Open Access Open Access  Restricted Access Subscription Access

A Survey on Neural Network based Classifier for Arrhythmia Detection

Mihir Narayan Mohanty


Electrocardiogram (ECG) is one of the important diagnostic tool for the detection of the heart problem. Increasing number of cardiac patients need automatic detection techniques for various abnormalities or arrhythmias of the heart to reduce pressure on physicians and share their load. Coronary Care Units (CCUs) emphasizes on the task of accurate analysis of ECG signal at an early stage that can prevent disease, like tachycardia, to escalate there by reducing the mortality rate. The diagnostic power of these machines has grown manifolds mainly due to the exploration of effective and discriminate feature spaces that remain crucial for pattern classification and detection. In this paper a literature survey is conducted for the classification and detection of Arrhythmia using different machine learning techniques. The classification is also done using MLP and DNN. Around 96% and 99% classification accuracy is obtained from these two classifier respectively.


Electrocardiogram (ECG); Arrhythmia; Neural Network; Deep Neural Network

Full Text:



  • There are currently no refbacks.

Copyright (c) 2018 Journal of Communication Engineering & Systems