Machine Learning-Backed Planning of Rapid COVID-19 Tests With Autonomous Vehicles With Zero-Day Considerations

ABSTRACT

The COVID-19 pandemic has stretched public health resources to the limits, and the only realistic way to keep the infection rates low is effective testing to prevent community transmission. In this research study, we propose an innovative method to empower autonomous vehicle-driven mobile assessment facilities to support early detection of the cases contracted with the virus, and enable early detection of sources for hot spots. We describe a self organizing feature map (SOFM) approach to the allocation of the mobile assessment centers, and also use the same method to determine the travel route of the autonomous vehicles, and provide critical decision support to the supply chain manager. Our results reveal that the optimal number of neurons under varying test times can be obtained by 5 different zero-day coordinates of initially contracted cases and worst-case scenario to find out the contracted cases in 17 days and 27 days under two different test time scenarios.