Sustainable IoT Entry System with Contactless Temperature Detection and Cloud-Based Contact Tracing

Amid the surge in COVID-19 cases, nations are imposing stringent measures to curb transmission. In response, we developed a sustainable IoT-based system to manage the movement of potential COVID-19 patients in public spaces, emphasizing reduced resource consumption and long-term health management. The system provides an affordable, contactless body temperature measurement solution by leveraging fever as a primary symptom. A portable IoT device was engineered, processing data with neural networks and storing it in the cloud for efficient contact tracing. When temperatures exceed a predefined threshold, the device restricts entry to crowded areas and captures images using a Raspberry Pi camera for those identified with higher temperatures. The selective entry mechanism achieved 97% accuracy. The system also integrates a neural network-based mask detection algorithm to prevent unmasked entries, capturing images of individuals denied entry. These images are securely encrypted and stored in the cloud, ensuring privacy and facilitating future contact tracing. This novel IoT system combines high accuracy with sustainable practices, offering a cost-effective solution for selective entry, contact tracing, and secure cloud storage, contributing to the sustainable management of public health during pandemics.