Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG Images
Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signa...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/23/9572 |
| _version_ | 1827591987892584448 |
|---|---|
| author | Shafi Ullah Khan Sana Ullah Jan Insoo Koo |
| author_facet | Shafi Ullah Khan Sana Ullah Jan Insoo Koo |
| author_sort | Shafi Ullah Khan |
| collection | DOAJ |
| description | Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to human error. Recognizing this limitation, the rise in deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time–frequency domain along with pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time–frequency (CWT) images processed using autoencoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: a remarkable 100% accuracy in most of the binary classifications, exceeding 95% accuracy in three-class and four-class challenges, and a commendable rate, exceeding 93.5% for the five-class classification. |
| first_indexed | 2024-03-09T01:42:23Z |
| format | Article |
| id | doaj.art-b91346ceba7943279f725c38498f1a0c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T01:42:23Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b91346ceba7943279f725c38498f1a0c2023-12-08T15:26:27ZengMDPI AGSensors1424-82202023-12-012323957210.3390/s23239572Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG ImagesShafi Ullah Khan0Sana Ullah Jan1Insoo Koo2Department of Electrical Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaSchool of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UKDepartment of Electrical Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaEpilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to human error. Recognizing this limitation, the rise in deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time–frequency domain along with pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time–frequency (CWT) images processed using autoencoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: a remarkable 100% accuracy in most of the binary classifications, exceeding 95% accuracy in three-class and four-class challenges, and a commendable rate, exceeding 93.5% for the five-class classification.https://www.mdpi.com/1424-8220/23/23/9572artificial intelligenceEEGseizure detectioncontinues wavelet transformhybrid features |
| spellingShingle | Shafi Ullah Khan Sana Ullah Jan Insoo Koo Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG Images Sensors artificial intelligence EEG seizure detection continues wavelet transform hybrid features |
| title | Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG Images |
| title_full | Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG Images |
| title_fullStr | Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG Images |
| title_full_unstemmed | Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG Images |
| title_short | Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG Images |
| title_sort | robust epileptic seizure detection using long short term memory and feature fusion of compressed time frequency eeg images |
| topic | artificial intelligence EEG seizure detection continues wavelet transform hybrid features |
| url | https://www.mdpi.com/1424-8220/23/23/9572 |
| work_keys_str_mv | AT shafiullahkhan robustepilepticseizuredetectionusinglongshorttermmemoryandfeaturefusionofcompressedtimefrequencyeegimages AT sanaullahjan robustepilepticseizuredetectionusinglongshorttermmemoryandfeaturefusionofcompressedtimefrequencyeegimages AT insookoo robustepilepticseizuredetectionusinglongshorttermmemoryandfeaturefusionofcompressedtimefrequencyeegimages |