Real-Time COVID-19 Infection Risk Assessment and Mitigation based on Public-Domain Data

Workshop:Urgent HPC: HPC for Urgent Decision Making

Authors: Albert Cheng (University of Houston)

Abstract: A number of models have been developed to predict the spreads of the COVID-19 pandemic and how non-pharmaceutical interventions (NPIs) such as social distancing, facial coverings, and business and school closures can contain this pandemic. Evolutionary artificial intelligence (AI) approaches have recently been proposed to automatically determine the most effective interventions by generating a large number of candidate strategies customized for different countries and locales and evaluating them with predictive models. These epidemiological models and advanced AI techniques assist policy makers by providing them with strategies in balancing the need to contain the pandemic and the need to minimize their economic impact as well as educating the general public about ways to reduce the chance of infection. However, they do not advise an individual citizen at a specific moment and location on taking the best course of actions to accomplish a task such as grocery shopping while minimizing infection. Therefore, this paper describes a new project aiming to develop a mobile-phone-deployable, real-time COVID-19 infection risk assessment and mitigation (RT-CIRAM) system which analyzes up-to-date data from multiple open sources leveraging urgent HPC/cloud computing, coupled with time-critical scheduling and routing techniques. Facing the increasing spread of the more contagious Delta (B.1.617.2) variant, this personal system will be especially useful for individual citizen to reduce her/his infection risk despite increasing vaccination rates while contributing to containing the spread of the current and future pandemics.

Back to Urgent HPC: HPC for Urgent Decision Making Archive Listing

Back to Full Workshop Archive Listing