Published Paper Details:

Of all the reasons for death, one of the most common reasons is Cardiovascular diseases (CVDs). Factual data says that more than 17.9 million people die every year because of these diseases. Some of the known CVDs are cerebrovascular disease, rheumatic heart disease, coronary artery disease, and various other blood vessel and heart-based illnesses. Arrhythmias are generally innocuous, but some can be harmful or even deadly. If the heartbeat is excessively rapid, too slow, or irregular, the heart may not be able to provide sufficient of blood to amount to the body. This disease also produces the possibilities to elevate your chances of having a stroke, heart failure, or other cardiac problems. My goal is to categorize ECG by preprocessing the raw signal to identify Cardiac Arrhythmias and then to separate the signals into various classes with the help of convolutional neural networks (CCN). After the data-preprocessing step, the model is developed with a properly built CNN. The dataset has been split in an 80:20 ratio so that they can be trained and then tested respectively. A single ECG file is also evaluated using the learned model. The point of using a CNN model was to produce the most accurate results. Our goal with this project was to create an efficient method for classifying and detecting cardiovascular disorders in the medical and health sectors, for which we managed to provide an algorithm