Rule-based model of the risk of SARS-CoV-2 infection spread in indoor environments

The COVID-19 pandemic has exposed the need for robust and interpretable analytical tools to assist decision-makers in their tricky task of establishing directives that aim to slow the spread of the disease without negatively impacting the normal operation of society. The OPENNESS project (http://openness.iasi.cnr.it/) identifies this need and proposes to generate a forecasting system that exploits AI methods to identify a behavioural logic that is appropriate to follow. In this talk we will present preliminary results obtained as part of the development of the project, in particular we will show models based on IF-THEN type rules, which were generated from a dataset obtained through a virtual environment that aims to emulate the dynamics developed in a given time lapse within the Roma Termini station