Jul 2026· Archivos Latinoamericanos de Producción Animal· Vol 34, pp. 195-210· 0 citations
Abstract
Precision livestock farming represents a key technological alternative to address the health, production, and environmental challenges of the beef cattle sector. This systematic review analyzes the use of emerging technologies, both hardware and software, focused on cattle health management. The PRISMA methodology and the Parsifal tool were applied to identify, select and evaluate studies published between 2020 and 2025, related to sensors, communication systems, artificial intelligence algorithms and digital platforms. The results show that technologies such as biometric sensors, GPS devices, thermal cameras and IoT communication networks have improved early disease detection, behavioral monitoring and livestock welfare. Likewise, the high performance of artificial intelligence models such as CNN, LSTM, SVM and Random Forest in the prediction of physiological events is highlighted, with efficiencies above 95%. Although significant benefits in efficiency and sustainability are observed, barriers related to technological adoption, connectivity and costs are identified. Finally, the development of scalable and adaptable solutions to diverse rural contexts is proposed as a future line, thus consolidating precision livestock farming as a key model for the sustainability of the livestock sector.
ABSTRACT Background Ensuring animal welfare in extensive sheep production systems remains challenging due to large grazing areas, limited human supervision and the difficulty of detecting early signs of health or behavioural problems. Precision Livestock Farming (PLF) technologies have emerged as promising tools to enhance monitoring and welfare assessment in such environments. Objective This review examines recent advances in PLF technologies and their potential contribution to improving sheep welfare in extensive farming systems. Methods A synthesis of more than 35 peer‐reviewed studies was conducted, focusing on the use of wearable sensors, computer vision, artificial intelligence and environmental monitoring technologies for behavioural and physiological assessment in sheep. Results The reviewed literature indicates that wearable devices, including accelerometers and Global Positioning System (GPS) collars, can achieve up to 85% accuracy in detecting lameness and over 97% accuracy in identifying stress‐related physiological changes. Integration of remote sensing tools, drones and ground‐based sensors also improves monitoring of grazing patterns, social behaviour and environmental conditions. However, adoption remains limited due to economic costs, technical constraints and limited farmer awareness. Conclusions Advances in cost‐effective sensors, standardized welfare indicators and participatory technology design may facilitate wider adoption of PLF tools, supporting improved animal welfare, productivity and sustainability in extensive sheep production systems.
Ikram Ben Souf, C. Darej, Amel Najjar et al.· Veterinary Medicine and Scie...· 0 citations
The increasing global demand for livestock products requires management efficiency that slower, conventional methods cannot meet. This study aims to synthesize the implementation of Internet of Things (IoT) technology for monitoring livestock health and behavior within the Precision Livestock Farming (PLF) framework. The method used is a literature review of 50 relevant scientific articles from 2019 to 2025, focusing on sensor technology, system architecture, applications, benefits, and existing challenges. The synthesis results show that wearable devices with temperature and motion sensors are effective for early disease detection, reproduction optimization, and behavioral analysis. This study confirms the transformative potential of IoT in the livestock industry but also identifies key challenges such as battery life, connectivity in rural areas, and implementation costs. Further research is needed to develop more energy-efficient and affordable solutions to encourage broader adoption.
The global poultry industry faces increasing pressure to improve production efficiency, reduce environmental impacts, and meet stricter animal welfare standards. Conventional manual monitoring methods are increasingly inadequate for addressing the complexities of large-scale commercial poultry production. This systematic review synthesizes current evidence on the effectiveness of smart technologies, including the Internet of Things (IoT), Artificial Intelligence (AI), computer vision, acoustic monitoring, and robotics, in advancing precision poultry farming. Following PRISMA 2020 guidelines, 39 peer-reviewed studies published between 2020 and 2026 were systematically identified, screened, and analyzed using thematic synthesis across five major technological domains. The geographical distribution of research revealed a strong concentration of studies in Asia, highlighting the region's leading role in the development and implementation of smart poultry farming technologies, while also indicating the need for broader geographic representation in future research. Findings revealed that IoT-based environmental monitoring is the most mature technology, with reported accuracies ranging from 93.7% to over 99%. AI-driven disease detection has also advanced rapidly, with YOLO-based models achieving 0.964 precision and more than 90% mean average precision. Acoustic monitoring systems, such as SmartEars, outperformed human veterinary experts under real farm noise conditions, achieving 96.03% accuracy compared with 85–93%. In contrast, robotics and big data integration remain largely in prototype and early-development stages. Despite substantial progress, major barriers to large-scale adoption persist, including limited long-term field validation, inadequate inclusion of smallholder systems, lack of standardized datasets, weak multimodal data integration, and insufficient ethical oversight. Overall, smart poultry technologies demonstrate strong potential to improve precision management, productivity, and animal welfare. Future research should prioritize commercial-scale validation, inclusive technology design, standardized datasets, stronger multimodal integration, and robust ethical and regulatory frameworks to support sustainable adoption in modern poultry systems.
Jopeth Cahanap, Lyn Abalde, Divilyn T. Sambulan et al.· International Journal of Tra...· 0 citations
Livestock production underpins food security, income generation and cultural identity across Africa, yet the sector remains constrained by disease burden, low productivity, weak infrastructure and limited access to modern management tools. Artificial intelligence (AI), encompassing machine learning, computer vision, and Internet of Things (IoT)-enabled sensing, has begun to reshape livestock husbandry in high-income countries and is increasingly being tested and adapted for African production systems, including Nigeria's mixed crop-livestock and pastoral economies. This review synthesises the peer-reviewed literature on AI applications across animal health diagnostics, disease surveillance, poultry monitoring, dairy and cattle management, genomic selection, feed optimisation and climate-resilience planning, with particular attention to Nigerian case studies and the wider sub-Saharan African context. The review finds that AI tools have demonstrated technical feasibility for disease detection, individual animal identification, oestrus monitoring, and methane emission prediction, and that mobile-phone-based advisory platforms have delivered measurable productivity gains in East African dairy systems. However, adoption in Nigeria and across much of the continent remains constrained by fragmented connectivity, high hardware costs, scarce training data representative of indigenous breeds and agro-ecologies, low digital literacy among smallholders, and underdeveloped data governance frameworks. The review argues that the translation of AI from proof-of-concept studies to routine farm practice depends on locally trained models, affordable low-bandwidth solutions, gender-responsive design, and coordinated policy support, rather than the direct transplantation of technologies developed for intensive, capital-rich systems elsewhere. The paper concludes with directions for future research and practice that could narrow the gap between the technical promise of AI and its realised benefit for African livestock keepers.
A. Ayandiji, Y. Ajibade· Asian Journal of Agricultura...· 1 citation
This paper proposes Livestock IoT (LIoT), a five-layer Software Ecosystem (SECO) to improve precision livestock farming that utilizes IoT sensors, TinyML-based on-device inference, LoRa long-range communication, and a cloud layer to analyze data and provide continuous monitoring of cattle body temperature, heart rate, movements, and voice sounds. The designed neck-wearable node, based on the ESP32-S3 microcontroller, is capable of local inference using a TinyML health classifier model that has achieved around 75% accuracy in field trials. The extracted alerts and health status updates are delivered through a LoRa gateway to farm management dashboards, improving veterinary monitoring and facilitating farmers’ decisions. The proposed architecture is also envisioned with federated learning for decentralized model updates and blockchain for secure and tamper-proof log recording as future working directions. The system effectiveness was demonstrated in rural environments where LoRa connectivity was achieved at distances up to 2 km and the gateway operated continuously for the full 14-day trial without recharging. LIoT offers a low-cost, scalable approach to improving the efficiency, sustainability, and animal welfare of livestock farming in the Agriculture 4.0 era.
How smart sensors, satellite and aerial imaging platforms and cloud-based data infrastructures play a vital role in the development of crop health monitoring and predictive analytics is discussed, including the heterogeneity of data, false positives, and the interpretability of the AI models.
