Analysis the dengue patients increasing rate in Bangladesh based on weather by using machine learning models

Abstract

Dengue virus is created in the medium of Aedes mosquito. Because the virus is more prevalent in tropical areas and people are more affected, people in these areas should be aware of it as a health concern and have effective disease management measures in place. Reduction and prediction of dengue outbreaks is crucial for prevention and reduction of mortality. As the death rate has been decreasing in recent years, recently machine learning algorithm are all of them models have the potential to dengue prediction and reduce mortality as they analyze correlations between large datasets. All are algorithms are an too much basis for dengue risk prevention and control. Dengue is dangerous and sometimes fatal. This fever infection has become a major problem. So we need to predict the dengue outbreak and reduce mortality. Provides an overview of various ML methods used in dengue prediction including Logistic Regression models, DT, KNN. Examining the limitations of each, discussing features, selection, model interpretability and in addition, we discuss related data for dengue forecasting and mortality reduction, such as models for different geographic regions. My aim to decrease the accuracy of dengue forecasting models and provide directions for future research. Various ML algorithms are used to analyze dengue data sets of summer patient illness in Dhaka city to reduce dengue prevalence and mortality. Our results suggest that applying machine learning techniques is an accurate tool to predict dengue. which is used to reduce the effects of disease on humans, including incorporating real data. ML plays a role in dengue prediction.