Back

Covid-19 Prediction in USA using modified SIR derived model

desan, J.

2020-12-22 public and global health
10.1101/2020.12.20.20248600 medRxiv
Show abstract

The Covid-19 pandemic is rapidly extended into the extraordinary crisis. Based on the SIR model and published datasets the Covid-19 spread is assessed and predicted in USA in terms of susceptible, recovered and infected in the communities is focused on this study. For modelling the USA pandemic prediction several variants have been utilized. The SIR model splits the whole population into three components such as Susceptible (S), Infected (I) and Recovered or Removed (R). A collection of differential equations have been utilized to propagate the model and resolve the disease dynamics. In the proposed study, the prediction of covid-19 based on time is performed using the modified SIR derived model SIR-D with discrete markov chain. This proposed technique analyse and forecasting the covid-19 spread in 19 states of USA. The performance analysis of the proposed Analytical results revealed that though the probable uncertainty of the proposed model provides prediction, it becomes difficult to determine the death cases in future.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.