Electrocardiogram (ECG) is a low-cost diagnostic instrument used by healthcare practitioners to examine heart electrical impulses. Arrhythmia, or an aberrant heart signal, can be life-threatening and even fatal. Tachycardia, bradycardia, supraventricular arrhythmias, and ventricular arrhythmias are some of the several types of arrhythmias. Doctors benefit greatly from automated arrhythmia monitoring and classification using ECG. We employ deep machine learning for automated arrhythmia classification in this study, with an emphasis on recent arrhythmia classification trends. We ran intensive and sophisticated simulations on the St. Mary's University Deep Learning Platform to assess the performance of the various arrhythmia classification and detection models. Finally, we show that the proposed deep learning algorithms are more accurate than existing methods in terms of precision and sensitivity.
Author(S) Details
Shalin Savalia
Department of Electrical Engineering, St. Mary’s University, 1 Camino Santa Maria, San Antonio, TX 78228, USA.
Vahid Emamian
School of Science, Engineering and Technology, St. Mary’s University, San Antonio, TX 78228, USA.
View Book:- https://stm.bookpi.org/NVST-V9/article/view/4783
No comments:
Post a Comment