Time-frequency analysis in ictal and interictal seizure epilepsy patients using electroencephalogram

Mohd Syakir Fathillah, Kalaivani Chell, Rosmina Jaafar, Rabani Remli, Wan Asyraf Wan Zaidi

Research output: Contribution to journalArticle

Abstract

Conventional method to distinguish normal and seizure EEG by an epileptologist’s visual screening is tedious and operator dependent. Normal DWT-based seizure detection technique established before suffers from deteriorating of performance due to increasing number of non-relevant features by wavelet decomposition. PCA approach has been utilized in this paper to overcome this problem. Energy, amplitude dispersion and approximate entropy (ApEn) of each sub-band were used as feature of interest and fed to Support Vector Machine (SVM) classifier. Differences between ictal, interictal and normal EEG based on these features were explored. There are significant differences in delta, theta and alpha band in sub-band energy, whereas ApEn changes are found in beta and alpha for ictal EEG. Amplitude dispersion illustrates changes in all sub-bands. PCA approach has been proven to have better accuracy (98%) compared to non-PCA approach (97%) in detecting ictal seizure. The proposed method produced the highest accuracy (98%) compared to other existing methods. The algorithm shows potential to be used clinically.

Original languageEnglish
Pages (from-to)3433-3443
Number of pages11
JournalJournal of Theoretical and Applied Information Technology
Volume96
Issue number11
Publication statusPublished - 15 Jun 2018

Fingerprint

Epilepsy
Time-frequency Analysis
Electroencephalography
Approximate Entropy
Entropy
Wavelet decomposition
Band structure
Support vector machines
Wavelet Decomposition
Screening
Classifiers
Energy
Support Vector Machine
High Accuracy
Classifier
Electroencephalogram
Dependent
Operator

Keywords

  • Approximate entropy (ApEn)
  • Discrete wavelet transform (DWT)
  • Epilepsy
  • Principal component analysis (PCA)
  • Seizure detection
  • Support vector machine (SVM)
  • Time frequency analysis

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

Time-frequency analysis in ictal and interictal seizure epilepsy patients using electroencephalogram. / Fathillah, Mohd Syakir; Chell, Kalaivani; Jaafar, Rosmina; Remli, Rabani; Zaidi, Wan Asyraf Wan.

In: Journal of Theoretical and Applied Information Technology, Vol. 96, No. 11, 15.06.2018, p. 3433-3443.

Research output: Contribution to journalArticle

@article{a01fe157ace140bcb27204bda40c20d5,
title = "Time-frequency analysis in ictal and interictal seizure epilepsy patients using electroencephalogram",
abstract = "Conventional method to distinguish normal and seizure EEG by an epileptologist’s visual screening is tedious and operator dependent. Normal DWT-based seizure detection technique established before suffers from deteriorating of performance due to increasing number of non-relevant features by wavelet decomposition. PCA approach has been utilized in this paper to overcome this problem. Energy, amplitude dispersion and approximate entropy (ApEn) of each sub-band were used as feature of interest and fed to Support Vector Machine (SVM) classifier. Differences between ictal, interictal and normal EEG based on these features were explored. There are significant differences in delta, theta and alpha band in sub-band energy, whereas ApEn changes are found in beta and alpha for ictal EEG. Amplitude dispersion illustrates changes in all sub-bands. PCA approach has been proven to have better accuracy (98{\%}) compared to non-PCA approach (97{\%}) in detecting ictal seizure. The proposed method produced the highest accuracy (98{\%}) compared to other existing methods. The algorithm shows potential to be used clinically.",
keywords = "Approximate entropy (ApEn), Discrete wavelet transform (DWT), Epilepsy, Principal component analysis (PCA), Seizure detection, Support vector machine (SVM), Time frequency analysis",
author = "Fathillah, {Mohd Syakir} and Kalaivani Chell and Rosmina Jaafar and Rabani Remli and Zaidi, {Wan Asyraf Wan}",
year = "2018",
month = "6",
day = "15",
language = "English",
volume = "96",
pages = "3433--3443",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "11",

}

TY - JOUR

T1 - Time-frequency analysis in ictal and interictal seizure epilepsy patients using electroencephalogram

AU - Fathillah, Mohd Syakir

AU - Chell, Kalaivani

AU - Jaafar, Rosmina

AU - Remli, Rabani

AU - Zaidi, Wan Asyraf Wan

PY - 2018/6/15

Y1 - 2018/6/15

N2 - Conventional method to distinguish normal and seizure EEG by an epileptologist’s visual screening is tedious and operator dependent. Normal DWT-based seizure detection technique established before suffers from deteriorating of performance due to increasing number of non-relevant features by wavelet decomposition. PCA approach has been utilized in this paper to overcome this problem. Energy, amplitude dispersion and approximate entropy (ApEn) of each sub-band were used as feature of interest and fed to Support Vector Machine (SVM) classifier. Differences between ictal, interictal and normal EEG based on these features were explored. There are significant differences in delta, theta and alpha band in sub-band energy, whereas ApEn changes are found in beta and alpha for ictal EEG. Amplitude dispersion illustrates changes in all sub-bands. PCA approach has been proven to have better accuracy (98%) compared to non-PCA approach (97%) in detecting ictal seizure. The proposed method produced the highest accuracy (98%) compared to other existing methods. The algorithm shows potential to be used clinically.

AB - Conventional method to distinguish normal and seizure EEG by an epileptologist’s visual screening is tedious and operator dependent. Normal DWT-based seizure detection technique established before suffers from deteriorating of performance due to increasing number of non-relevant features by wavelet decomposition. PCA approach has been utilized in this paper to overcome this problem. Energy, amplitude dispersion and approximate entropy (ApEn) of each sub-band were used as feature of interest and fed to Support Vector Machine (SVM) classifier. Differences between ictal, interictal and normal EEG based on these features were explored. There are significant differences in delta, theta and alpha band in sub-band energy, whereas ApEn changes are found in beta and alpha for ictal EEG. Amplitude dispersion illustrates changes in all sub-bands. PCA approach has been proven to have better accuracy (98%) compared to non-PCA approach (97%) in detecting ictal seizure. The proposed method produced the highest accuracy (98%) compared to other existing methods. The algorithm shows potential to be used clinically.

KW - Approximate entropy (ApEn)

KW - Discrete wavelet transform (DWT)

KW - Epilepsy

KW - Principal component analysis (PCA)

KW - Seizure detection

KW - Support vector machine (SVM)

KW - Time frequency analysis

UR - http://www.scopus.com/inward/record.url?scp=85048599952&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048599952&partnerID=8YFLogxK

M3 - Article

VL - 96

SP - 3433

EP - 3443

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 11

ER -