Abstract
AbstractThe last two years have been marked by the emergence of Coronavirus. The pandemic has spread in most countries, causing substantial changes all over the world. Many studies sought to analyze phenomena related to the pandemic from different perspectives. This study analyzes data from the governorates of the Kingdom of Saudi Arabia (the KSA), proposing a broad analysis that addresses three different research objectives. The first is to identify the main factors affecting the variations between KSA governorates in the cumulative number of COVID-19 infections. The study uses principal component regression. Results highlight the significant positive effects of the number of schools in each governorate, and classroom density within each school on the number of infections in the KSA. The second aim of this study is to use the number of COVID-19 infections, in addition to its significant predictors, to classify KSA governorates using the K-mean cluster method. Findings show that all KSA governorates can be grouped into two clusters. The first cluster includes 31 governorates that can be considered at greater risk of Covid infections as they have higher values in all the significant determinants of Covid infections. The last objective is to compare between traditional statistical methods and artificial intelligence techniques in predicting the future number of COVID-19 infections, with the aim of determining the method that provides the highest accuracy. Results also show that multilayer perceptron neural network outperforms others in forecasting the future number of COVID-19. Finally, the future number of infections for each cluster is predicted using multilayer perceptron neural network method.
Publisher
Springer Science and Business Media LLC
Subject
General Economics, Econometrics and Finance,General Psychology,General Social Sciences,General Arts and Humanities,General Business, Management and Accounting
Reference36 articles.
1. Alabdulrazzaq H, Alenezi M, Rawajfih Y, Alghannam B, Al-Hassan A, Al-Anzi F (2021) On the accuracy of ARIMA based prediction of COVID-19 spread. Results Phys 27:104509
2. Alkhowailed M, Shariq A, Alqossayir F, Alzahrani O, Rasheed Z, Al Abdulmonem W (2020) Impact of meteorological parameters on COVID-19 pandemic: a comprehensive study from Saudi Arabia. Inform Med Unlocked 20:100418
3. Benvenuto D, Giovanetti M, Vassallo L, Angeletti S, Ciccozzi M (2020) Application of the ARIMA model on the COVID-2019 epidemic dataset. Data Brief 29:105340
4. Blatná D (2006) Outliers in regression. Trutnov 30:1–6
5. Box G, Jenkins G, Reinsel G, Ljung G (2015) Time series analysis: forecasting and control: John Wiley & Sons.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献