Answers are grounded in this paper and cite their sources.
Background: The detection and prevention of diseases in livestock, particularly among cows, are of the greatest to ensure animal welfare, minimize economic losses, and uphold food safety standards. Conventional methods for identifying cow diseases rely on visual assessments conducted by experienced veterinarians. However, these methods are time-consuming, subjective, and error-prone. Method: In recent years, the application of machine learning (ML) algorithms has shown considerable promise in automating the detection of cow diseases using various sources of data. In this study, we present an investigation into the utilization of ML classifiers for cow disease detection. Our dataset consists of information from 6600 cattle, centered around sensory parameters obtained through cost-effective sensors as well as prevalence data for mastitis. We conducted training and evaluation of multiple ML classifiers, including Random Forest (RF), Support Vector Machine (SVM), k Nearest Neighbors (kNN), Decision Tree (DT), and Naïve Bayes (NB), using the dataset to determine the most effective technique for cow disease identification. Result: Our experimental findings reveal that kNN achieved an impressive accuracy of 99.46% in detecting common cow mastitis disease, closely followed by RF with an accuracy of 99.1%. We performed an in-depth analysis of the classification outcomes, exploring the strengths and limitations of each classifier in terms of sensitivity, specificity, and likelihood ratio. Conclusion: Overall, our study underscores the potential of ML classifiers in achieving precise and efficient classification of both healthy and unhealthy cows. This advancement could prove beneficial to farmers, veterinarians, and stakeholders within the livestock industry.
No takes yet. Share an insight, caveat, or question.
Kuma et al. (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: