AI-enhanced ECG monitoring for arrhythmia detection using semantic LinkNet deep neural network
by Soumen Ghosh; Satish Chander
International Journal of Innovative Computing and Applications (IJICA), Vol. 15, No. 2, 2025

Abstract: Cardiac disease is a leading cause of death globally, making early detection crucial for improving diagnosis and treatment. An electrocardiogram (ECG) is a key tool for monitoring heart activity, especially in identifying cardiac arrhythmia, which involves irregular heartbeats - either too fast or too slow. Automated detection systems are vital for improving detection accuracy. This work introduces a deep learning-based semantic LinkNet classifier to detect arrhythmias. The process begins by preprocessing the ECG signal including DC drift cancellation, normalisation, and low-pass filtering. QRS detection is then performed followed by feature extraction. The semantic LinkNet classifier is applied to classify normal and abnormal ECG signals. The system's performance is evaluated using the MIT-BIH database, with metrics such as accuracy, sensitivity, specificity, precision, recall, and F-measure. The proposed method's results, after filtering and QRS detection, are compared to existing models. The outcomes demonstrate that the semantic LinkNet-based system outperforms other approaches, showing superior detection rates in identifying arrhythmias.

Online publication date: Mon, 17-Mar-2025

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Innovative Computing and Applications (IJICA):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com