AI-driven autonomous vehicles as COVID-19 assessment centers: A novel crowdsensing-enabled strategy

Simsek, M.; Boukerche, A.; Kantarci, B.; Khan, S.

Internet of Things(IoT) facilitates key technologies that rely on sensing, communication and processing in daily routines. As an IoT-enabled paradigm, mobile crowdsensing (MCS) can offer more possibilities for data collection to support various IoT applications and services. As an extension, MCS can be used for data gathering amid COVID-19 pandemic crisis. Bridging Artificial Intelligence and IoT can achieve not only maintaining low infection rates of COVID-19 but can also facilitate an effective rapid testing strategy to reduce community spread. In this research, an intelligent strategy to deploy autonomous vehicle-based mobile testing facilities is proposed to enable early detection of infected cases based upon MCS data acquired through smart devices via wireless communications such as Wifi, LTE and 5G. To this end, a Self Organizing Feature Map is designed to manage MCS-based data for planning of the autonomous mobile assessment centers. Pre-identified zero-day locations and worst-case scenario are considered to determine the best combination for MCS participation rate and budget limitations. Numerical results demonstrate that once 30% of MCS participants are recruited, it becomes possible to cover the pre-identified zero-day locations and enable detection of infected cases under the worst case scenario to determine the AV routes more efficiently than other options for a certain number of neurons in SOFM. The worst-case scenario demonstrates that 30% participant rate ensures detection of infected cases in 27 days for 81 stops even infected cases are outside of the autonomous vehicle testing coverage. © 2021 Elsevier B.V.