Simple Detection of Epilepsy From EEG Signal Using Local Binary Pattern Transition Histogram

This paper proposed a simple but highly accurate feature extraction method for epilepsy detection from electroencephalogram (EEG) signals. Based on the combination of Discrete Wavelet Transform (DWT) and the newly proposed features Local Binary Pattern Transition Histogram (LBPTH) and Local Binary P...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Muhammad Yazid, Fahmi Fahmi, Erwin Sutanto, Wervyan Shalannanda, Ruhush Shoalihin, Gwo-Jiun Horng, Aripriharta
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
eeg
Acceso en línea:https://doaj.org/article/3bd9e2edacd446a88124e798f98013ac
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:3bd9e2edacd446a88124e798f98013ac
record_format dspace
spelling oai:doaj.org-article:3bd9e2edacd446a88124e798f98013ac2021-11-18T00:09:23ZSimple Detection of Epilepsy From EEG Signal Using Local Binary Pattern Transition Histogram2169-353610.1109/ACCESS.2021.3126065https://doaj.org/article/3bd9e2edacd446a88124e798f98013ac2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9605664/https://doaj.org/toc/2169-3536This paper proposed a simple but highly accurate feature extraction method for epilepsy detection from electroencephalogram (EEG) signals. Based on the combination of Discrete Wavelet Transform (DWT) and the newly proposed features Local Binary Pattern Transition Histogram (LBPTH) and Local Binary Pattern Mean Absolute Deviation (LBPMAD), our proposed feature extraction method can efficiently extract features from EEG signals for machine learning classification of epilepsy, achieving high classification accuracy with a feature size of only 18 for each signal. Tested on the publicly available University of Bonn Epilepsy EEG Dataset using a signal length of 4097 data points (23.61 seconds), the proposed method achieved larger than 99.6&#x0025; accuracy results for Support Vector Machine (SVM) and k-Nearest Neighbor (KNN) classification of ictal (set E) against any non-ictal (set A, B, C, or D) or combinations of non-ictal (set <inline-formula> <tex-math notation="LaTeX">$\text{A}+\text{B}$ </tex-math></inline-formula>, set <inline-formula> <tex-math notation="LaTeX">$\text{C}+\text{D}$ </tex-math></inline-formula>, or set <inline-formula> <tex-math notation="LaTeX">$\text{A}+\text{B}+\text{C}+\text{D}$ </tex-math></inline-formula>) EEG signals, which is among the best of currently published works. Our method can maintain high classification accuracy even with short input signals, achieving more than 99.1&#x0025; SVM classification accuracy when input signal length is reduced to 512 data points (2.95 seconds). The high accuracy, small feature size, ability to work with short input signals and low computing requirements made the proposed method suitable for mobile, low power, and low-cost wearable medical devices.Muhammad YazidFahmi FahmiErwin SutantoWervyan ShalannandaRuhush ShoalihinGwo-Jiun Horng AriprihartaIEEEarticleBiomedicaldisability and family supporthealtheegepilepsybonnElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 150252-150267 (2021)
institution DOAJ
collection DOAJ
language EN
topic Biomedical
disability and family support
health
eeg
epilepsy
bonn
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Biomedical
disability and family support
health
eeg
epilepsy
bonn
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Muhammad Yazid
Fahmi Fahmi
Erwin Sutanto
Wervyan Shalannanda
Ruhush Shoalihin
Gwo-Jiun Horng
Aripriharta
Simple Detection of Epilepsy From EEG Signal Using Local Binary Pattern Transition Histogram
description This paper proposed a simple but highly accurate feature extraction method for epilepsy detection from electroencephalogram (EEG) signals. Based on the combination of Discrete Wavelet Transform (DWT) and the newly proposed features Local Binary Pattern Transition Histogram (LBPTH) and Local Binary Pattern Mean Absolute Deviation (LBPMAD), our proposed feature extraction method can efficiently extract features from EEG signals for machine learning classification of epilepsy, achieving high classification accuracy with a feature size of only 18 for each signal. Tested on the publicly available University of Bonn Epilepsy EEG Dataset using a signal length of 4097 data points (23.61 seconds), the proposed method achieved larger than 99.6&#x0025; accuracy results for Support Vector Machine (SVM) and k-Nearest Neighbor (KNN) classification of ictal (set E) against any non-ictal (set A, B, C, or D) or combinations of non-ictal (set <inline-formula> <tex-math notation="LaTeX">$\text{A}+\text{B}$ </tex-math></inline-formula>, set <inline-formula> <tex-math notation="LaTeX">$\text{C}+\text{D}$ </tex-math></inline-formula>, or set <inline-formula> <tex-math notation="LaTeX">$\text{A}+\text{B}+\text{C}+\text{D}$ </tex-math></inline-formula>) EEG signals, which is among the best of currently published works. Our method can maintain high classification accuracy even with short input signals, achieving more than 99.1&#x0025; SVM classification accuracy when input signal length is reduced to 512 data points (2.95 seconds). The high accuracy, small feature size, ability to work with short input signals and low computing requirements made the proposed method suitable for mobile, low power, and low-cost wearable medical devices.
format article
author Muhammad Yazid
Fahmi Fahmi
Erwin Sutanto
Wervyan Shalannanda
Ruhush Shoalihin
Gwo-Jiun Horng
Aripriharta
author_facet Muhammad Yazid
Fahmi Fahmi
Erwin Sutanto
Wervyan Shalannanda
Ruhush Shoalihin
Gwo-Jiun Horng
Aripriharta
author_sort Muhammad Yazid
title Simple Detection of Epilepsy From EEG Signal Using Local Binary Pattern Transition Histogram
title_short Simple Detection of Epilepsy From EEG Signal Using Local Binary Pattern Transition Histogram
title_full Simple Detection of Epilepsy From EEG Signal Using Local Binary Pattern Transition Histogram
title_fullStr Simple Detection of Epilepsy From EEG Signal Using Local Binary Pattern Transition Histogram
title_full_unstemmed Simple Detection of Epilepsy From EEG Signal Using Local Binary Pattern Transition Histogram
title_sort simple detection of epilepsy from eeg signal using local binary pattern transition histogram
publisher IEEE
publishDate 2021
url https://doaj.org/article/3bd9e2edacd446a88124e798f98013ac
work_keys_str_mv AT muhammadyazid simpledetectionofepilepsyfromeegsignalusinglocalbinarypatterntransitionhistogram
AT fahmifahmi simpledetectionofepilepsyfromeegsignalusinglocalbinarypatterntransitionhistogram
AT erwinsutanto simpledetectionofepilepsyfromeegsignalusinglocalbinarypatterntransitionhistogram
AT wervyanshalannanda simpledetectionofepilepsyfromeegsignalusinglocalbinarypatterntransitionhistogram
AT ruhushshoalihin simpledetectionofepilepsyfromeegsignalusinglocalbinarypatterntransitionhistogram
AT gwojiunhorng simpledetectionofepilepsyfromeegsignalusinglocalbinarypatterntransitionhistogram
AT aripriharta simpledetectionofepilepsyfromeegsignalusinglocalbinarypatterntransitionhistogram
_version_ 1718425218681143296