Evaluating Machine Learning Models for Optimal Livestock Environment Prediction in Smart Farming Applications to Enhance Food Security Academic Article uri icon

abstract

  • Livestock is a vital protein source for the global population, and any supply disruptions can significantly threaten national food security. Therefore, ensuring a stable and continuous livestock supply is essential. Previous studies have highlighted a strong link between livestock production and environmental factors and proposed several smart farming solutions to be adopted to monitor and optimize livestock production effectively. In this study, we propose adopting sensor technology and machine learning to establish optimal environmental conditions for livestock in Malaysia. Machine-learning techniques are evaluated to determine the most effective model for enhancing livestock production in smart farming systems. This research simulates the livestock living environment equipped with sensors and selected parameters for data collection to train the machine learning chosen models: Decision Tree, Naïve Bayes, and K-Nearest Neighbors. The trained machine learning models are then applied to predict the optimum environment for livestock using the dataset of the simulated environment. Then, performance evaluation on the machine learning models was carried out. The accuracy results for Decision Tree, Naïve Bayes, and K-Nearest Neighbors are 99%, 63%, and 89%, respectively. The research shows that the Decision Tree model is the best-performing model at predicting the optimum environment for livestock. These findings provide invaluable insight to advance research on optimum livestock environment prediction in smart farming for the Malaysia use case. They will enable precise adjustments and monitoring to achieve ideal conditions for livestock growth to provide consistent livestock production.

publication date

  • 2025

number of pages

  • 7

start page

  • 36

end page

  • 43

volume

  • 15

issue

  • 1