Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194016,
        author = {Nagraj Motti and Chetan and Uday and Tilak Singh and Sangameshwar Kawdi},
        title = {IoT Based ECG Anomaly Detection Using Self Supervised Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {2887-2895},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194016},
        abstract = {Over the past few decades, heart disease has become one of the main causes of death worldwide. Timely diagnosis and prevention of life-threatening illnesses depend on early identification and ongoing heart activity monitoring. The goal of this project, "Anomaly Detection in Electrocardiograms: Advancing Clinical Diagnosis Through Self-Supervised Learning," is to create an intelligent ECG monitoring and analysis system that uses sensor-based data acquisition and self-supervised learning concepts to identify abnormal cardiac patterns. An Arduino microprocessor processes the electrical activity of the heart, which is recorded by an AD8232 ECG sensor. The ESP8266 Wi-Fi module transmits the analyzed ECG signals to the Thing Speak cloud for data storage and real-time monitoring. Without the need for large labeled datasets, a self-supervised learning model is intended to examine ECG patterns, spot abnormalities, and support clinical diagnosis. The device sounds a buzzer alert and shows the discovered condition on an LCD screen when it detects an aberrant ECG pattern. Through automated anomaly identification, this method not only guarantees ongoing, remote monitoring of cardiac health but also improves diagnostic precision and decision-making. For effective and intelligent cardiac care, the suggested solution shows a step forward in combining IoT, embedded technologies, and AI-driven learning.},
        keywords = {Multi-scale Cross-Attention, Trend Assisted Restoration, Attribute Prediction Module, Rare Cardiac Anomalies, Patient-specific attributes},
        month = {March},
        }