Date of Award

Fall 2021

Publication Type


Degree Name



Computer Science

First Advisor

P. Zadeh


Agent-Based Modeling, Artificial Intelligence, COVID-19, Multi-Agent Systems, Pandemic, Social Isolation




The spread of Coronavirus, widely known as COVID-19, has posed detrimental effects worldwide, affecting almost every primary sector. Due to its asymptomatic behavior and non-early diagnosis, government and health organizations implemented interventions such as physical distancing, lockdown, and quarantine, to mitigate the spread of the virus. Studies have shown that a connection exists between social isolation and health risks experienced by individuals. Thus, this research proposes an agent-based model to address the impact of varying interventions in our society. For simulation purposes, the SEIR model is followed, and agents are categorized into two classes based on their pace of movement, low and high mobility agents. These are further classified into four different states: susceptible, infected, recovered, and dead depending upon their changing health status. Their corresponding probabilities are determined, and the algorithm proceeds accordingly. Simulations of different scenarios before and during the COVID-19 are performed using multi-agents. Resulting outcomes are evaluated and analyzed, where agents may follow one or more interventions at a time. Various parameters are used in this research to imitate real-time physical situations while formulating the simulation environment. Some of these include the hospitals count, hospital capacity, transmission rate, and recovery time for agents in different states. Our model defines certain metrics based on the number of contacts an agent has with the other agents and the distance between the agents and its neighbors. Considering these multiple parameters and metrics enable the model to simulate varying conditions. For validation purposes, the simulation environment is made similar to the real-world society. Our model may benefit in deciding the mitigating factors in times of a similar pandemic or epidemic situations in the long term. Policymakers, health professionals, or researchers may extend this model and simulate the dissemination of ailments identical to this one.