Classification Between Normal Heartbeat and Angina Pectoris in Phonocardiograph Using Neural Network

DOI

10.2991/assehr.k.200204.032How to use a DOI?

Keywords

Angina Pectoris, phonocardiograph, neural network

Abstract

Data from the Ministry of Health shows that heart disease is the highest cause of death in all ages after stroke. This death rate will continue to increase if heart disease is not treated early. Delay in the handling of patients with cardiac abnormalities is due to the limited heart detection devices especially in health facilities in remote areas. This study aims to build a cheap but reliable tool for detecting heart abnormalities to be applied to various health centers in remote areas. A phonocardiography (PCG) device has been built that can record acoustic heartbeat signals. The final step in this research is to build an artificial intelligence-based pattern recognition system to determine the type of heart defects suffered by patients. The results of PCG output have been analyzed using Short Time Fourier Transform and the results found that the output of the system is consistent, which indicates that the system has good reliability. It proves that the system can recognize a healthy heart rate and heart rate with Angina Pectoris up to 90%. After PCG validation, it will be tried to be applied in Giritontro health center which does not have a detection of heart abnormalities so that it can help early treatment of heart disease.

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  - Dyah Kurniawati Agustika
AU  - Juli Astono
AU  - Sumarna
AU  - Agus Purwanto
PY  - 2020
DA  - 2020/02/12
TI  - Classification Between Normal Heartbeat and Angina Pectoris in Phonocardiograph Using Neural Network
BT  - Proceedings of the International Conference on Educational Research and Innovation (ICERI 2019)
PB  - Atlantis Press
SP  - 176
EP  - 178
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.200204.032
DO  - 10.2991/assehr.k.200204.032
ID  - Agustika2020
ER  -