Automated Seizure Detection through EEG Analysis and Deep Learning Technique
Detecting epileptic seizures automatically through intelligent methods has been a main challenge in recent years. This is because neurologists are burdened with analyzing electroencephalogram (EEG) data via visual inspection, and automating the process can reduce their workload. However, one of the...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2024-06-01
|
| Series: | Journal of Artificial Intelligence and System Modelling |
| Subjects: | |
| Online Access: | https://jaism.bilijipub.com/article_199128_c79d75b0d9d0a753e74b0e14e4c3e063.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849389579003494400 |
|---|---|
| author | Srinivas Nowduri M. Madhusudhana Subramanyam |
| author_facet | Srinivas Nowduri M. Madhusudhana Subramanyam |
| author_sort | Srinivas Nowduri |
| collection | DOAJ |
| description | Detecting epileptic seizures automatically through intelligent methods has been a main challenge in recent years. This is because neurologists are burdened with analyzing electroencephalogram (EEG) data via visual inspection, and automating the process can reduce their workload. However, one of the challenges of automatic seizure detection using EEG analysis is extracting optimal features that can distinguish between different states of epilepsy. To address this issue, this research proposes a new approach for automatically identifying epileptic seizures using a deep convolutional network. The network has nine convolutional layers and one fully-connected layer, which learn the features hierarchically and identify epileptic seizures through the EEG analysis. The designed deep network was applied to the epileptic EEG dataset from the University of Bonn. The results showed that 100% accuracy, 100% sensitivity, and 100% specificity were achieved using the proposed method and 10-fold cross-validation for classifying the three investigated EEG conditions (i.e., normal, preictal, and ictal states). The proposed architecture was very efficient in classifying epileptic EEG data. Due to the high accuracy of the algorithm, it can be used for automatic detection of different stages of epilepsy using large EEG data. |
| format | Article |
| id | doaj-art-77df613da5ad4dc28995ed2cb9c60854 |
| institution | Kabale University |
| issn | 3041-850X |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Bilijipub publisher |
| record_format | Article |
| series | Journal of Artificial Intelligence and System Modelling |
| spelling | doaj-art-77df613da5ad4dc28995ed2cb9c608542025-08-20T03:41:56ZengBilijipub publisherJournal of Artificial Intelligence and System Modelling3041-850X2024-06-010202526110.22034/jaism.2024.458242.1042199128Automated Seizure Detection through EEG Analysis and Deep Learning TechniqueSrinivas Nowduri0M. Madhusudhana Subramanyam1College of Pueblo Community, Colorado, 81004, United StatesDepartment of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur, Andhra Pradesh, 522302, IndiaDetecting epileptic seizures automatically through intelligent methods has been a main challenge in recent years. This is because neurologists are burdened with analyzing electroencephalogram (EEG) data via visual inspection, and automating the process can reduce their workload. However, one of the challenges of automatic seizure detection using EEG analysis is extracting optimal features that can distinguish between different states of epilepsy. To address this issue, this research proposes a new approach for automatically identifying epileptic seizures using a deep convolutional network. The network has nine convolutional layers and one fully-connected layer, which learn the features hierarchically and identify epileptic seizures through the EEG analysis. The designed deep network was applied to the epileptic EEG dataset from the University of Bonn. The results showed that 100% accuracy, 100% sensitivity, and 100% specificity were achieved using the proposed method and 10-fold cross-validation for classifying the three investigated EEG conditions (i.e., normal, preictal, and ictal states). The proposed architecture was very efficient in classifying epileptic EEG data. Due to the high accuracy of the algorithm, it can be used for automatic detection of different stages of epilepsy using large EEG data.https://jaism.bilijipub.com/article_199128_c79d75b0d9d0a753e74b0e14e4c3e063.pdfepilepsyseizure detectionelectroencephalogramconvolutional neural networkdeep learningclassification |
| spellingShingle | Srinivas Nowduri M. Madhusudhana Subramanyam Automated Seizure Detection through EEG Analysis and Deep Learning Technique Journal of Artificial Intelligence and System Modelling epilepsy seizure detection electroencephalogram convolutional neural network deep learning classification |
| title | Automated Seizure Detection through EEG Analysis and Deep Learning Technique |
| title_full | Automated Seizure Detection through EEG Analysis and Deep Learning Technique |
| title_fullStr | Automated Seizure Detection through EEG Analysis and Deep Learning Technique |
| title_full_unstemmed | Automated Seizure Detection through EEG Analysis and Deep Learning Technique |
| title_short | Automated Seizure Detection through EEG Analysis and Deep Learning Technique |
| title_sort | automated seizure detection through eeg analysis and deep learning technique |
| topic | epilepsy seizure detection electroencephalogram convolutional neural network deep learning classification |
| url | https://jaism.bilijipub.com/article_199128_c79d75b0d9d0a753e74b0e14e4c3e063.pdf |
| work_keys_str_mv | AT srinivasnowduri automatedseizuredetectionthrougheeganalysisanddeeplearningtechnique AT mmadhusudhanasubramanyam automatedseizuredetectionthrougheeganalysisanddeeplearningtechnique |