Affiliation:
1. IT Fusion Technology Research Center, Department of IT Fusion Technology, Chosun University, 309 Pilmun-daero Dong-gu Gwangju 61452, Korea.
Abstract
Arrhythmia is a cardiovascular disease with an irregular heartbeat, which can lead to a heart attack if it lasts for an excessive amount of time. Because the symptoms of arrhythmia occur irregularly, the heart needs to be monitored for a lengthy time period. This study suggests an arrhythmia diagnosis algorithm using GoogLeNet and a GAN. Because the algorithm proposed in this study can add to the number of data using a GAN, it can accurately diagnose an arrhythmic occurrence from measured lifelog over a short period of time. The classification of ECG data using GoogLeNet and a GAN showed an accuracy of approximately 99%.
Publisher
North Atlantic University Union (NAUN)
Subject
General Biochemistry, Genetics and Molecular Biology,Biomedical Engineering,General Medicine,Bioengineering
Reference17 articles.
1. Mayo Clinic, LIVESCIENCE, “What is a Normal Heart Rate?”, 2018
2. Victor Chang, Cardiac Research institue “Arrhythmia”, 2020.
3. VOLLMER, Marcus, “Arrhythmia classification in long-term data using relative RR intervals”, In: 2017 Computing in Cardiology (CinC). IEEE, 2017, pp. 1-4.
4. HUANG, Jingshan, et al, “ECG arrhythmia classification using STFTbased spectrogram and convolutional neural network”, IEEE Access, 2019, pp. 92871-92880.
5. GUPTA, Varun; MITTAL, Monika, “R-peak based Arrhythmia Detection using Hilbert Transform and Principal Component Analysis”, In: 2018 3rd International Innovative Applications of Computational Intelligence on Power, Energy and Controls with their Impact on Humanity (CIPECH), IEEE, 2018. pp. 1-4.