Publication detail

Atrial Fibrillation Classification Using Deep Convolutional Network

NOVOTNÁ, P.

Original Title

Atrial Fibrillation Classification Using Deep Convolutional Network

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

We propose the usage of three deep convolutional neural networks architectures for classification of a single lead electrocardiogram (ECG) recordings and evaluate them on the atrial fibrillation (AFIB) classification, for which data set was provided by the Department of Biomedical Engineering, BUT. The compared networks are based on ResNet, VGG net and AlexNet. Single lead signals are transformed into the form of spectrogram. AFIB data was augmented for the purpose of similar size of both respected classes and for successful classification. The most successful architecture, based on AlexNet, was found to perform obtaining an accuracy of 92 \% and F1 score of 56 \% on the hidden testing set.

Keywords

ECG; atrial fibrillation; signal processing classification; deep learning, neural networks; convolution; resnet; alexnet; vgg

Authors

NOVOTNÁ, P.

Released

23. 4. 2020

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií

Location

Brno

ISBN

978-80-214-5867-3

Book

Proceedings I of the 26th Conference STUDENT EEICT 2020

Edition

1

Edition number

1

Pages from

345

Pages to

349

Pages count

5

URL

https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2020_sbornik_1.pdf

BibTex

@inproceedings{BUT163729,
  author="Petra {Novotná}",
  title="Atrial Fibrillation Classification Using Deep Convolutional Network",
  booktitle="Proceedings I of the 26th Conference STUDENT EEICT 2020",
  year="2020",
  series="1",
  number="1",
  pages="345--349",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  address="Brno",
  isbn="978-80-214-5867-3",
  url="https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2020_sbornik_1.pdf"
}