Next-Gen Agriculture: Enhancing Animal Welfare Through IoT, Edge Devices, and Artificial Intelligence

Abstract

Agriculture has always been a field of innovation, evolving alongside technological advancements to boost productivity and address sector-specific challenges. Today, the Internet of Things (IoT), edge computing, and artificial intelligence (AI) are revolutionizing farming practices, particularly in livestock management. These technologies enable real-time monitoring of animal health, facilitate early disease detection, and optimize decision-making. Beyond immediate benefits, they contribute to more sustainable agriculture and improved animal welfare, issues of growing concern to consumers. However, adoption faces several hurdles, notably regarding cost, data management, and connectivity. Solutions are emerging to overcome these challenges, such as advanced technology integration, remote sensing, and improved digital infrastructure. In this article, we propose a hybrid Edge-Fog-Cloud architecture for the intelligent monitoring of animal welfare, based on a simulation using synthetic data (100,000 observations covering 100 simulated animals). In addition to standard classification metrics (accuracy, precision, recall, F1-score), the article presents a comprehensive factorial ablation study to determine the marginal contribution of each method, as well as indicators related to event-level detection (detection delay, alert fragmentation, false alert rate) and model performance in terms of resource usage and latency; the aim is to highlight the advantages of the proposed architecture and justify it with quantified, reproducible evidence, rather than relying solely on aggregate accuracy figures. The results presented here constitute a proof of concept based on simulated data, not a demonstration of agricultural performance under real-world conditions with live animals.