Analyzing and minimizing the effects of Vector-borne diseases using machine and deep learning techniques : A systematic review

Abstract

Among the numerous threats facing our world, Vector-borne illnesses pose the greatest threat. Although arboviruses have a long history of infecting humans, they have recently become more widespread and are affecting larger populations. This is due to a number of reasons, including increased air travel and uncontrollable mosquito vector populations. To halt the spread of fatal infectious diseases epidemics, machine learning and neural networks may be employed. Numerous studies omitted discussing the algorithms, data, and performance measures used in applications for predicting and detecting deadly infectious illnesses. To counteract the development of deadly disease epidemics, this article summarizes studies on two major methods (prediction and detection). This research will examine the current advances, difficulties, and future possibilities for utilizing machine and deep learning to identify and forecast fatal disease outbreaks in order to reduce the risk of spreading illness. This study examines previous studies, methodologies, datasets, variables, and performance metrics.