ablation studies. The experimental results demonstrate that the proposed model outperforms the current state-of-the-art results for the studied datasets, making it suitable for use as an automated system for the diagnosis of epilepsy.