An IoT-Based Wristband for Automatic People Tracking, Contact Tracing and Geofencing for COVID-19.

The coronavirus disease (COVID-19) pandemic has triggered a huge transformation in the use of existing technologies. Many innovations have been made in the field of contact tracing and tracking. However, studies have shown that there is no holistic system that integrates the overall process from data collection to the proper analysis of the data and actions corresponding to the results. It is critical to identify any contact with infected people and to ensure that they do not interact with others. In this research, we propose an IoT-based system that provides automatic tracking and contact tracing of people using radio frequency identification (RFID) and a global positioning system (GPS)-enabled wristband. Additionally, the proposed system defines virtual boundaries for individuals using geofencing technology to effectively monitor and keep track of infected people. Furthermore, the developed system offers robust and modular data collection, authentication through a fingerprint scanner, and real-time database management, and it communicates the health status of the individuals to appropriate authorities. The validation results prove that the proposed system identifies infected people and curbs the spread of the virus inside organizations and workplaces.

A System for Conversion of Hand-drawn Electrical circuit to Digital circuit: A Deep learning approach

The conversion of hand-drawn circuit to digital image is very essential for designers to save their rough sketch. Due to COVID-19, the teaching-learning process has become completely virtual. In this scenario, the present work on conversion of hand-drawn circuit to digital circuit is expected to help the faculty and students of engineering circuit branches. The MobileNet SSD architecture is used for detection of resistors, capacitors, inductors and battery in the hand-drawn circuit. Image overlay and skeletonization technique are used to obtain the digital image. In the present work, very few electrical components are considered for modeling;however, the proposed system can be extended (trained) for more number of electrical components and can be deployed in mobile applications with ease. © 2021 IEEE.