Epileptic Seizure Detection using Deep Learning Approach
An epileptic seizure is a sign of abnormal activity in the human brain. Electroencephalogram (EEG) is a standard tool that has been used vastly for detection of seizure activities. Many methods have been developed to help the neurophysiologists to detect the seizure activities with high accuracy. Mo...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Human Development
2019-08-01
|
| Series: | UHD Journal of Science and Technology |
| Subjects: | |
| Online Access: | http://journals.uhd.edu.iq/index.php/uhdjst/article/view/392/230 |
| _version_ | 1828340041699557376 |
|---|---|
| author | Sirwan Tofiq Jaafar Mokhtar Mohammadi |
| author_facet | Sirwan Tofiq Jaafar Mokhtar Mohammadi |
| author_sort | Sirwan Tofiq Jaafar |
| collection | DOAJ |
| description | An epileptic seizure is a sign of abnormal activity in the human brain. Electroencephalogram (EEG) is a standard tool that has been used vastly for detection of seizure activities. Many methods have been developed to help the neurophysiologists to detect the seizure activities with high accuracy. Most of them rely on the features extracted in the time, frequency, or time-frequency domains. The performance of the proposed methods is related to the performance of the features extracted from EEG recordings. Deep neural networks enable learning directly on the data without the domain knowledge needed to construct a feature set. This approach has been hugely successful in almost all machine learning applications. We propose a new framework that also learns directly from the data, without extracting a feature set. We proposed an original deep-learning-based method to classify EEG recordings. The EEG signal is segmented into 4 s segments and used to train the long- and short-term memory network. The trained model is used to discriminate the EEG seizure from the background. The Freiburg EEG dataset is used to assess the performance of the classifier. The 5-fold cross-validation is selected for evaluating the performance of the proposed method. About 97.75% of the accuracy is achieved. |
| first_indexed | 2024-04-13T22:51:23Z |
| format | Article |
| id | doaj.art-a5729f44190e4c739ad3a4cf151c29ec |
| institution | Directory Open Access Journal |
| issn | 2521-4209 2521-4217 |
| language | English |
| last_indexed | 2024-04-13T22:51:23Z |
| publishDate | 2019-08-01 |
| publisher | University of Human Development |
| record_format | Article |
| series | UHD Journal of Science and Technology |
| spelling | doaj.art-a5729f44190e4c739ad3a4cf151c29ec2022-12-22T02:26:10ZengUniversity of Human DevelopmentUHD Journal of Science and Technology2521-42092521-42172019-08-01324150https://doi.org/10.21928/uhdjst.v3n2y2019.pp41-50Epileptic Seizure Detection using Deep Learning ApproachSirwan Tofiq Jaafar0Mokhtar Mohammadi1Computer Department, College of Science, University of Sulaimani, Sulaymaniyah, IraqDepartment of Information Technology, University of Human Development, Sulaymaniyah, IraqAn epileptic seizure is a sign of abnormal activity in the human brain. Electroencephalogram (EEG) is a standard tool that has been used vastly for detection of seizure activities. Many methods have been developed to help the neurophysiologists to detect the seizure activities with high accuracy. Most of them rely on the features extracted in the time, frequency, or time-frequency domains. The performance of the proposed methods is related to the performance of the features extracted from EEG recordings. Deep neural networks enable learning directly on the data without the domain knowledge needed to construct a feature set. This approach has been hugely successful in almost all machine learning applications. We propose a new framework that also learns directly from the data, without extracting a feature set. We proposed an original deep-learning-based method to classify EEG recordings. The EEG signal is segmented into 4 s segments and used to train the long- and short-term memory network. The trained model is used to discriminate the EEG seizure from the background. The Freiburg EEG dataset is used to assess the performance of the classifier. The 5-fold cross-validation is selected for evaluating the performance of the proposed method. About 97.75% of the accuracy is achieved.http://journals.uhd.edu.iq/index.php/uhdjst/article/view/392/230ElectroencephalogramEpilepsyEpileptic SeizureLong- and short-term MemorySeizure Detection |
| spellingShingle | Sirwan Tofiq Jaafar Mokhtar Mohammadi Epileptic Seizure Detection using Deep Learning Approach UHD Journal of Science and Technology Electroencephalogram Epilepsy Epileptic Seizure Long- and short-term Memory Seizure Detection |
| title | Epileptic Seizure Detection using Deep Learning Approach |
| title_full | Epileptic Seizure Detection using Deep Learning Approach |
| title_fullStr | Epileptic Seizure Detection using Deep Learning Approach |
| title_full_unstemmed | Epileptic Seizure Detection using Deep Learning Approach |
| title_short | Epileptic Seizure Detection using Deep Learning Approach |
| title_sort | epileptic seizure detection using deep learning approach |
| topic | Electroencephalogram Epilepsy Epileptic Seizure Long- and short-term Memory Seizure Detection |
| url | http://journals.uhd.edu.iq/index.php/uhdjst/article/view/392/230 |
| work_keys_str_mv | AT sirwantofiqjaafar epilepticseizuredetectionusingdeeplearningapproach AT mokhtarmohammadi epilepticseizuredetectionusingdeeplearningapproach |