Digital twins

Abstract

Airborne diseases like COVID-19, measles, and tuberculosis spread rapidly in enclosed spaces such as elevators. This project develops a real-time Digital Twin using low-cost sensors and cloud-based monitoring to assess infection risk in lifts. By fusing CO₂, temperature, and humidity data with machine learning and the Wells-Riley model, the system forecasts high-risk conditions, detects anomalies, and classifies safety levels. It also provides comfort ratings to ensure thermal wellbeing. The scalable, database-free design makes it ideal for resource-constrained settings like schools and hospitals. This work offers a smart, affordable solution to enhance health resilience in everyday public infrastructure.