AUTHOR=Xu Gaowei , Ren Tianhe , Chen Yu , Che Wenliang TITLE=A One-Dimensional CNN-LSTM Model for Epileptic Seizure Recognition Using EEG Signal Analysis JOURNAL=Frontiers in Neuroscience VOLUME=Volume 14 - 2020 YEAR=2020 URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2020.578126 DOI=10.3389/fnins.2020.578126 ISSN=1662-453X ABSTRACT=Frequent epileptic seizure causes damage to the human’s brain, resulting in memory impairment, mental decline and so on. Therefore, it is important to detect epileptic seizure and provide medical treatment in a timely manner. Currently, medical experts recognize epileptic seizure activity through the visual inspection of electroencephalographic (EEG) signal recordings of patients based on their experience, which takes much time and effort of medical experts. In view of this, this paper proposes a one-dimensional convolutional neural network-long short-term memory (1D CNN-LSTM) model for automatic recognition of epileptic seizure through EEG signal analysis. Firstly, the raw EEG signal data is preprocessed and normalized. Then, a 1D convolutional neural network (CNN) is designed to effectively extract the features of the normalized EEG sequence data. In addition, the extracted features are then processed by the LSTM layers in order to further extract the temporal features. After that, the output features are fed into several fully connected layers for final epileptic seizure recognition. The performance of the proposed 1D CNN-LSTM model is verified on the public UCI epileptic seizure recognition data set. Experiments results show that the proposed method achieves high recognition accuracies of 99.39% and 82.00% on the binary and five-class epileptic seizure recognition tasks, respectively. Comparing results with traditional machine learning methods including k-nearest neighbor, support vector machine and decision tree, other deep learning methods including standard deep neural network and CNN further verify the superiority of the proposed method.