Parameter pattern discovery in nonlinear dynamic model for EEGs analysis

Sun Hee Kim, Christos Faloutsos, Hyung Jeong Yang, Seong Whan Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We propose a nonlinear dynamic model for an invasive electroencephalogram analysis that learns the optimal parameters of the neural population model via the Levenberg-Marquardt algorithm. We introduce the crucial windows where the estimated parameters present patterns before seizure onset. The optimal parameters minimizes the error between the observed signal and the generated signal by the model. The proposed approach effectively discriminates between healthy signals and epileptic seizure signals. We evaluate the proposed method using an electroencephalogram dataset with normal and epileptic seizure sequences. The empirical results show that the patterns of parameters as a seizure approach and the method is efficient in analyzing nonlinear epilepsy electroencephalogram data. The accuracy of estimating the optimal parameters is improved by using the nonlinear dynamic model.

Original languageEnglish
Pages (from-to)381-402
Number of pages22
JournalJournal of Integrative Neuroscience
Volume15
Issue number3
Publication statusPublished - 2016 Sep 1

Fingerprint

Nonlinear Dynamics
Electroencephalography
Epilepsy
Seizures
Population

Keywords

  • electroencephalogram
  • Epileptic seizure
  • neurons population
  • nonlinear dynamic model
  • parameter changes

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

Parameter pattern discovery in nonlinear dynamic model for EEGs analysis. / Kim, Sun Hee; Faloutsos, Christos; Yang, Hyung Jeong; Lee, Seong Whan.

In: Journal of Integrative Neuroscience, Vol. 15, No. 3, 01.09.2016, p. 381-402.

Research output: Contribution to journalArticle

Kim, Sun Hee ; Faloutsos, Christos ; Yang, Hyung Jeong ; Lee, Seong Whan. / Parameter pattern discovery in nonlinear dynamic model for EEGs analysis. In: Journal of Integrative Neuroscience. 2016 ; Vol. 15, No. 3. pp. 381-402.
@article{ff5d0ad91a804cf2b93f45e2ac141bf3,
title = "Parameter pattern discovery in nonlinear dynamic model for EEGs analysis",
abstract = "We propose a nonlinear dynamic model for an invasive electroencephalogram analysis that learns the optimal parameters of the neural population model via the Levenberg-Marquardt algorithm. We introduce the crucial windows where the estimated parameters present patterns before seizure onset. The optimal parameters minimizes the error between the observed signal and the generated signal by the model. The proposed approach effectively discriminates between healthy signals and epileptic seizure signals. We evaluate the proposed method using an electroencephalogram dataset with normal and epileptic seizure sequences. The empirical results show that the patterns of parameters as a seizure approach and the method is efficient in analyzing nonlinear epilepsy electroencephalogram data. The accuracy of estimating the optimal parameters is improved by using the nonlinear dynamic model.",
keywords = "electroencephalogram, Epileptic seizure, neurons population, nonlinear dynamic model, parameter changes",
author = "Kim, {Sun Hee} and Christos Faloutsos and Yang, {Hyung Jeong} and Lee, {Seong Whan}",
year = "2016",
month = "9",
day = "1",
language = "English",
volume = "15",
pages = "381--402",
journal = "Journal of Integrative Neuroscience",
issn = "0219-6352",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "3",

}

TY - JOUR

T1 - Parameter pattern discovery in nonlinear dynamic model for EEGs analysis

AU - Kim, Sun Hee

AU - Faloutsos, Christos

AU - Yang, Hyung Jeong

AU - Lee, Seong Whan

PY - 2016/9/1

Y1 - 2016/9/1

N2 - We propose a nonlinear dynamic model for an invasive electroencephalogram analysis that learns the optimal parameters of the neural population model via the Levenberg-Marquardt algorithm. We introduce the crucial windows where the estimated parameters present patterns before seizure onset. The optimal parameters minimizes the error between the observed signal and the generated signal by the model. The proposed approach effectively discriminates between healthy signals and epileptic seizure signals. We evaluate the proposed method using an electroencephalogram dataset with normal and epileptic seizure sequences. The empirical results show that the patterns of parameters as a seizure approach and the method is efficient in analyzing nonlinear epilepsy electroencephalogram data. The accuracy of estimating the optimal parameters is improved by using the nonlinear dynamic model.

AB - We propose a nonlinear dynamic model for an invasive electroencephalogram analysis that learns the optimal parameters of the neural population model via the Levenberg-Marquardt algorithm. We introduce the crucial windows where the estimated parameters present patterns before seizure onset. The optimal parameters minimizes the error between the observed signal and the generated signal by the model. The proposed approach effectively discriminates between healthy signals and epileptic seizure signals. We evaluate the proposed method using an electroencephalogram dataset with normal and epileptic seizure sequences. The empirical results show that the patterns of parameters as a seizure approach and the method is efficient in analyzing nonlinear epilepsy electroencephalogram data. The accuracy of estimating the optimal parameters is improved by using the nonlinear dynamic model.

KW - electroencephalogram

KW - Epileptic seizure

KW - neurons population

KW - nonlinear dynamic model

KW - parameter changes

UR - http://www.scopus.com/inward/record.url?scp=85028278034&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028278034&partnerID=8YFLogxK

M3 - Article

C2 - 27774837

AN - SCOPUS:85028278034

VL - 15

SP - 381

EP - 402

JO - Journal of Integrative Neuroscience

JF - Journal of Integrative Neuroscience

SN - 0219-6352

IS - 3

ER -