WSEAS Transactions on Information Science and Applications
Print ISSN: 1790-0832, E-ISSN: 2224-3402
Volume 20, 2023
Development of Regression Models for COVID-19 Trends in Malaysia
Authors: , , , ,
Abstract: COVID-19 has emerged as the biggest threat to the world’s population, since December 2019. There have been fatalities, financial losses, and widespread fear as a result of this extraordinary occurrence, especially in Malaysia. Using available COVID-19 data from the Ministry of Health (MOH) Malaysia website, from 25/1/2020 to 17/6/2022, this study generated regression models that describe the trends of COVID-19 cases in Malaysia, taking into account the unpredictable nature of COVID-19 cases. Three techniques are used in Weka software: 60:40 / 70:30 split ratio, 10 and 20-fold cross-validation, Support Vector Regression (SVR), Multi Linear Regression (MLR), and Random Forest (RF). Based on new instances among adults, the study’s findings indicate that RF has the strongest coefficient correlation and the lowest Root Mean Square Error of 22.7611 when it comes to predicting new COVID-19 deaths in Malaysia. Further investigation into prospective characteristics like vaccination status and types, as well as other external factors like locations, could be added to this study in the future.
Search Articles
Keywords: COVID-19, Regression Models, Random Forest, Support Vector Regression, Linear Regression, Supervised
Pages: 398-408
DOI: 10.37394/23209.2023.20.42