Convergence of Cloud with AI for Big Data Analytics

15Detecting Heart Arrhythmias Using Deep Learning Algorithms

Dilip Kumar Choubey¹*, Chandan Kumar Jha², Niraj Kumar², Neha Kumari² and Vaibhav Soni³

¹ Department of Computer Science and Engineering, Indian Institute of Information Technology Bhagalpur, Bihar, India

² Department of Electronics and Communication Engineering, Indian Institute of Information Technology Bhagalpur, Bihar, India

³ Department of Computer Science and Engineering, Maulana Azad National Institute of Technology, Bhopal, M.P., India

Abstract

An electrocardiogram measures the electrical activity of the heart and has been widely used for detecting heart diseases due to its simplicity and non-invasive nature. It is possible to detect some of the heart’s abnormalities by analyzing the electrical signal of each heartbeat, which is the combination of action impulse waveforms produced by different specialized cardiac tissues found in the heart, as it is challenging to visually detect heart disease from the ECG signals. Implementing an automated ECG signal detection system can aid in the identification of arrhythmia and increase diagnostic accuracy. In this chapter, we proposed ECG signal (continuous electrical measurement of the heart), implemented, and compared multiple types of deep learning models to predict heart arrhythmias for classifying normal signals and abnormal signals. The MIT-BIH arrhythmia dataset has been used. Finally, authors have discussed the limitations and drawbacks of the methods in the literature ...