Epileptic waveform recognition using wavelet decomposition and artificial neural networks

László Szilágyi, Z. Benyó

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

The recognition of epileptic waveforms from the electroencephalogram is an important physiological signal processing task, as epilepsy is still one of the most frequent brain disorders. The main goal of this paper is to present a new method to diagnose the epileptic waveforms directly from EEG, by performing a quick signal processing, which makes it possible to apply in on-line monitoring systems. The EEG signal processing is performed in two steps. In the first step, by using the multi-resolution wavelet decomposition, we obtain different spectral components (α, β, δ, θ) of the measured signal. These components serve as input signals for the artificial neural network (ANN), which accomplishes the recognition of epileptic waves. The recognition rate for all test signals turned out to be over 95%.

Original languageEnglish
Pages (from-to)301-303
Number of pages3
JournalIFAC Proceedings Volumes (IFAC-PapersOnline)
Volume36
Issue number15
DOIs
Publication statusPublished - Jan 1 2003
Event5th IFAC Symposium on Modelling and Control in Biomedical Systems 2003 - Melbourne, Australia
Duration: Aug 21 2003Aug 23 2003

Fingerprint

Wavelet decomposition
Electroencephalography
Signal processing
Neural networks
Brain
Monitoring

Keywords

  • Biomedical systems
  • Detection algorithms
  • Filtering techniques
  • Neural networks
  • Signal processing

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Epileptic waveform recognition using wavelet decomposition and artificial neural networks. / Szilágyi, László; Benyó, Z.

In: IFAC Proceedings Volumes (IFAC-PapersOnline), Vol. 36, No. 15, 01.01.2003, p. 301-303.

Research output: Contribution to journalConference article

@article{5fa610aea36d4fa7b42be83e29d955ba,
title = "Epileptic waveform recognition using wavelet decomposition and artificial neural networks",
abstract = "The recognition of epileptic waveforms from the electroencephalogram is an important physiological signal processing task, as epilepsy is still one of the most frequent brain disorders. The main goal of this paper is to present a new method to diagnose the epileptic waveforms directly from EEG, by performing a quick signal processing, which makes it possible to apply in on-line monitoring systems. The EEG signal processing is performed in two steps. In the first step, by using the multi-resolution wavelet decomposition, we obtain different spectral components (α, β, δ, θ) of the measured signal. These components serve as input signals for the artificial neural network (ANN), which accomplishes the recognition of epileptic waves. The recognition rate for all test signals turned out to be over 95{\%}.",
keywords = "Biomedical systems, Detection algorithms, Filtering techniques, Neural networks, Signal processing",
author = "L{\'a}szl{\'o} Szil{\'a}gyi and Z. Beny{\'o}",
year = "2003",
month = "1",
day = "1",
doi = "10.1016/S1474-6670(17)33519-X",
language = "English",
volume = "36",
pages = "301--303",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "IFAC Secretariat",
number = "15",

}

TY - JOUR

T1 - Epileptic waveform recognition using wavelet decomposition and artificial neural networks

AU - Szilágyi, László

AU - Benyó, Z.

PY - 2003/1/1

Y1 - 2003/1/1

N2 - The recognition of epileptic waveforms from the electroencephalogram is an important physiological signal processing task, as epilepsy is still one of the most frequent brain disorders. The main goal of this paper is to present a new method to diagnose the epileptic waveforms directly from EEG, by performing a quick signal processing, which makes it possible to apply in on-line monitoring systems. The EEG signal processing is performed in two steps. In the first step, by using the multi-resolution wavelet decomposition, we obtain different spectral components (α, β, δ, θ) of the measured signal. These components serve as input signals for the artificial neural network (ANN), which accomplishes the recognition of epileptic waves. The recognition rate for all test signals turned out to be over 95%.

AB - The recognition of epileptic waveforms from the electroencephalogram is an important physiological signal processing task, as epilepsy is still one of the most frequent brain disorders. The main goal of this paper is to present a new method to diagnose the epileptic waveforms directly from EEG, by performing a quick signal processing, which makes it possible to apply in on-line monitoring systems. The EEG signal processing is performed in two steps. In the first step, by using the multi-resolution wavelet decomposition, we obtain different spectral components (α, β, δ, θ) of the measured signal. These components serve as input signals for the artificial neural network (ANN), which accomplishes the recognition of epileptic waves. The recognition rate for all test signals turned out to be over 95%.

KW - Biomedical systems

KW - Detection algorithms

KW - Filtering techniques

KW - Neural networks

KW - Signal processing

UR - http://www.scopus.com/inward/record.url?scp=84899188915&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899188915&partnerID=8YFLogxK

U2 - 10.1016/S1474-6670(17)33519-X

DO - 10.1016/S1474-6670(17)33519-X

M3 - Conference article

AN - SCOPUS:84899188915

VL - 36

SP - 301

EP - 303

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 15

ER -