Publication detail

Heart beat classification

POTOČŇÁK, T. RONZHINA, M.

Original Title

Heart beat classification

Czech Title

Heart beat classification

English Title

Heart beat classification

Type

conference paper

Language

sk

Original Abstract

The aim of this work was to develop the method for classification of ECG beats into two classes, namely ischemic and non-ischemic beats. Heart beats (QRS-T cycles) from animal orthogonal ECGs were preprocessed and used as input signal. Spectral features vectors (values of cross spectral coherency) were derived from the beats and the beats were classified using feedforward multilayer neural network designed in Matlab. Classification performance reached the value approx. 99%. Presented results can be suitable in future studies aimed to automatic classification of ECG.

Czech abstract

The aim of this work was to develop the method for classification of ECG beats into two classes, namely ischemic and non-ischemic beats. Heart beats (QRS-T cycles) from animal orthogonal ECGs were preprocessed and used as input signal. Spectral features vectors (values of cross spectral coherency) were derived from the beats and the beats were classified using feedforward multilayer neural network designed in Matlab. Classification performance reached the value approx. 99%. Presented results can be suitable in future studies aimed to automatic classification of ECG.

English abstract

The aim of this work was to develop the method for classification of ECG beats into two classes, namely ischemic and non-ischemic beats. Heart beats (QRS-T cycles) from animal orthogonal ECGs were preprocessed and used as input signal. Spectral features vectors (values of cross spectral coherency) were derived from the beats and the beats were classified using feedforward multilayer neural network designed in Matlab. Classification performance reached the value approx. 99%. Presented results can be suitable in future studies aimed to automatic classification of ECG.

Keywords

Heart beat classification, cardiac ischemia, cross spectral coherency analysis, artificial neural network

RIV year

2013

Released

25.04.2013

ISBN

978-80-214-4694-6

Book

Proceedings of the 19th Conference STUDENT EEICT 2013 Volume 2

Edition number

1

Pages from

182

Pages to

184

Pages count

3

BibTex


@inproceedings{BUT99449,
  author="Tomáš {Potočňák} and Marina {Ronzhina}",
  title="Heart beat classification",
  annote="The aim of this work was to develop the method for classification of ECG beats into two classes, namely ischemic and non-ischemic beats. Heart beats (QRS-T cycles) from animal orthogonal ECGs were preprocessed and used as input signal. Spectral features vectors (values of cross spectral coherency) were derived from the beats and the beats were classified using feedforward multilayer neural network designed in Matlab. Classification performance reached the value approx. 99%. Presented results can be suitable in future studies aimed to automatic classification of ECG.",
  booktitle="Proceedings of the 19th Conference STUDENT EEICT 2013 Volume 2",
  chapter="99449",
  howpublished="print",
  year="2013",
  month="april",
  pages="182--184",
  type="conference paper"
}