JISE

Dengue fever is a mosquito-borne pathological infection that is the nation's most dan-gerous widespread human illness disorder, posing a critical threat to humankind. Moreover, accuracy is a major challenge during dengue epidemic prediction that must be addressed. A few research studies have looked into the factors influencing dengue outbreak prediction. Furthermore, only a tiny fraction of the infected population can be properly predicted using a forecasting approach for dengue infection disorders based solely on meteorological vari-ables. This limitation is caused by a low mosquito population below infection transmission thresholds. Therefore, an Improved Deep Learning Model for Predicting Dengue Outbreaks is proposed, in which novel climatic parameters such as the TempWind factor are evaluated. Then to estimate the dengue risk incidence level, the Bayes network model combined with Particle Swarm Optimization (PSO) is introduced. As a result, the proposed model has pro-ven that using the correct and relevant factor of putting aspects for epidemic forecasting yields improved and accurate findings.