A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification
Epilepsy is one of the most severe non-communicable brain disorders associated with sudden attacks. Electroencephalography (EEG), a non-invasive technique, records brain activities, and these recordings are routinely used for the clinical evaluation of epilepsy. EEG signal analysis for seizure ident...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Utara Malaysia Press
2023
|
| Subjects: | |
| Online Access: | https://repo.uum.edu.my/id/eprint/29906/1/JICT%2022%2004%202023%20587-617.pdf https://doi.org/10.32890/jict2023.22.4.3 |
| _version_ | 1825806079556059136 |
|---|---|
| author | Prakash, Vinod Kumar, Dharmender |
| author_facet | Prakash, Vinod Kumar, Dharmender |
| author_sort | Prakash, Vinod |
| collection | UUM |
| description | Epilepsy is one of the most severe non-communicable brain disorders associated with sudden attacks. Electroencephalography (EEG), a non-invasive technique, records brain activities, and these recordings are routinely used for the clinical evaluation of epilepsy. EEG signal analysis for seizure identification relies on expert manual examination, which is labour-intensive, time-consuming, and prone to human error. To overcome these limitations, researchers have proposed machine learning and deep learning approaches. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) have shown significant results in automating seizure prediction, but due to complex gated mechanisms and the storage of excessive redundant information, these approaches face slow convergence and a low learning rate. The proposed modified GRU approach includes an improved update gate unit that adjusts the update gate based on the output of the reset gate. By decreasing the amount of superfluous data in the reset gate, convergence is speeded, which improves both learning efficiency and the accuracy of epilepsy seizure prediction. The performance of the proposed approach is verified on a publicly available epileptic EEG dataset collected from the University of California, Irvine machine learning repository (UCI) in terms of performance metrics such as accuracy, precision, recall, and F1 score when it comes to diagnosing epileptic seizures. The proposed modified GRU has obtained 98.84% accuracy, 96.9% precision, 97.1 recall, and 97% F1 score. The performance results are significant because they could enhance the diagnosis and treatment of neurological disorders, leading to better patient outcomes. |
| first_indexed | 2024-07-04T06:43:05Z |
| format | Article |
| id | uum-29906 |
| institution | Universiti Utara Malaysia |
| language | English |
| last_indexed | 2024-07-04T06:43:05Z |
| publishDate | 2023 |
| publisher | Universiti Utara Malaysia Press |
| record_format | eprints |
| spelling | uum-299062023-11-05T10:09:39Z https://repo.uum.edu.my/id/eprint/29906/ A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification Prakash, Vinod Kumar, Dharmender T Technology (General) Epilepsy is one of the most severe non-communicable brain disorders associated with sudden attacks. Electroencephalography (EEG), a non-invasive technique, records brain activities, and these recordings are routinely used for the clinical evaluation of epilepsy. EEG signal analysis for seizure identification relies on expert manual examination, which is labour-intensive, time-consuming, and prone to human error. To overcome these limitations, researchers have proposed machine learning and deep learning approaches. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) have shown significant results in automating seizure prediction, but due to complex gated mechanisms and the storage of excessive redundant information, these approaches face slow convergence and a low learning rate. The proposed modified GRU approach includes an improved update gate unit that adjusts the update gate based on the output of the reset gate. By decreasing the amount of superfluous data in the reset gate, convergence is speeded, which improves both learning efficiency and the accuracy of epilepsy seizure prediction. The performance of the proposed approach is verified on a publicly available epileptic EEG dataset collected from the University of California, Irvine machine learning repository (UCI) in terms of performance metrics such as accuracy, precision, recall, and F1 score when it comes to diagnosing epileptic seizures. The proposed modified GRU has obtained 98.84% accuracy, 96.9% precision, 97.1 recall, and 97% F1 score. The performance results are significant because they could enhance the diagnosis and treatment of neurological disorders, leading to better patient outcomes. Universiti Utara Malaysia Press 2023 Article PeerReviewed application/pdf en cc4_by https://repo.uum.edu.my/id/eprint/29906/1/JICT%2022%2004%202023%20587-617.pdf Prakash, Vinod and Kumar, Dharmender (2023) A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification. Journal of Information and Communication Technology, 22 (4). pp. 587-617. ISSN 2180-3862 https://e-journal.uum.edu.my/index.php/jict/article/view/15364 https://doi.org/10.32890/jict2023.22.4.3 https://doi.org/10.32890/jict2023.22.4.3 |
| spellingShingle | T Technology (General) Prakash, Vinod Kumar, Dharmender A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification |
| title | A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification |
| title_full | A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification |
| title_fullStr | A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification |
| title_full_unstemmed | A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification |
| title_short | A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification |
| title_sort | modified gated recurrent unit approach for epileptic electroencephalography classification |
| topic | T Technology (General) |
| url | https://repo.uum.edu.my/id/eprint/29906/1/JICT%2022%2004%202023%20587-617.pdf https://doi.org/10.32890/jict2023.22.4.3 |
| work_keys_str_mv | AT prakashvinod amodifiedgatedrecurrentunitapproachforepilepticelectroencephalographyclassification AT kumardharmender amodifiedgatedrecurrentunitapproachforepilepticelectroencephalographyclassification AT prakashvinod modifiedgatedrecurrentunitapproachforepilepticelectroencephalographyclassification AT kumardharmender modifiedgatedrecurrentunitapproachforepilepticelectroencephalographyclassification |