AI-Powered Human Digital Twin for Personalized Health Monitoring
Vigneshwaran, P and Vasantha Kumar, Sither and Packialatha, A (2025) AI-Powered Human Digital Twin for Personalized Health Monitoring. 2nd International Conference on Global Trends in Engineering and Technological Advancement (2nd ICGTETA’25), 2 . GOJAN School of Business and Technology, CHENNAI. ISBN 978-81-993196-8-4
2nd ICGTETA_25 Proceeding book.pdf
Download (16MB)
Abstract
The AI-Powered Human Digital Twin for Personalized Health Monitoring is an intelligent
platform that creates a virtual replica of an individual capable of learning from continuous
health data. By integrating Artificial Intelligence (AI), Machine Learning (ML), and wearable
sensor analytics, the system forms a comprehensive digital health ecosystem that supports
preventive and personalized healthcare. It addresses key health challenges such as irregular
sleep, poor lifestyle habits, stress, and dietary imbalance by processing real-time physiological
and behavioral data, including heart rate, sleep patterns, and physical activity. The platform
includes advanced modules for Health Data Monitoring, Predictive Analytics, Lifestyle
Simulation, and Smart Recommendations. Using algorithms such as Long Short-Term Memory
(LSTM), Random Forest, and Reinforcement Learning, it predicts future health outcomes and
provides preventive lifestyle suggestions. A “what-if” simulation engine allows users to
visualize the impact of specific lifestyle changes on long-term wellness. A user-friendly
dashboard presents visual insights into health trends and recommendations, integrating data
from wearable devices and mobile applications to promote early anomaly detection and
proactive care. This approach enhances preventive medicine, empowers individuals with
personalized insights, and contributes to improving overall quality of life.
| Item Type: | Book |
|---|---|
| Subjects: | Computer Science Engineering > Big Data |
| Domains: | Computer Science Engineering |
| Depositing User: | IR Admin |
| Date Deposited: | 07 Sep 2026 16:23 |
| Last Modified: | 08 Sep 2026 06:49 |
| URI: | https://ir.vistas.ac.in/id/eprint/22844 |
