IoT Geofencing for COVID-19 Home Quarantine Enforcement

Abstract

Containment is the first-priority measure in infection control to curb the spread of highly infectious diseases such as COVID-19. Home quarantine is one such measure to keep people at their accommodations for the incubation period (typically 14 days). Compared to dedicated monitoring centers, home quarantine is a more cost-effective and comfortable approach to isolate a large number of low-risk people. However, efficient monitoring of confinees inside their accommodations is a challenging problem because the quarantined locations are scattered throughout the city. We propose and study SignatureHome, an automated IoT-based geofencing algorithm to cost-effectively monitor confinees. The core principles of SignatureHome was adopted by the Hong Kong government and implemented as an app to enforce home quarantine order in March 2020 for hundreds of thousands of entrants from other regions.The system employs waterproof Bluetooth Low Energy wristbands that are uniquely paired with the confinees' smartphones. SignatureHome uses the identifiers of the environmental network facilities (Wi-Fi access points and cellular networks) as the home signature. By comparing the current observed signals of the phone with the home signature, the algorithm can efficiently determine whether the user is within the geofenced area. SignatureHome is computationally efficient, responsive, privacy-preserving, cost-effective, and adaptive to home diversity and changing environments. Our experimental results validate its design and high accuracy in terms of precision, recall, F-measure, and false alarm rate.