Arrhythmia Detection from ECG Signals using CNN Model

The World Health Organization (WHO) has conducted research that shows how difficult it is to diagnose and treat cardiovascular illnesses. A low-cost diagnostic tool called an electrocardiogram (ECG) is used to assess the electrical conductivity of the heart. The most well-known issue for arrhythmia identification in relation to cardiovascular illness is classification. In this work, we created a novel deep CNN (9-layer) model that classifies ECG heartbeats into five categories automatically in accordance with the ANSI-AAMI standard (1998). This classification is done without the use of feature extraction and selection methods. The publicly accessible Physio net MIT-BIH database is used for the experiment. The assessed findings are then compared with the previously published research.