IoT-Enabled Environmental Monitoring System for Improving Animal Welfare in Smart Barns

Abstract

Smart livestock farming has become a critical solution to enhancing the welfare of animals, the agriculture productivity, and the sustainable management of agriculture using intelligent sensing and automation technologies. Factors in environmental settings of barns, such as temperatures, humidity, ammonia levels, carbon dioxide levels, lights, and the quality of ventilation, have a great impact on animal health, the level of animal stress, and the overall livestock productivity. The conventional methods of monitoring the welfare in barns are based on manual check-up and regular check-up of the environment condition, which is not effective in monitoring the welfare continuously and identifying stress at the earliest stage. This study aims to solve these problems by introducing an IoT-based environmental monitoring in better animal welfare in smart barns through intelligent integration of sensors and a classification system based on Random Forest. The suggested system constantly measures key parameters of the environment with a network of IoT sensors and processes the measured data with machine learning algorithms to categorize the status of the barns as comfortable, mild stress, severe stress, and unsafe environment. Random Forest algorithm is used because of its strength, capacity to classify and its ability to use multi-parameter environmental data. Core metrics such as accuracy, precision, recall and F1-score are used to measure the performance of the proposed framework to determine welfare classification effectiveness and prediction reliability. The experimental analysis shows the developed system is effective in identifying poor barn conditions, enhancing the ability to monitor environmental conditions in real-time, and proactive livestock management approaches. The suggested framework helps to achieve sustainable livestock production by alleviating animal stress, increasing the effectiveness of environmental control, reducing the need of human involvement, and allowing smart welfare-centric smart barn control to achieve next-generation precision livestock production.