Classification of Lumpy Skin Disease using Principal Component Analysis PCA based Supervised Machine Learning

A viral illness, lumpy skin in cattle is spread by mosquitoes and other insects that feed on human blood. Animals that have never been exposed to the virus are mostly affected by the sickness. Milk, meat, and domestic and international livestock commerce are all impacted by cattle lumpy skin disease. Traditional lumpy skin disease diagnosis is exceedingly time consuming, complicated, and resource constrained. As a consequence, it is essential to use deep learning algorithms that can categorize the condition with excellent performance outcomes. In order to segment and classify diseases using deep features, deep learning based segmentation and classification are suggested. Convolutional neural networks with 10 layers have been selected for this. The created framework is first trained using data gathered from cattle with Cattles Lumpy Skin Disease CLSD . The skin tone is crucial to identifying the damaged region when a disease is represented since the characteristics are derived from the input photographs. To do this, a color histogram was utilized. A deep pre trained CNN uses this divided region of altered skin color to extract features. Next, a threshold is used to transform the produced result into a binary format. The classifier for classification is PCA Driven Supervised Machine Learning. The suggested methodologys classification performance has a 96 CLSD accuracy rate. We give a comparison with cutting edge methodologies to demonstrate the efficacy of the suggested strategies. Rajesh Kumar | Dr. Sneha Soni "Classification of Lumpy Skin Disease using Principal Component Analysis (PCA)-based Supervised Machine Learning" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-8 | Issue-3 , June 2024, URL: https://www.ijtsrd.com/papers/ijtsrd64954.pdf Paper Url: https://www.ijtsrd.com/computer-science/other/64954/classification-of-lumpy-skin-disease-using-principal-component-analysis-pcabased-supervised-machine-learning/rajesh-kumar