Using C-support vector classification to forecast dengue fever epidemics in Taiwan

The outbreak of dengue fever in southern Taiwan put the whole nation on alert. This paper approaches the linear optimization and RBF kernel function of C-Support Vector Classification (C-SVC) to forecast the statistical dengue fever outbreak that has association with location, air temperature, and daily precipitation. Those attributes may cause dengue fever to risk medical complications or deaths. We apply the grid search method to the dataset to solve the hyper-parameter selection problem in the learning algorithms. Experimental results verify that RBF kernel after parameter optimization achieves better prediction accuracy on dengue fever outbreak.