Detail publikace

Epilepsy diagnosis using probability density functions of EEG signals

ORHAN, U. HEKIM, M. OZER, M. PROVAZNÍK, I.

Originální název

Epilepsy diagnosis using probability density functions of EEG signals

Český název

Epilepsy diagnosis using probability density functions of EEG signals

Anglický název

Epilepsy diagnosis using probability density functions of EEG signals

Typ

článek ve sborníku

Jazyk

en

Originální abstrakt

In this paper, the equal frequency discretization (EFD) based probability density approach was proposed to be used in the diagnosis of epilepsy from electroencephalogram (EEG) signals. For this aim, EEG signals were decomposed by using the discrete wavelet discretization (DWT) method into subbands, the coefficients in each subband were discretized to several intervals by EFD method, and the probability density of each subband of each EEG segment was computed according to the number of coefficients in discrete intervals. Then, two probability density functions were defined by means of the curve fitting over the probability densities of the sets of both healthy subjects and epilepsy patients. EEG signals were classified by applying the mean square error (MSE) criterion to these functions. The result of the classification was evaluated by using the ROC analysis, which indicated 82.50% success in the diagnosis of epilepsy. As a result, the EFD based probability density approach may be considered as an alternative way to diagnose epilepsy disease on EEG signals.

Český abstrakt

In this paper, the equal frequency discretization (EFD) based probability density approach was proposed to be used in the diagnosis of epilepsy from electroencephalogram (EEG) signals. For this aim, EEG signals were decomposed by using the discrete wavelet discretization (DWT) method into subbands, the coefficients in each subband were discretized to several intervals by EFD method, and the probability density of each subband of each EEG segment was computed according to the number of coefficients in discrete intervals. Then, two probability density functions were defined by means of the curve fitting over the probability densities of the sets of both healthy subjects and epilepsy patients. EEG signals were classified by applying the mean square error (MSE) criterion to these functions. The result of the classification was evaluated by using the ROC analysis, which indicated 82.50% success in the diagnosis of epilepsy. As a result, the EFD based probability density approach may be considered as an alternative way to diagnose epilepsy disease on EEG signals.

Anglický abstrakt

In this paper, the equal frequency discretization (EFD) based probability density approach was proposed to be used in the diagnosis of epilepsy from electroencephalogram (EEG) signals. For this aim, EEG signals were decomposed by using the discrete wavelet discretization (DWT) method into subbands, the coefficients in each subband were discretized to several intervals by EFD method, and the probability density of each subband of each EEG segment was computed according to the number of coefficients in discrete intervals. Then, two probability density functions were defined by means of the curve fitting over the probability densities of the sets of both healthy subjects and epilepsy patients. EEG signals were classified by applying the mean square error (MSE) criterion to these functions. The result of the classification was evaluated by using the ROC analysis, which indicated 82.50% success in the diagnosis of epilepsy. As a result, the EFD based probability density approach may be considered as an alternative way to diagnose epilepsy disease on EEG signals.

Klíčová slova

curve fitting; EEG signals; epilepsy; equal frequency discretization; mean square error; probability density; wavelet transform

Rok RIV

2011

Vydáno

05.09.2011

Nakladatel

IEEE

Místo

Istanbul

ISBN

978-1-61284-919-5

Kniha

Proceedings of INISTA 2011

Strany od

626

Strany do

630

Strany počet

5

BibTex


@inproceedings{BUT73121,
  author="Umut {Orhan} and Mahmut {Hekim} and Mahmut {Ozer} and Ivo {Provazník}",
  title="Epilepsy diagnosis using probability density functions of EEG signals",
  annote="In this paper, the equal frequency discretization (EFD) based probability density approach was proposed to be used in the diagnosis of epilepsy from electroencephalogram (EEG) signals. For this aim, EEG signals were decomposed by using the discrete wavelet discretization (DWT) method into subbands, the coefficients in each subband were discretized to several intervals by EFD method, and the probability density of each subband of each EEG segment was computed according to the number of coefficients in discrete intervals. Then, two probability density functions were defined by means of the curve fitting over the probability densities of the sets of both healthy subjects and epilepsy patients. EEG signals were classified by applying the mean square error (MSE) criterion to these functions. The result of the classification was evaluated by using the ROC analysis, which indicated 82.50% success in the diagnosis of epilepsy. As a result, the EFD based probability density approach may be considered as an alternative way to diagnose epilepsy disease on EEG signals.",
  address="IEEE",
  booktitle="Proceedings of INISTA 2011",
  chapter="73121",
  howpublished="online",
  institution="IEEE",
  year="2011",
  month="september",
  pages="626--630",
  publisher="IEEE",
  type="conference paper"
}