Advertisement
Published in:
2022 | OriginalPaper | Chapter
Epileptic Seizure Detection Based on Electroencephalography Signals and One-Dimensional Convolutional Neural Network
Authors : Quynh Vu Nguyen Phuong, Minh Hiep Do Tran, Huong Nguyen Thi Minh
Published in: 8th International Conference on the Development of Biomedical Engineering in Vietnam
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Epilepsy is a group of neurological disorders characterized by recurrent epileptic seizures. According to the World Health Organization, there are about 50 million people who have epilepsy. Electroencephalography (EEG) is used as a powerful tool for doctors in diagnosis. By visualizing the EEG recordings, experts can initiate antiepileptic drug therapy and reduce the risk of future seizure. However, this current method is time-consuming and inflexible. With the development of deep learning, the problems can be solved. In this study, a 25-channel EEG data recorded at Neurology Department of 115 Hospital was converted into images after filtering, and a one-dimensional convolutional neural network (1-D CNN) model was applied to classify seizure states as seizure or non-seizure accurately. The accuracy of the model is about 90%. With the development of deep learning, it is more convenient to distinguish between different data of seizure and non-seizure without difficulties and consumption of time.