CoronaSim utilizes A.I and machine learning to model an elastic COVID-19 simulation to analyze the spread of the novel coronavirus.

  • 210 Raised
  • 6 Juries


  • Main


CoronaSim is a pathogen simulation based on the use of hidden agents and nodes functioning within a dynamic convolutional neural network. A multitude of features have been implemented for the customization of environmental and circumstantial factors on which the simulation is conducted on. This allows the user to see the effects of demographic factors as well as preventative measures on infection rates, such as quarantining a building. The user can also analyze the simulation in real-time with a graph to gain a better understanding of the correlation between infected and recovered.

In regard to artificial intelligence, the simulations acts as a function of agents and nodes used in a dynamic convolutional neural network (CNN). At CNN initialization, agents are assigned either "Susceptible" or "Infected" states. As time passes within the simulation itself, the neural network operates as a function of ticks. As ticks progress, infected agents spread the pathogen (based on a transition model optimized with the specific weights of the coronavirus) to the rest of the simulated population and other agents get infected as well. Probabilistic values based on a deterministic Markov chain and real world application are utilized to dictate whether the agent will switch to a "Recovered" or "Dead" state. Additionally, all agent pathfinding is facilitated by a similar Markov chain between varying building nodes, which are acting as schools, supermarkets, and hospitals.

Demonstration Video:


Code (GitHub Repository):

Copyright © 2022 All rights reserved. TAIKAI — Hackathon Platform.