Intelligent Systems for Efficiently Predicting and Managing Dengue Fever using Machine Learning Techniques

Main Article Content

Dhanam B, Jesmalar L, Rajeshkannan C, Mythili D, Arumalla Naga Raju, Mihirkumar B. Suthar, Vengatesh T

Abstract

Dengue fever's high frequency and the possibility of catastrophic outbreaks render major worldwide health concerns in tropical and subtropical areas. Existing model for dengue fever prediction and treatment based on their static models and epidemiological surveillance, often fails to capture the intricate interactions among biological, social, and environmental elements. This study examines, recent developments in machine learning (ML) algorithms for precisely predicting and controlling dengue outbreaks. The review process concentrates on several ML models for forecasting dengue risk and incidence. The forecast accuracy is enhanced to integrate a variety of statistics, such as vector indices, population density, and meteorological variables. The deep learning model utilizes geographical and temporal data to surpass existing models. The review process highlights the results of the ML method for predicting outbreaks identifying high-risk areas, and allocating resources for intervention strategies. The findings of the hybrid ML architectures and real-time data attain greater reliability and accuracy.  To enhance model robustness and report points out the gaps in previous research, including the requirement for uniform datasets and socioeconomic elements. This paper paves the way for generating intelligent systems for the proactive management of dengue fever by providing the vital role that ML plays in minimizing the disease's negative effects on public health.

Article Details

Section
Articles