Prediction of dengue cases based on the meteorogical factors by using machine learning

Dengue that is affected by meteorological factors, including the rainfall and temperature had caused many deaths. Nurulhusna AH even added that "Malaysia is endemic for dengue". To effectively manage and prevent dengue outbreaks, accurate prediction systems are essential. However, currently Malaysia still lack of system that makes predictions about dengue. Thus, the objective of this project is to develop a web-based system that can predict the number of dengue cases, along with the week and state that have the highest number of dengue cases. System will be developed by using python language, to apply machine learning techniques namely Multiple Linear Regression (MLR), Random Forest Regression, Gradient Boosting Regression (GBR), and Support Vector Regression (SVR). Based on the project, Support Vector Regression (SVR) algorithm was identified as the most suitable model to make prediction on the number of dengue cases. Besides, the week with highest number of dengue cases vary for each state. It also discovered that Selangor is the state with the highest number of dengue cases. In the future, the researcher can perform feature selection to identify significant factors impacting dengue transmission through exploratory data analysis and machine learning-based techniques, other than using a more accurate dataset.