A nonstationary model of newborn EEG

Luke Rankine, Nathan Stevenson, Mostefa Mesbah, Boualem Boashash

Research output: Contribution to journalArticle

67 Citations (Scopus)

Abstract

The detection of seizure in the newborn is a critical aspect of neurological research. Current automatic detection techniques are difficult to assess due to the problems associated with acquiring and labelling newborn electroencephalogram (EEG) data. A realistic model for newborn EEG would allow confident development, assessment and comparison of these detection techniques. This paper presents a model for newborn EEG that accounts for its self-similar and nonstationary nature. The model consists of background and seizure submodels. The newborn EEG background model is based on the short-time power spectrum with a time-varying power law. The relationship between the fractal dimension and the power law of a power spectrum is utilized for accurate estimation of the short-time power law exponent. The newborn EEG seizure model is based on a well-known time-frequency signal model. This model addresses all significant time-frequency characteristics of newborn EEG seizure which include; multiple components or harmonics, piecewise linear instantaneous frequency laws and harmonic amplitude modulation. Estimates of the parameters of both models are shown to be random and are modelled using the data from a total of 500 background epochs and 204 seizure epochs. The newborn EEG background and seizure models are validated against real newborn EEG data using the correlation coefficient. The results show that the output of the proposed models have a higher correlation with real newborn EEG than currently accepted models (a 10% and 38% improvement for background and seizure models, respectively).

Original languageEnglish
Article number6
Pages (from-to)19-28
Number of pages10
JournalIEEE Transactions on Biomedical Engineering
Volume54
Issue number1
DOIs
Publication statusPublished - Jan 2007

Fingerprint

Electroencephalography
Power spectrum
Amplitude modulation
Fractal dimension
Labeling

Keywords

  • EEG
  • Fractal dimension
  • Modelling
  • Neonate
  • Nonstationary
  • Simulation
  • Stochastic processes
  • Time-frequency signal processing

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

A nonstationary model of newborn EEG. / Rankine, Luke; Stevenson, Nathan; Mesbah, Mostefa; Boashash, Boualem.

In: IEEE Transactions on Biomedical Engineering, Vol. 54, No. 1, 6, 01.2007, p. 19-28.

Research output: Contribution to journalArticle

Rankine, Luke ; Stevenson, Nathan ; Mesbah, Mostefa ; Boashash, Boualem. / A nonstationary model of newborn EEG. In: IEEE Transactions on Biomedical Engineering. 2007 ; Vol. 54, No. 1. pp. 19-28.
@article{ffe7197ab4a24390a59178eda8e020cf,
title = "A nonstationary model of newborn EEG",
abstract = "The detection of seizure in the newborn is a critical aspect of neurological research. Current automatic detection techniques are difficult to assess due to the problems associated with acquiring and labelling newborn electroencephalogram (EEG) data. A realistic model for newborn EEG would allow confident development, assessment and comparison of these detection techniques. This paper presents a model for newborn EEG that accounts for its self-similar and nonstationary nature. The model consists of background and seizure submodels. The newborn EEG background model is based on the short-time power spectrum with a time-varying power law. The relationship between the fractal dimension and the power law of a power spectrum is utilized for accurate estimation of the short-time power law exponent. The newborn EEG seizure model is based on a well-known time-frequency signal model. This model addresses all significant time-frequency characteristics of newborn EEG seizure which include; multiple components or harmonics, piecewise linear instantaneous frequency laws and harmonic amplitude modulation. Estimates of the parameters of both models are shown to be random and are modelled using the data from a total of 500 background epochs and 204 seizure epochs. The newborn EEG background and seizure models are validated against real newborn EEG data using the correlation coefficient. The results show that the output of the proposed models have a higher correlation with real newborn EEG than currently accepted models (a 10{\%} and 38{\%} improvement for background and seizure models, respectively).",
keywords = "EEG, Fractal dimension, Modelling, Neonate, Nonstationary, Simulation, Stochastic processes, Time-frequency signal processing",
author = "Luke Rankine and Nathan Stevenson and Mostefa Mesbah and Boualem Boashash",
year = "2007",
month = "1",
doi = "10.1109/TBME.2006.886667",
language = "English",
volume = "54",
pages = "19--28",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - A nonstationary model of newborn EEG

AU - Rankine, Luke

AU - Stevenson, Nathan

AU - Mesbah, Mostefa

AU - Boashash, Boualem

PY - 2007/1

Y1 - 2007/1

N2 - The detection of seizure in the newborn is a critical aspect of neurological research. Current automatic detection techniques are difficult to assess due to the problems associated with acquiring and labelling newborn electroencephalogram (EEG) data. A realistic model for newborn EEG would allow confident development, assessment and comparison of these detection techniques. This paper presents a model for newborn EEG that accounts for its self-similar and nonstationary nature. The model consists of background and seizure submodels. The newborn EEG background model is based on the short-time power spectrum with a time-varying power law. The relationship between the fractal dimension and the power law of a power spectrum is utilized for accurate estimation of the short-time power law exponent. The newborn EEG seizure model is based on a well-known time-frequency signal model. This model addresses all significant time-frequency characteristics of newborn EEG seizure which include; multiple components or harmonics, piecewise linear instantaneous frequency laws and harmonic amplitude modulation. Estimates of the parameters of both models are shown to be random and are modelled using the data from a total of 500 background epochs and 204 seizure epochs. The newborn EEG background and seizure models are validated against real newborn EEG data using the correlation coefficient. The results show that the output of the proposed models have a higher correlation with real newborn EEG than currently accepted models (a 10% and 38% improvement for background and seizure models, respectively).

AB - The detection of seizure in the newborn is a critical aspect of neurological research. Current automatic detection techniques are difficult to assess due to the problems associated with acquiring and labelling newborn electroencephalogram (EEG) data. A realistic model for newborn EEG would allow confident development, assessment and comparison of these detection techniques. This paper presents a model for newborn EEG that accounts for its self-similar and nonstationary nature. The model consists of background and seizure submodels. The newborn EEG background model is based on the short-time power spectrum with a time-varying power law. The relationship between the fractal dimension and the power law of a power spectrum is utilized for accurate estimation of the short-time power law exponent. The newborn EEG seizure model is based on a well-known time-frequency signal model. This model addresses all significant time-frequency characteristics of newborn EEG seizure which include; multiple components or harmonics, piecewise linear instantaneous frequency laws and harmonic amplitude modulation. Estimates of the parameters of both models are shown to be random and are modelled using the data from a total of 500 background epochs and 204 seizure epochs. The newborn EEG background and seizure models are validated against real newborn EEG data using the correlation coefficient. The results show that the output of the proposed models have a higher correlation with real newborn EEG than currently accepted models (a 10% and 38% improvement for background and seizure models, respectively).

KW - EEG

KW - Fractal dimension

KW - Modelling

KW - Neonate

KW - Nonstationary

KW - Simulation

KW - Stochastic processes

KW - Time-frequency signal processing

UR - http://www.scopus.com/inward/record.url?scp=33846361354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846361354&partnerID=8YFLogxK

U2 - 10.1109/TBME.2006.886667

DO - 10.1109/TBME.2006.886667

M3 - Article

C2 - 17260852

AN - SCOPUS:33846361354

VL - 54

SP - 19

EP - 28

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 1

M1 - 6

ER -