Automatic Seizure Detection based on a Convolutional Neural Network-Recurrent Neural Network Model
Date
2022-05
Authors
Shao, Lu
Major Professor
Bao, Forrest
Advisor
Committee Member
Zhang, Wensheng
Aduri, Pavankumar
Journal Title
Journal ISSN
Volume Title
Publisher
Altmetrics
Abstract
Epilepsy is one of the most common neurological disorders that impacts 1-2% of the world's population. Detecting seizures through electroencephalogram (EEG) data is a common way for epilepsy diagnosis. Existing automatic systems for EEG-based seizure detection have limitations. Some use manual feature extraction, which is not suitable for generalization in the future, whereas those without manual feature extraction do not have high performances. In this paper, a convolutional neural network combined with a recurrent neural network, known as a CNN-RNN model, is developed to detect seizures on the EEG dataset CHB-MIT. The proposed model is designed to achieve high performances without manual feature extraction. The promising results with a high accuracy of 99.24%, specificity of 99.29%, and recall of 99.16% validate the effectiveness of the proposed model.
Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
creative component
Comments
Rights Statement
Copyright
2022-05