Adaptive Baseline Modeling for Personalized Cardiovascular Anomaly Detection
Onkar Belure1, Ketki Landge2, Aryan Mansuke3, Aditya Jain4, Aarti Kale5
1Onkar Belure, Department of Computer Science and Engineering, MIT-ADT University, Pune (Maharashtra), India.
2Ketki Landge, Department of Computer Science and Engineering, MITADT University, Pune (Maharashtra), India.
3Aryan Mansuke, Department of Computer Science and Engineering, MIT-ADT University, Pune (Maharashtra), India.
4Aditya Jain, Department of Computer Science and Engineering, MITADT University, Pune (Maharashtra), India.
5Dr. Aarti Kale, Department of Computer Science and Engineering, MITADT University, Pune (Maharashtra), India.
Manuscript received on 24 April 2026 | First Revised Manuscript received on 04 May 2026 | Manuscript Accepted on 15 May 2026 | Manuscript published on 30 May 2026 | PP: 17-18 | Volume-13 Issue-5, May 2026 | Retrieval Number: 100.1/ijies.E477115050626 | DOI: 10.35940/ijies.E4771.13050526
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Wearable devices such as smartwatches allow continuous monitoring of physiological signals, including heart rate and activity levels. Many current monitoring systems rely on fixed population-based thresholds that may not reflect individual physiological differences. This paper explores a personalised monitoring framework based on adaptive baseline modelling and anomaly detection. Physiological signals obtained from wearable sensors such as photoplethysmography (PPG), accelerometers, and gyroscopes are used to derive features including heart rate, heart rate variability, and motion activity. By learning an individual’s normal physiological patterns over time, the system can identify deviations that may indicate unusual cardiovascular behaviour. The goal of this work is to outline a monitoring approach to support personalised health monitoring using wearable devices.
Keywords: Cardiovascular Monitoring, Wearable Sensors, Anomaly Detection, Adaptive Baseline Modelling, Autoencoder.
Scope of the Article: Computer Science and Engineering