ECG Data Classification Using Machine Learning Approaches

Abstract

Electric heartbeat was monitored with an electrocardiogram. It was an easy and fun way to diagnose heart problems but also to keep a
healthy record of our bodies. Heart disease often manifests itself as chest tightness, sickness, light head edness, severe instability,
chest tightness, rapid heartbeat, shortness of breath, fatigue, drowsiness, or even decreased exercise rate. The same basic principle
would be for machines to be straight within it, but without the intervention of users, and also to change their habits accordingly.
Distinguishing is among the machine-readable learning strategies they use to classify data sets effectively. This paper introduces a
multidisciplinary survey in the separation of ECG data using machine learning methods found at the beginning of the literature. It is
very useful in both computer and medical research in the field of automatic diagnosis of heart disease. Class dividers improve
physician accuracy and early detection for better treatment of affected patients.