|
|
 |
| |
|
|
|
Predicting Covid-19 Data Using Machine Learning and Statistical Methods |
|
|
|
PP: 387- 393 |
|
|
|
doi:10.18576/isl/130216
|
|
|
|
Author(s) |
|
|
|
Abdelgalal O. I. Abaker,
Wahiba Ismaiel,
F. M. DawAlbait,
Zahra. I. Mahamoud,
Hago E. M. Ali,
Adil. O. Y. Mohamed,
Azhari A. Elhag,
|
|
|
|
Abstract |
|
|
| Overall, there has been a 21% reduction in new COVID-19 cases and a 17% reduction in deaths during the most recent 28-day period (April 24 to May 21, 2023) compared to the previous 28-day period (March 27 to April 23, 2023). However, there are regional variations in the situation. The WHO Western Pacific and African Regions have seen an increase in reported cases, while the Western Pacific, African, American, South-East Asian, and American Regions have observed an increase in mortality. As of May 21, 2023, there have been a total of 6.9 million fatalities and over 766 million confirmed cases worldwide. This information can be found on the homepage of the World Health Organization (WHO). This paper focuses on the application of machine learning and statistical models to predict COVID-19 data. Both machine learning and statistical theory aim to find predictive functions from the available data through statistical inference. The study compares a time series model as a statistical approach and a decision tree model as a machine learning approach, using various statistical metrics. The findings indicate that the decision tree model exhibits the highest level of accuracy. The study specifically examines new cases of COVID-19 infection in the Kingdom of Saudi Arabia from January 3, 2020, to June 3, 2023, utilizing data obtained from the World Health Organization website.
|
|
|
|
|
|
|
|
