International Journal of Applied Information Systems |
Foundation of Computer Science (FCS), NY, USA |
Volume 12 - Number 36 |
Year of Publication: 2021 |
Authors: Ajinaja Micheal Olalekan, Abiona Akeem Adekunle, Ibiyomi Michael Adeniyi |
10.5120/ijais2020451899 |
Ajinaja Micheal Olalekan, Abiona Akeem Adekunle, Ibiyomi Michael Adeniyi . Predictive Modelling of Covid-19 Confirmed, Death related and Recovered Cases in Italy, Wuhan, South Korea and India. International Journal of Applied Information Systems. 12, 36 ( January 2021), 7-19. DOI=10.5120/ijais2020451899
The coronavirus pandemic has been ravaging the world since December 2019.The pandemic started from Wuhan in China late 2019 and has greatly affected thousands of people with the impact felt in different economy. This required the need to observe, monitor and predict infected, recovered and death related COVID-19 cases for suitable control. Prophet was used to predict future values by creating a base model with no tweaking of seasonality-related parameters and additional regressors. The data was extracted from the John Hopkins state of art data centre website which spanned from 31st January 2020 to 25th Match 2020. We adopted the machine learning library (prophet) to predict a week data and also showed analysis using Plotly. Italy, Wuhan, South Korea and India were compared and analysed using the model. The results showed that confirmed cases in Italy continually kept rising exponentially with a certain fixed pattern, confirmed cases in India continually kept rising exponentially with no fixed pattern with the graph attaining sigmoid early but later increased exponentially with no particular fixed pattern which was as a result of very less test done in India, confirmed cases in South Korea was rising gradually with sigmoid attained at some level with the government able to reduce the spike in infected persons and in Wuhan, there have been almost a negligible number confirmed cases in a week. This prediction showed how government can prepare for any eventualities in the future and be able to combat future pandemic occurrence, Emphasis should be on testing and enforcing early lockdown