Early Detection of Stress and Anxiety Based Seizures in Position Data Augmented EEG Signal Using Hybrid Deep Learning Algorithms
Epilepsy is a neurological problem due to aberrant brain activity. Epilepsy diagnose through Electroencephalography (EEG) signal. Human interpretation and analysis of EEG signal for earlier detection of epilepsy is subjected to error. Detection of Epileptic seizures due to stress and anxiety is the...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10433184/ |
_version_ | 1797243361954889728 |
---|---|
author | Kamini Kamakshi Arthi Rengaraj |
author_facet | Kamini Kamakshi Arthi Rengaraj |
author_sort | Kamini Kamakshi |
collection | DOAJ |
description | Epilepsy is a neurological problem due to aberrant brain activity. Epilepsy diagnose through Electroencephalography (EEG) signal. Human interpretation and analysis of EEG signal for earlier detection of epilepsy is subjected to error. Detection of Epileptic seizures due to stress and anxiety is the major problem. Epileptic seizure signal size, and shape changes from person to person based on their stress and anxiety level. Stress and anxiety based epileptic seizure signals vary in amplitude, width, combination of width and amplitude. In this paper, seizures of different size and shape are synthesized using data augmentation for different stress and anxiety level. Different augmentation such as (i) position data augmentation (PDA) (ii) random data augmentation (RDA) applied to BONN EEG dataset for synthetizations of stress and anxiety based epileptic seizure signals. Augment EEG epileptic seizure signals are analyzed using proposed methods such as i) FCM-PSO-LSTM and ii) PSO-LSTM for earlier detection of stress and anxiety-based seizures. The proposed algorithms perform better in earlier detection of stress and anxiety-based seizure signals. The predicted accuracy of proposed methods such as (i) FCM-PSO-LSTM and (ii) PSO-LSTM is about (i)98.5% and (ii) 97% for PDA and RDA is about (i) 98% and (ii) 98.5% for BONN. The accuracy of proposed methods such as(i) FCM-PSO-LSTM and (ii) PSO-LSTM is about (i)98% and(ii) 97.5% for PDA and RDA is about (i) 97.5% and (ii) 98% respectively for CHB-MIT. |
first_indexed | 2024-04-24T18:53:54Z |
format | Article |
id | doaj.art-4f0d9a812eb24f6f9f65450406088552 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-24T18:53:54Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-4f0d9a812eb24f6f9f654504060885522024-03-26T17:46:26ZengIEEEIEEE Access2169-35362024-01-0112353513536510.1109/ACCESS.2024.336519210433184Early Detection of Stress and Anxiety Based Seizures in Position Data Augmented EEG Signal Using Hybrid Deep Learning AlgorithmsKamini Kamakshi0https://orcid.org/0000-0003-3017-7416Arthi Rengaraj1https://orcid.org/0000-0001-9638-1634Department of ECE, SRM Institute of Science and Technology, Ramapuram Campus, Ramapuram, Chennai, Tamil Nadu, IndiaDepartment of ECE, SRM Institute of Science and Technology, Ramapuram Campus, Ramapuram, Chennai, Tamil Nadu, IndiaEpilepsy is a neurological problem due to aberrant brain activity. Epilepsy diagnose through Electroencephalography (EEG) signal. Human interpretation and analysis of EEG signal for earlier detection of epilepsy is subjected to error. Detection of Epileptic seizures due to stress and anxiety is the major problem. Epileptic seizure signal size, and shape changes from person to person based on their stress and anxiety level. Stress and anxiety based epileptic seizure signals vary in amplitude, width, combination of width and amplitude. In this paper, seizures of different size and shape are synthesized using data augmentation for different stress and anxiety level. Different augmentation such as (i) position data augmentation (PDA) (ii) random data augmentation (RDA) applied to BONN EEG dataset for synthetizations of stress and anxiety based epileptic seizure signals. Augment EEG epileptic seizure signals are analyzed using proposed methods such as i) FCM-PSO-LSTM and ii) PSO-LSTM for earlier detection of stress and anxiety-based seizures. The proposed algorithms perform better in earlier detection of stress and anxiety-based seizure signals. The predicted accuracy of proposed methods such as (i) FCM-PSO-LSTM and (ii) PSO-LSTM is about (i)98.5% and (ii) 97% for PDA and RDA is about (i) 98% and (ii) 98.5% for BONN. The accuracy of proposed methods such as(i) FCM-PSO-LSTM and (ii) PSO-LSTM is about (i)98% and(ii) 97.5% for PDA and RDA is about (i) 97.5% and (ii) 98% respectively for CHB-MIT.https://ieeexplore.ieee.org/document/10433184/Data augmentationEEGepileptic seizure signalfeature extractionLSTM classifier |
spellingShingle | Kamini Kamakshi Arthi Rengaraj Early Detection of Stress and Anxiety Based Seizures in Position Data Augmented EEG Signal Using Hybrid Deep Learning Algorithms IEEE Access Data augmentation EEG epileptic seizure signal feature extraction LSTM classifier |
title | Early Detection of Stress and Anxiety Based Seizures in Position Data Augmented EEG Signal Using Hybrid Deep Learning Algorithms |
title_full | Early Detection of Stress and Anxiety Based Seizures in Position Data Augmented EEG Signal Using Hybrid Deep Learning Algorithms |
title_fullStr | Early Detection of Stress and Anxiety Based Seizures in Position Data Augmented EEG Signal Using Hybrid Deep Learning Algorithms |
title_full_unstemmed | Early Detection of Stress and Anxiety Based Seizures in Position Data Augmented EEG Signal Using Hybrid Deep Learning Algorithms |
title_short | Early Detection of Stress and Anxiety Based Seizures in Position Data Augmented EEG Signal Using Hybrid Deep Learning Algorithms |
title_sort | early detection of stress and anxiety based seizures in position data augmented eeg signal using hybrid deep learning algorithms |
topic | Data augmentation EEG epileptic seizure signal feature extraction LSTM classifier |
url | https://ieeexplore.ieee.org/document/10433184/ |
work_keys_str_mv | AT kaminikamakshi earlydetectionofstressandanxietybasedseizuresinpositiondataaugmentedeegsignalusinghybriddeeplearningalgorithms AT arthirengaraj earlydetectionofstressandanxietybasedseizuresinpositiondataaugmentedeegsignalusinghybriddeeplearningalgorithms |