Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193762,
        author = {A R Kishore Kumar and I. Kavya and U.  Dilshad and K. Dhanush Kumar and M. Bharath},
        title = {Machine Learning-Based Detection Of Lumpy Skin Disease In Cattle Using Deep Feature Extraction Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {1399-1407},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193762},
        abstract = {Lumpy skin disease (LSD) is a viral disease that infects cattle at a very high rate and was initially discovered in Africa. It is spreading now through the Middle East, Asia, and even into Eastern Europe and this is of great concern as its prevalence rate is growing and it is also affecting the livestock industry economically. Symptoms of the disease include fever, excessive drooling, excessive tearing, swollen lymph nodes, and the formation of nodules in the skin which is firm. PCR testing, virus isolation, and histopathological analysis are the most common diagnostic methods that are used to detect the disease; these methods may be time-consuming, expensive, and may also need laboratory facilities. Cattle are prone to numerous diseases and LSD thus requires early and precise diagnosis in order to curb the continuous spread and loss. Neethling virus causes the disease and this may cause permanent damage of the skin, infertility, retarded growth, miscarriages, low milk output and death in extreme cases. In order to overcome these challenges, the research that follows suggests an automated disease detection strategy based on deep learning models like the VGG-16, VGG-19, and Inception-V3 (effective on feature extraction) along with machine learning classifiers (good at disease detection). Throughout experimental results, it is established that the proposed method has higher feature extraction and classification scores as compared to conventional algorithms, including KNN, SVM, Naive Bayes, ANN, and Logistic Regression, and as such has potential to be applied to real-time and field-level disease monitoring.},
        keywords = {VGG16, VGG19, Inception V3, Image classification, Machine learning, Deep learning},
        month = {March},
        }