Scholarlink

The health of animals and agricultural productivity can be greatly impacted by cattle diseases. For timely interventions and to stop these diseases from spreading throughout the herd, early detection and prognosis are crucial in rural communities across Somalia. In this study, the use of machine learning models to predict cattle diseases based on pertinent parameters was investigated. These parameters encompass kids of lesions Blister, Ulcer and Scab, a collection of 31,000 rows of datasets, each labeled with the presence or absence of disease, was gathered from various cattle herds. The main objective was to evaluate the effectiveness of five popular machine learning models: Random Forest, Logistic Regression K-Nearest Neighbors, Decision Tree, support vector machine (SVM) random forest and Naïve Bayes multinomial (NBM). The results demonstrated that random forest RF consistently outperformed the other models, having the highest accuracy in terms of disease prediction in cattle. On the test dataset, the RF model had an accuracy rate of 99%. Its ability to manage complex connections between input characteristics and reduce overfitting through ensemble learning is responsible for this accomplishment. These revelations can provide important details regarding the risk factors and early warning signs of a variety of livestock diseases.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Leveraging Supervised Learning Algorithms for Automated and Accurate Cattle Disease Diagnosis in Livestock Farming in Somalia

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Zakaria Mohamed Nur,
  • Ali Hussein Hassan,
  • Abdullahi Mukhtar Mohamed,
  • Usama Mahamud Ibrahim,
  • Mohamed Abdullahi Ali,
  • Abdulaziz Ahmed Siyad

摘要

The health of animals and agricultural productivity can be greatly impacted by cattle diseases. For timely interventions and to stop these diseases from spreading throughout the herd, early detection and prognosis are crucial in rural communities across Somalia. In this study, the use of machine learning models to predict cattle diseases based on pertinent parameters was investigated. These parameters encompass kids of lesions Blister, Ulcer and Scab, a collection of 31,000 rows of datasets, each labeled with the presence or absence of disease, was gathered from various cattle herds. The main objective was to evaluate the effectiveness of five popular machine learning models: Random Forest, Logistic Regression K-Nearest Neighbors, Decision Tree, support vector machine (SVM) random forest and Naïve Bayes multinomial (NBM). The results demonstrated that random forest RF consistently outperformed the other models, having the highest accuracy in terms of disease prediction in cattle. On the test dataset, the RF model had an accuracy rate of 99%. Its ability to manage complex connections between input characteristics and reduce overfitting through ensemble learning is responsible for this accomplishment. These revelations can provide important details regarding the risk factors and early warning signs of a variety of livestock diseases.