A multiclass epilepsy identification technique using wavelet-based features

Sameh A. Bellegdi; Mohamed Deriche; Samer M.A. Arafat

doi:10.1109/SSD.2018.8570496

A multiclass epilepsy identification technique using wavelet-based features

Sameh A. Bellegdi, Mohamed Deriche, Samer M.A. Arafat

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Epilepsy affects around 1% of the world's population. The electroencephalogram (EEG) is the most common measure of the brain's electrical activity. It is used clinically and by the research community to study brain disorders. This paper presents a comparative study of automatic detection of epilepsy using wavelet-based features with different classifiers. Both binary and multiclass classification setups are studied. The classifiers used are TreeBoost, multilayer perceptron (MLP) neural network, and support vector machine (SVM). Our study is evaluated using EEG dataset from the University of Bonn Hospital in Germany. The obtained results show the significance of different features block for the classifiers. In addition, the results show that TreeBoost outperforms other classifiers. In contrast to existing works carry only binary classification, we consider here 4 classes and show that our results are comparable to the results reported for the single 2-class problem.

Original language	English
Title of host publication	2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1246-1251
Number of pages	6
ISBN (Electronic)	9781538653050
DOIs	https://doi.org/10.1109/SSD.2018.8570496
State	Published - 7 Dec 2018

Publication series

Name	2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Keywords

EEG
TreeBoost
computer-aided diagnostics
electroencephalogram
epilepsy detection
multilayer perceptron neural network
support vector machines
wavelet transform

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Control and Optimization
Instrumentation

Access to Document

10.1109/SSD.2018.8570496

Cite this

Bellegdi, S. A., Deriche, M., & Arafat, S. M. A. (2018). A multiclass epilepsy identification technique using wavelet-based features. In 2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018 (pp. 1246-1251). Article 8570496 (2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSD.2018.8570496

Bellegdi, Sameh A. ; Deriche, Mohamed ; Arafat, Samer M.A. / A multiclass epilepsy identification technique using wavelet-based features. 2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1246-1251 (2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018).

@inproceedings{58e54f6b54a0464c9b3b22c563d2eae0,

title = "A multiclass epilepsy identification technique using wavelet-based features",

abstract = "Epilepsy affects around 1% of the world's population. The electroencephalogram (EEG) is the most common measure of the brain's electrical activity. It is used clinically and by the research community to study brain disorders. This paper presents a comparative study of automatic detection of epilepsy using wavelet-based features with different classifiers. Both binary and multiclass classification setups are studied. The classifiers used are TreeBoost, multilayer perceptron (MLP) neural network, and support vector machine (SVM). Our study is evaluated using EEG dataset from the University of Bonn Hospital in Germany. The obtained results show the significance of different features block for the classifiers. In addition, the results show that TreeBoost outperforms other classifiers. In contrast to existing works carry only binary classification, we consider here 4 classes and show that our results are comparable to the results reported for the single 2-class problem.",

keywords = "EEG, TreeBoost, computer-aided diagnostics, electroencephalogram, epilepsy detection, multilayer perceptron neural network, support vector machines, wavelet transform",

author = "Bellegdi, {Sameh A.} and Mohamed Deriche and Arafat, {Samer M.A.}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.",

year = "2018",

month = dec,

day = "7",

doi = "10.1109/SSD.2018.8570496",

language = "English",

series = "2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1246--1251",

booktitle = "2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018",

address = "United States",

}

Bellegdi, SA, Deriche, M & Arafat, SMA 2018, A multiclass epilepsy identification technique using wavelet-based features. in 2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018., 8570496, 2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1246-1251. https://doi.org/10.1109/SSD.2018.8570496

A multiclass epilepsy identification technique using wavelet-based features. / Bellegdi, Sameh A.; Deriche, Mohamed; Arafat, Samer M.A.
2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1246-1251 8570496 (2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A multiclass epilepsy identification technique using wavelet-based features

AU - Bellegdi, Sameh A.

AU - Deriche, Mohamed

AU - Arafat, Samer M.A.

PY - 2018/12/7

Y1 - 2018/12/7

N2 - Epilepsy affects around 1% of the world's population. The electroencephalogram (EEG) is the most common measure of the brain's electrical activity. It is used clinically and by the research community to study brain disorders. This paper presents a comparative study of automatic detection of epilepsy using wavelet-based features with different classifiers. Both binary and multiclass classification setups are studied. The classifiers used are TreeBoost, multilayer perceptron (MLP) neural network, and support vector machine (SVM). Our study is evaluated using EEG dataset from the University of Bonn Hospital in Germany. The obtained results show the significance of different features block for the classifiers. In addition, the results show that TreeBoost outperforms other classifiers. In contrast to existing works carry only binary classification, we consider here 4 classes and show that our results are comparable to the results reported for the single 2-class problem.

AB - Epilepsy affects around 1% of the world's population. The electroencephalogram (EEG) is the most common measure of the brain's electrical activity. It is used clinically and by the research community to study brain disorders. This paper presents a comparative study of automatic detection of epilepsy using wavelet-based features with different classifiers. Both binary and multiclass classification setups are studied. The classifiers used are TreeBoost, multilayer perceptron (MLP) neural network, and support vector machine (SVM). Our study is evaluated using EEG dataset from the University of Bonn Hospital in Germany. The obtained results show the significance of different features block for the classifiers. In addition, the results show that TreeBoost outperforms other classifiers. In contrast to existing works carry only binary classification, we consider here 4 classes and show that our results are comparable to the results reported for the single 2-class problem.

KW - EEG

KW - TreeBoost

KW - computer-aided diagnostics

KW - electroencephalogram

KW - epilepsy detection

KW - multilayer perceptron neural network

KW - support vector machines

KW - wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=85060568203&partnerID=8YFLogxK

U2 - 10.1109/SSD.2018.8570496

DO - 10.1109/SSD.2018.8570496

M3 - Conference contribution

AN - SCOPUS:85060568203

T3 - 2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018

SP - 1246

EP - 1251

BT - 2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Bellegdi SA, Deriche M, Arafat SMA. A multiclass epilepsy identification technique using wavelet-based features. In 2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1246-1251. 8570496. (2018 15th International Multi-Conference on Systems, Signals and Devices, SSD 2018). doi: 10.1109/SSD.2018.8570496

A multiclass epilepsy identification technique using wavelet-based features

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this