Machine Learning Based Diagnosis of Lumpy Skin Disease

Lumpy skin disease is a transmissible virus contracted by cattle that has led to concern among the nations. It has a direct relation with climate as the latter plays a major role in studying the infection and the pattern of transmission followed by it. This study depicts how the various climatic factors help in determining whether the cattle in the specific region or a country has the lumpy skin disease or not by using machine learning algorithms. Machine learning algorithms employed in the present study predicted lumpy disease with accuracy and F1 score of 100% and 1.0, respectively. In the present study, four different machine learning algorithms: Adaboost, K-nearest neighbors, decision tree and random forest are employed. The present research suggests that the decision trees can be used to predict lumpy skin disease infection using the geospatial and climatic parameters. The predicting power of machine learning algorithms can help in monitoring the disease spread patterns. It will also help in the application of vaccine campaigns in regions where the spread of disease poses a great risk to health.