Ensemble machine learning based prediction of dengue disease with performance and accuracy elevation patterns

Abstract

Abstract Mosquitoes have numerous illnesses and are one of the deadliest animals in the planet. Including Zika, dengue, palaria, West Niles, chikungunya, yellow fever, and more, mosquitoborne illnesses. Various areas suffer from various climate-induced mosquito-borne illnesses, kinds of mosquitoes widespread across the region and access to preventive measures and medicines. Dengue fever is a mosquito-borne disease that is transferred to the dengue virus via the bite of an Aedes mosquito. The bits of the infected female Aedes mosquito, which spreads the virus to others as it feeds on the infected people s blood. Transmission of dengue is susceptible to climate due to many causes, such as temperature, humidity, precipitation, etc. Areas with higher vapor pressure and precipitation rates are more prone to dengue illness transmission. We utilized the classification algorithms to discover the essential characteristics that spread the dengue. Machine learning is one of the most important approaches of current analysis. For medical applications, many algorithms were employed. Dengue disease is one of the worst infectious diseases that require a high level machine to develop good models in order to learn. We employed the Ensemble Machine Learning technique in hybrid integrations to identify characteristics associated with the spread of the Dengue illness and achieve improved performance.