ISSN Approved Journal || eISSN: 2582-8185 || CODEN: IJSRO2 || Impact Factor 8.2 || Google Scholar and CrossRef Indexed
Fast Publication within 48 hours || Low Article Processing Charges || Peer Reviewed and Referred Journal || Free Certificate
Integrating deep learning architectures for improved arrhythmia detection in electrocardiogram signals
Department of ECE, ACE College of Engineering & APJ Abdul Kalam Technological University Thiruvananthapuram, India.
Research Article
International Journal of Science and Research Archive, 2023, 08(02), 704–715.
Article DOI: 10.30574/ijsra.2023.8.2.0332
Publication history:
Received on 17 March 2023; revised on 29 April 2023; accepted on 01 May 2023
Abstract:
Cardiovascular ailment (CVD)is a main reason of morbidity and mortality worldwide. WHO reviews that there are almost 1 crore 20 Lakhs of deaths due to coronary heart illnesses. Early detection and correct prognosis of CVDs are important for powerful remedy and prevention. Monitoring the affected person for twenty-four hrs isn't continually feasible as it calls for plenty of understanding and time. Heart disorder remedy or prognosis are very complicated, specifically in growing countries or poor nations. The clinical enterprise has a big quantity of statistics and is constantly utilized by researchers to increase advancing technology and generation to limit sizeable quantity of deaths because of coronary heart sicknesses. A good buy of statistics mining and ML strategies or algorithms are to be had to fetch the statistics from databases and use this fetched statistics to expect the coronary heart sicknesses very accurately. This paper offers a comparative study of those 3 deep learning architectures for arrhythmia detection using electrocardiogram (ECG) signals. The overall performance of the models become evaluated using standard metrics together with accuracy, sensitivity, and specificity.
Keywords:
Congenital heart disease; Recurrent Neural Network; Rectified Linear Network; Cardiac Arrhythmia
Full text article in PDF:
Copyright information:
Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0
