Authors: Ashu Gulia, Ajay Dagar, Dr.Sangeeta Rani, Ms. Monika Saini
Abstract: Pacemakers serve as critical medical devices for monitoring and regulating heart rhythms within patients afflicted with arrhythmias or heart failure. Truly ensuring their accuracy, with reliability and cybersecurity, is paramount. This paper here explores the usage of Support Vector Machines (SVM), and particularly one-class SVM, for the anomaly detection of pacemaker signal patterns. Effectively, deviations showing device failure, cardiac irregularities, or potential cyberattacks can be identified via training models to recognize "normal" cardiac signals. Drawing on methodologies from malware anomaly detection [1][2][3], we adapt as well as repurpose these machine learning techniques to the medical context. The study presents several implementation steps and deployment challenges. The study gives a comparative evaluation with many detection methods, contributing to a safer, clever, and secure pacemaker infrastructure.
