On the Problem of Class Imbalance in the Recognition of Electrocardiograms

DOI

10.2991/aisr.k.201029.048How to use a DOI?

Keywords

Machine Learning, Electrocardiogram, Deep Learning, Diagnoses of heart diseases

Abstract

The paper is about the problem of class imbalance in the diagnosis of diseases of the cardiovascular system using recognition of electrocardiograms. Under researching two oversampling approaches were compared. Complete cardiocycles (600 points) were used as features. In the first case, the bootstrap method was used. For recognition, a Multylayer Perceptron neural network was used. To solve the problem, significant computational resources and high costs of computer time were required. In the second case, cardiocycles were converted into images oversampled by augmentation. The calculation time was reduced from two and a half hours to 15 minutes. In the third case, both approaches were combined, which reduced the computation time to three minutes. In all three cases, recognition accuracy exceeded 97%.

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Marat Bogdanov
AU  - Nikolai Oskin
AU  - Irina Dumchikova
PY  - 2020
DA  - 2020/11/10
TI  - On the Problem of Class Imbalance in the Recognition of Electrocardiograms
BT  - Proceedings of the 8th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2020)
PB  - Atlantis Press
SP  - 249
EP  - 254
SN  - 1951-6851
UR  - https://doi.org/10.2991/aisr.k.201029.048
DO  - 10.2991/aisr.k.201029.048
ID  - Bogdanov2020
ER  -