Evaluating machine learning methods voting system for predicting the occurrence of lumpy skin condition

Abstract

Lumpy skin disease is a viral disease that primarily affects cattle. It is caused by the lumpy skin disease, which belongs to the Capripoxvirus genus. LSD is characterized by the formation of nodules or lumps on the skin of infected cattle. This study aimed to evaluate how well some machine learning algorithms could predict the likelihood of LSDV infection based on geographical and meteorological characteristics. Geospatial and climatic factors are crucial to the disease’s epidemiology because of their close connection to the persistence of arthropod vectors. The results of this study suggest that by combining geographical and meteorological factors, a voting system of different machine learning outputs is utilized to forecast the occurrence of LSDV infection with high precision. In locations where there is a high risk of LSDV infection, applying the predicting capability of these methodologies could be very helpful in implementing screening and awareness programs as well as preventative efforts like vaccination