Diagnosing Lumpy Skin Disease: A Comparative Analysis of Machine Learning Algorithms
Mibah Daud, Department of Computer Science, Shaheed Benazir Bhutto Women University, Peshawar, Pakistan.
Lala Rukh, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Muhammad Omair Khan, Department of Computer Science, Islamia College Peshawar, Pakistan.
Muahammad Abdullah, Department of Computer Science, Islamia College Peshawar, Pakistan.
Corresponding Author:
Mibah Daud (misbahdaud@gmail.com)
Abstract:
Lumpy Skin Disease (LSD) is a viral disease in cattles caused by the well-known Capripoxvirus, a member of the Poxviridae family. The major symptoms of the LSD is characterized by fever, appearance of nodules on the cattle skin, and presence of swelling on various parts of the body, including the neck, head, and genitalia. Diagnosing the LSD in cattle has been an issue and various research works have been done in the past. The focus of this research is to diagnose the LSD using the well-known machine learning models i.e. Support Vector Machine, Random Forest Classifier, Naïve Bayees Classifier, Decision Tree Classifier and CNN. The results show that Support Vector Machine achieves 87%, Random Forest Classifier 96%, Naïve Bayees Classifier gains 89%, Decision Tree Classifier achieves 96% while CNN results 93% accuracy. The detailed comparison shows that SVM and Decision Tree Classifier achieves higher accuracy in diagnosing the LSD in cattles
Keywords:
Lumpy Skin Disease (LSD); Image Processing, SVM, Random Forest Classifier, Decision Tree Classifier