COVID-SAFE: An IoT-Based System for Automated Health Monitoring and Surveillance in Post-Pandemic Life

Area of Science:

• Digital Health
• Internet of Things (IoT)
• Epidemiology

Background:

• The COVID-19 pandemic highlighted the need for effective infection control measures like self-isolation and physical distancing.
• Existing methods for monitoring health and enforcing distancing are often limited in real-time application during widespread outbreaks.

Purpose of the Study:

• To propose and evaluate the COVID-SAFE framework, an integrated system for real-time health monitoring and physical distancing enforcement using IoT and Machine Learning (ML).
• To assess the framework's potential in minimizing coronavirus exposure risk by combining individual health data with environmental risk factors.

Main Methods:

• Development of a lightweight IoT node for tracking vital signs (temperature, respiratory rate, blood oxygen, cough).
• Integration with a smartphone application for user health display and distancing alerts (2m/6ft).
• Implementation of a fog-based ML system utilizing a Fuzzy Mamdani model to predict infection spread risk based on health and environmental data.

Main Results:

• The framework effectively integrates IoT sensing, mobile health monitoring, and ML-driven risk assessment.
• Analysis of energy usage and bandwidth consumption for different communication scenarios (4G/5G/WiFi, LoRa).
• Demonstration of the Fuzzy Mamdani system's capability in real-time infection risk prediction.

Conclusions:

• The COVID-SAFE framework offers a viable technological solution for managing infectious disease spread by enabling remote health monitoring and enforcing physical distancing.
• This approach can significantly assist in minimizing exposure risk and controlling outbreaks in pandemic situations.