Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier

Antonio Quintero-Rincón; Carlos D'Giano; Hadj Batatia

doi:10.1007/978-3-030-11800-6_1

Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier

Antonio Quintero-Rincón^*, Carlos D'Giano, Hadj Batatia

^*Corresponding author for this work

School of Mathematical & Computer Sciences

Research output: Chapter in Book/Report/Conference proceeding › Chapter

6 Citations (Scopus)

Abstract

This paper proposes a new algorithm for epileptic seizure onset detection in EEG signals. The algorithm relies on the measure of the entropy of observed data sequences. Precisely, the data is decomposed into different brain rhythms using wavelet multi-scale transformation. The resulting coefficients are represented using their generalized Gaussian distribution. The proposed algorithm estimates the parameters of the distribution and the associated entropy. Next, an ensemble bagging classifier is used to performs the seizure onset detection using the entropy of each brain rhythm, by discriminating between seizure and non-seizure. Preliminary experiments with 105 epileptic events suggest that the proposed methodology is a powerful tool for detecting seizures in epileptic signals in terms of classification accuracy, sensitivity and specificity.

Original language	English
Title of host publication	Digital Health Approach for Predictive, Preventive, Personalised and Participatory Medicine
Publisher	Springer
Pages	1-10
Number of pages	10
ISBN (Electronic)	9783030118006
ISBN (Print)	9783030117993
DOIs	https://doi.org/10.1007/978-3-030-11800-6_1
Publication status	Published - 2019

Publication series

Name	Advances in Predictive, Preventive and Personalised Medicine
Volume	10
ISSN (Print)	2211-3495
ISSN (Electronic)	2211-3509

Keywords

EEG
Ensemble bagging classifier
Entropy
Epilepsy
Generalized Gaussian distribution
Wavelet filter banks

ASJC Scopus subject areas

Medicine (miscellaneous)

Access to Document

10.1007/978-3-030-11800-6_1

Cite this

Quintero-Rincón, A., D'Giano, C., & Batatia, H. (2019). Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier. In Digital Health Approach for Predictive, Preventive, Personalised and Participatory Medicine (pp. 1-10). (Advances in Predictive, Preventive and Personalised Medicine; Vol. 10). Springer. https://doi.org/10.1007/978-3-030-11800-6_1

Quintero-Rincón, Antonio ; D'Giano, Carlos ; Batatia, Hadj. / Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier. Digital Health Approach for Predictive, Preventive, Personalised and Participatory Medicine. Springer, 2019. pp. 1-10 (Advances in Predictive, Preventive and Personalised Medicine).

@inbook{8901923a29724d5e954165c94aef4919,

title = "Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier",

abstract = "This paper proposes a new algorithm for epileptic seizure onset detection in EEG signals. The algorithm relies on the measure of the entropy of observed data sequences. Precisely, the data is decomposed into different brain rhythms using wavelet multi-scale transformation. The resulting coefficients are represented using their generalized Gaussian distribution. The proposed algorithm estimates the parameters of the distribution and the associated entropy. Next, an ensemble bagging classifier is used to performs the seizure onset detection using the entropy of each brain rhythm, by discriminating between seizure and non-seizure. Preliminary experiments with 105 epileptic events suggest that the proposed methodology is a powerful tool for detecting seizures in epileptic signals in terms of classification accuracy, sensitivity and specificity.",

keywords = "EEG, Ensemble bagging classifier, Entropy, Epilepsy, Generalized Gaussian distribution, Wavelet filter banks",

author = "Antonio Quintero-Rinc{\'o}n and Carlos D'Giano and Hadj Batatia",

note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Switzerland AG.",

year = "2019",

doi = "10.1007/978-3-030-11800-6_1",

language = "English",

isbn = "9783030117993",

series = "Advances in Predictive, Preventive and Personalised Medicine",

publisher = "Springer",

pages = "1--10",

booktitle = "Digital Health Approach for Predictive, Preventive, Personalised and Participatory Medicine",

}

Quintero-Rincón, A, D'Giano, C & Batatia, H 2019, Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier. in Digital Health Approach for Predictive, Preventive, Personalised and Participatory Medicine. Advances in Predictive, Preventive and Personalised Medicine, vol. 10, Springer, pp. 1-10. https://doi.org/10.1007/978-3-030-11800-6_1

Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier. / Quintero-Rincón, Antonio; D'Giano, Carlos; Batatia, Hadj.
Digital Health Approach for Predictive, Preventive, Personalised and Participatory Medicine. Springer, 2019. p. 1-10 (Advances in Predictive, Preventive and Personalised Medicine; Vol. 10).

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier

AU - Quintero-Rincón, Antonio

AU - D'Giano, Carlos

AU - Batatia, Hadj

PY - 2019

Y1 - 2019

N2 - This paper proposes a new algorithm for epileptic seizure onset detection in EEG signals. The algorithm relies on the measure of the entropy of observed data sequences. Precisely, the data is decomposed into different brain rhythms using wavelet multi-scale transformation. The resulting coefficients are represented using their generalized Gaussian distribution. The proposed algorithm estimates the parameters of the distribution and the associated entropy. Next, an ensemble bagging classifier is used to performs the seizure onset detection using the entropy of each brain rhythm, by discriminating between seizure and non-seizure. Preliminary experiments with 105 epileptic events suggest that the proposed methodology is a powerful tool for detecting seizures in epileptic signals in terms of classification accuracy, sensitivity and specificity.

AB - This paper proposes a new algorithm for epileptic seizure onset detection in EEG signals. The algorithm relies on the measure of the entropy of observed data sequences. Precisely, the data is decomposed into different brain rhythms using wavelet multi-scale transformation. The resulting coefficients are represented using their generalized Gaussian distribution. The proposed algorithm estimates the parameters of the distribution and the associated entropy. Next, an ensemble bagging classifier is used to performs the seizure onset detection using the entropy of each brain rhythm, by discriminating between seizure and non-seizure. Preliminary experiments with 105 epileptic events suggest that the proposed methodology is a powerful tool for detecting seizures in epileptic signals in terms of classification accuracy, sensitivity and specificity.

KW - EEG

KW - Ensemble bagging classifier

KW - Entropy

KW - Epilepsy

KW - Generalized Gaussian distribution

KW - Wavelet filter banks

UR - http://www.scopus.com/inward/record.url?scp=85085273189&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-11800-6_1

DO - 10.1007/978-3-030-11800-6_1

M3 - Chapter

AN - SCOPUS:85085273189

SN - 9783030117993

T3 - Advances in Predictive, Preventive and Personalised Medicine

SP - 1

EP - 10

BT - Digital Health Approach for Predictive, Preventive, Personalised and Participatory Medicine

PB - Springer

ER -

Quintero-Rincón A, D'Giano C, Batatia H. Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier. In Digital Health Approach for Predictive, Preventive, Personalised and Participatory Medicine. Springer. 2019. p. 1-10. (Advances in Predictive, Preventive and Personalised Medicine). doi: 10.1007/978-3-030-11800-6_1

Seizure Onset Detection in EEG Signals Based on Entropy from Generalized Gaussian PDF Modeling and Ensemble Bagging Classifier

Abstract

Publication series

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this