Search Results (172)

Understanding the relationship between environmental variables and gas concentrations from livestock production is essential for evaluating the impact of pollutants on animal housing and surrounding areas. This study investigates the use of ANNs to predict NH₃ concentrations in a Mediterranean dairy barn under seasonal conditions—namely, hot, cold, and transitional weather. A Multi-Layer Perceptron (MLP) structure was employed, trained using Levenberg–Marquardt and Bayesian Regularization algorithms. The input dataset included ten variables related to internal and external environmental conditions, NH₃ concentrations, and time of day. The models were evaluated using R², R, MAE, MSE, and RMSE as performance metrics. Results showed strong predictive capabilities, with R² values ranging from 0.75 to 0.96 and RMSE values between 0.47 and 0.80 due to the number of input data (different days) and environmental conditions. These findings highlight the potential of ANNs as effective tools for real-time pollutant prediction, supporting Precision Livestock Farming (PLF) strategies. Full article

This study evaluated six supervised machine learning (ML) models for early detection of subclinical ketosis and low-grade ruminal acidosis in dairy cows during the transition period. Ninety-four Holstein cows were monitored for 21 days postpartum using in-line milk analyzers and intraruminal sensors that continuously recorded milk composition, behavioral, and physiological parameters. Based on clinical examination, blood β-hydroxybutyrate concentration, and fat-to-protein ratio, cows were classified as healthy (n = 44), subclinical ketosis (n = 24), or subclinical acidosis (n = 26). Among the tested models, Random Forest and XGBoost achieved perfect accuracy within this dataset, while Logistic Regression reached 89.5%, Decision Tree 84.2%, and both Naive Bayes and Support Vector Machine 78.9%. These results suggest that ensemble approaches, particularly Random Forest and XGBoost, show strong potential for integration with precision livestock technologies, but their apparent performance should be interpreted cautiously and confirmed in larger, multi-farm studies. Full article

Heat stress has a major impact on dairy cow health and productivity, especially during early lactation. Conventional heat stress monitoring methods frequently rely on single indicators, such as the temperature–humidity index (THI), which may miss subtle physiological and metabolic responses. This study presents a novel threshold-based classification framework that integrates biologically meaningful combinations of environmental, behavioural, and physiological variables to detect early-stage heat stress responses in dairy cows. Six composite heat stress conditions (C1–C6) were developed using real-time THI, milk temperature, reticulorumen pH, rumination time, milk lactose, and milk fat-to-protein ratio. The study applied and assessed five supervised machine learning models (Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machine (SVM), Random Forest (RF0, Neural Network (NN), and an Ensemble approach) trained on daily datasets gathered from early-lactation dairy cows fitted with intraruminal boluses and monitored through milking parlour sensor systems. The dataset comprised approximately 36,000 matched records from 200 cows monitored over 60 days. The highest classification performance was observed for RF and NN models, particularly under C1 (THI > 73 and milk temperature > 38.6 °C) and C6 (THI > 74 and milk temperature > 38.7 °C), with AUC values exceeding 0.90. SHAP analysis revealed that milk temperature, THI, rumination time, and milk lactose were the most informative features across conditions. This integrative approach enhances precision livestock monitoring by enabling individualised heat stress risk classification well before clinical or production-level consequences emerge. Full article

Paratuberculosis or Johne’s disease is caused by Mycobacterium avium subsp. paratuberculosis (MAP). The disease is characterized by a chronic and incurable enteritis in ruminants and it is responsible for significant economic losses, also raising concerns about food safety and animal welfare. Effective control is hindered by diagnostic limitations, long incubation periods, and the environmental resistance of the pathogen. This study aimed to reduce the apparent prevalence of paratuberculosis in a single intensive dairy herd through an integrated approach that combines diagnostics and management strategies. All cows over 24 months of age were tested using both fecal PCR and ELISA serology. Digital PCR (dPCR) was used to quantify MAP shedding in fecal-positive animals, enabling prioritization for removal based on environmental contamination risk. Integrating diagnostic tools allowed the precise identification and quantification of high-risk animals. Meanwhile, structural improvements and biosecurity measures were implemented on the farm. Preliminary outcomes suggest a marked reduction in herd-level MAP prevalence, lowering the seroprevalence from 7.6% to 4.5% and the fecal PCR prevalence from 6.5% to 2.8%. This case highlights the effectiveness of combining laboratory testing (serology and molecular diagnostics) and targeted changes in farm management to control paratuberculosis in high-density dairy systems. Full article

Feeding a balanced diet such as total mixed ration (TMR) is a widely adopted feeding strategy providing a uniformly blended diet of roughages, concentrates, and supplements that enhances ruminant productivity by optimizing nutrient utilization, stabilizing rumen fermentation, and improving microbial activity. Scientific studies have confirmed that TMR increases dry matter intake (DMI), milk yield, and growth performance in dairy and beef cattle, as well as in sheep and goats. TMR’s advantages include consistent feed quality, reduced selective feeding, and improved feed efficiency. A key benefit of TMR is its ability to promote the production of volatile fatty acids (VFAs), which are the primary energy source for ruminants, particularly propionate. This enhances energy metabolism, resulting in higher carcass yields, increased milk production, and economic benefits compared to conventional or supplementary feeding systems. However, TMR feeding is also susceptible to mycotoxin contamination (e.g., aflatoxins, zearalenone), potential effects on methane emissions, and the need for precise formulation to maintain consistency and optimise profitability. Prevention and good practices, including routine inspection of feed for pathogens and vulnerable ingredients, as well as careful management of particle size and forage-to-concentrate ratios, are crucial in preventing subacute ruminal acidosis (SARA) and the development of other subclinical diseases. Mycotoxin binders, such as hydrated sodium calcium aluminosilicate, can also reduce mycotoxin absorption. Another advantage of practicing TMR is that it can support sustainable farming by integrating agro-industrial byproducts, which minimises environmental impact. In conclusion, TMR is a widely adopted feeding strategy that significantly enhances ruminant productivity by optimizing nutrient utilization, stabilizing rumen fermentation, and improving microbial activity, leading to increased dry matter intake, milk yield, and growth performance. It offers key benefits such as consistent feed quality, reduced selective feeding, improved feed efficiency, and enhanced energy metabolism, providing economic advantages and supporting sustainable farming through agro-industrial byproduct integration. However, its implementation requires careful management to mitigate risks, including mycotoxin contamination, potential impacts on methane emissions, and digestive issues like SARA if formulation is not precise. Therefore, for sustainable production, future research should focus on optimizing TMR formulations with alternative ingredients (e.g., agro-industrial byproducts) and precision feeding strategies to enhance livestock health and animal productivity while minimizing environmental impacts. Full article

In real-world dairy farming environments, object recognition models often suffer from missed or false detections due to complex backgrounds and cow occlusions. In response to these issues, this paper proposes FSCA-YOLO, a multi-object cow behavior recognition model based on an improved YOLOv11 framework. First, the FEM-SCAM module is introduced along with the CoordAtt mechanism to enable the model to better focus on effective behavioral features of cows while suppressing irrelevant background information. Second, a small object detection head is added to enhance the model’s ability to recognize cow behaviors occurring at the distant regions of the camera’s field of view. Finally, the original loss function is replaced with the SIoU loss function to improve recognition accuracy and accelerate model convergence. Experimental results show that compared with mainstream object detection models, the improved YOLOv11 in this section demonstrates superior performance in terms of precision, recall, and mean average precision (mAP), achieving 95.7% precision, 92.1% recall, and 94.5% mAP—an improvement of 1.6%, 1.8%, and 2.1%, respectively, over the baseline YOLOv11 model. FSCA-YOLO can accurately extract cow features in real farming environments, providing a reliable vision-based solution for cow behavior recognition. To support specific behavior recognition and in-region counting needs in multi-object cow behavior recognition and tracking systems, OpenCV is integrated with the recognition model, enabling users to meet the diverse behavior identification requirements in groups of cows and improving the model’s adaptability and practical utility. Full article

The feeding behavior of dairy cows constitutes a complex temporal sequence comprising actions such as head lowering, sniffing, arching, eating, head raising, and chewing. Its precise recognition is crucial for refined livestock management. While existing 2D convolution-based models effectively extract features from individual frames, they lack temporal modeling capabilities. Conversely, due to their high computational complexity, 3D convolutional networks suffer from significantly limited recognition accuracy in high-density feeding scenarios. To address this, this paper proposes a Spatio-Temporal Fusion Network (DAS-Net): it designs a collaborative architecture featuring a 2D branch with a triple-attention module to enhance spatial key feature extraction, constructs a 3D branch based on multi-branch dilated convolution and integrates a 3D multi-scale attention mechanism to achieve efficient long-term temporal modeling. On our Spatio-Temporal Dairy Feeding Dataset (STDF Dataset), which contains 403 video clips and 10,478 annotated frames across seven behavior categories, the model achieves an average recognition accuracy of 56.83% for all action types. This result marks a significant improvement of 3.61 percentage points over the original model. Among them, the recognition accuracy of the eating action has been increased to 94.78%. This method provides a new idea for recognizing dairy cow feeding behavior and can provide technical support for developing intelligent feeding systems in real dairy farms. Full article

Neonatal calf diarrhea (NCD) remains one of the most prevalent and economically burdensome health challenges in preweaned calves, leading to compromised growth, increased morbidity, and high mortality rates worldwide. While traditional methods such as physical examination and clinical health scoring are widely used, they often require trained personnel, are resource-intensive, and are prone to subjectivity, which limits their scalability in large dairy operations. This observational cohort study investigated the feasibility of using suckle pressure measurement combined with machine learning (ML) techniques for NCD detection. A total of 51 female Holstein calves on a commercial dairy farm were enrolled at birth and health scored daily from 1 to 21 days of age. Suckle pressures were measured at 1, 3, 5, 7, 10, 14, and 21 days, as well as daily following NCD diagnosis until fecal consistency returned to normal. Pressure measurements were captured using impression film-wrapped nipples, producing 349 images, of which 54 were from calves diagnosed with NCD. Image features, including pixel density, color saturation, entropy, and histogram-based features, were extracted for analysis. Multiple ML classifiers—Support Vector Machine, K-Nearest Neighbors, Random Forest, Gradient Boosting, and Easy Ensemble (EE)—were applied to detect NCD status based on image features. The EE classifier achieved the best detection performance, with an accuracy of 0.90, precision of 0.64, and recall of 0.82, effectively handling data imbalance. Notably, the results also demonstrated that NCD onset could be predicted up to one day prior to clinical manifestation by training classifiers on pre-symptomatic suckle pressure data and testing on post-onset data. The EE classifier also outperformed other models in this early prediction window, with an accuracy of 0.74, precision of 0.67, and recall of 0.70. The results of our preliminary study suggest that suckle pressure may offer a novel, non-invasive approach for precision health monitoring in dairy systems, enabling timely intervention to reduce disease severity, improve calf health, and minimize economic losses. Full article

Computer vision is rapidly transforming the field of dairy farm management by enabling automated, non-invasive monitoring of animal health, behavior, and productivity. This review provides a comprehensive overview of recent applications of computer vision in dairy farming management operations, including cattle identification and tracking, and consequently the assessment of feeding and rumination behavior, body condition score, lameness and lying behavior, mastitis and milk yield, and social behavior and oestrus. By synthesizing findings from recent studies, we highlight how computer vision systems contribute to improving animal welfare and enhancing productivity and reproductive performance. The paper also discusses current technological limitations, such as variability in environmental conditions and data integration challenges, as well as opportunities for future development, particularly through the integration of artificial intelligence and machine learning. This review aims to guide researchers and practitioners toward more effective adoption of vision-based technologies in precision livestock farming. Full article

This study aimed to evaluate the accuracy of the accelerometer-equipped collar RUMI to detect estrus in dairy cows, establish a recommendation for the optimal timing for artificial insemination (AI) when using this device, and characterize the blood flow of the dominant follicle (F) and the corpus luteum (CL) as ovulation approaches. Forty-seven cycling cows were monitored following synchronization with a modified G6G protocol, allowing for spontaneous ovulation. Ultrasound examinations were conducted every 12 h, starting 48 h after the second PGF2α dose, to monitor uterine and ovarian changes. Blood samples were also collected to determine serum progesterone (P4) levels. Each cow was fitted with a RUMI collar, which continuously monitored behavioral changes to identify the onset, offset, and peak of activity of estrus. One-way ANOVA assessed the relationship between physiological parameters and time before ovulation. Results showed that the RUMI collar demonstrated high specificity (100%), sensitivity (90.90%), and accuracy (93.62%) for estrus detection. The optimal AI window was identified as between 11.4 and 15.5 h after heat onset. Increased blood flow to the F and reduced luteal activity were observed in the 48 h prior to ovulation. Further research is needed to assess the influence of this AI window on conception rates, and if it should be modified considering external factors. Full article

Timely, objective pain recognition in dairy cattle is essential for welfare assurance, productivity, and ethical husbandry yet remains elusive because evolutionary pressure renders bovine distress signals brief and inconspicuous. Without verbal self-reporting, cows suppress overt cues, so automated vision is indispensable for on-farm triage. Although earlier systems tracked whole-body posture or static grimace scales, frame-level detection of facial micro-expressions has not been explored fully in livestock. We translate micro-expression analytics from automotive driver monitoring to the barn, linking modern computer vision with veterinary ethology. Our two-stage pipeline first detects faces and 30 landmarks using a custom You Only Look Once (YOLO) version 8-Pose network, achieving a 96.9% mean average precision ($mAP$) at an Intersection over the Union (IoU) threshold of 0.50 for detection and 83.8% Object Keypoint Similarity (OKS) for keypoint placement. Cropped eye, ear, and muzzle patches are encoded using a pretrained MobileNetV2, generating 3840-dimensional descriptors that capture millisecond muscle twitches. Sequences of five consecutive frames are fed into a 128-unit Long Short-Term Memory (LSTM) classifier that outputs pain probabilities. On a held-out validation set of 1700 frames, the system records 99.65% accuracy and an F1-score of 0.997, with only three false positives and three false negatives. Tested on 14 unseen barn videos, it attains 64.3% clip-level accuracy (i.e., overall accuracy for the whole video clip) and 83% precision for the pain class, using a hybrid aggregation rule that combines a 30% mean probability threshold with micro-burst counting to temper false alarms. As an early exploration from our proof-of-concept study on a subset of our custom dairy farm datasets, these results show that micro-expression mining can deliver scalable, non-invasive pain surveillance across variations in illumination, camera angle, background, and individual morphology. Future work will explore attention-based temporal pooling, curriculum learning for variable window lengths, domain-adaptive fine-tuning, and multimodal fusion with accelerometry on the complete datasets to elevate the performance toward clinical deployment. Full article

Digital livestock farming faces a critical deployment challenge: bridging the gap between cutting-edge AI algorithms and practical implementation in resource-constrained agricultural environments. While deep learning models demonstrate exceptional accuracy in laboratory settings, their translation to operational farm systems remains limited by computational constraints, connectivity issues, and user accessibility barriers. Dairy DigiD addresses these challenges through a novel edge-cloud AI framework integrating YOLOv11 object detection with DenseNet121 physiological classification for cattle monitoring. The system employs YOLOv11-nano architecture optimized through INT8 quantization (achieving 73% model compression with <1% accuracy degradation) and TensorRT acceleration, enabling 24 FPS real-time inference on NVIDIA Jetson edge devices while maintaining 94.2% classification accuracy. Our key innovation lies in intelligent confidence-based offloading: routine detections execute locally at the edge, while ambiguous cases trigger cloud processing for enhanced accuracy. An entropy-based active learning pipeline using Roboflow reduces the annotation overhead by 65% while preserving 97% of the model performance. The Gradio interface democratizes system access, reducing technician training requirements by 84%. Comprehensive validation across ten commercial dairy farms in Atlantic Canada demonstrates robust performance under diverse environmental conditions (seasonal, lighting, weather variations). The framework achieves mAP@50 of 0.947 with balanced precision-recall across four physiological classes, while consuming 18% less energy than baseline implementations through attention-based optimization. Rather than proposing novel algorithms, this work contributes a systems-level integration methodology that transforms research-grade AI into deployable agricultural solutions. Our open-source framework provides a replicable blueprint for precision livestock farming adoption, addressing practical barriers that have historically limited AI deployment in agricultural settings. Full article

With the development of precision livestock farming, in order to achieve the goal of fine management and improve the health and welfare of dairy cows, research on dairy cow motion monitoring has become particularly important. In this study, considering the problems surrounding a large amount of model parameters, the poor accuracy of multi-target tracking, and the nonlinear motion of dairy cows in dairy farming scenes, a lightweight detection model based on improved YOLO v11n was proposed and four tracking algorithms were compared. Firstly, the Ghost module was used to replace the standard convolutions in the YOLO v11n network and a more lightweight attention mechanism called ELA was replaced, which reduced the number of model parameters by 18.59%. Then, a loss function called SDIoU was used to solve the influence of different cow target sizes. With the above improvements, the improved model achieved an increase of 2.0 percentage points and 2.3 percentage points in mAP@75 and mAP@50-95, respectively. Secondly, the performance of four tracking algorithms, including ByteTrack, BoT-SORT, OC-SORT, and BoostTrack, was systematically compared. The results show that 97.02% MOTA and 89.81% HOTA could be achieved when combined with the OC-SORT tracking algorithm. Considering the demand of equipment in lightweight models, the improved object detection model in this paper reduces the number of model parameters while offering better performance. The OC-SORT tracking algorithm enables the tracking and localization of cows through video surveillance alone, creating the necessary conditions for the continuous monitoring of cows. Full article

This review synthesizes advances in livestock genomics by examining the interplay between candidate genes, molecular markers (MMs), signatures of selection (SSs), and quantitative trait loci (QTLs) in shaping economically vital traits across livestock species. By integrating advances in genomics, bioinformatics, and precision breeding, the study elucidates genetic mechanisms underlying productivity, reproduction, meat quality, milk yield, fibre characteristics, disease resistance, and climate resilience traits pivotal to meeting the projected 70% surge in global animal product demand by 2050. A critical synthesis of 1455 peer-reviewed studies reveals that targeted genetic markers (e.g., SNPs, Indels) and QTL regions (e.g., IGF2 for muscle development, DGAT1 for milk composition) enable precise selection for superior phenotypes. SSs, identified through genome-wide scans and haplotype-based analyses, provide insights into domestication history, adaptive evolution, and breed-specific traits, such as heat tolerance in tropical cattle or parasite resistance in sheep. Functional candidate genes, including leptin (LEP) for feed efficiency and myostatin (MSTN) for double-muscling, are highlighted as drivers of genetic gain in breeding programs. The review underscores the transformative role of high-throughput sequencing, genome-wide association studies (GWASs), and CRISPR-based editing in accelerating trait discovery and validation. However, challenges persist, such as gene interactions, genotype–environment interactions, and ethical concerns over genetic diversity loss. By advocating for a multidisciplinary framework that merges genomic data with phenomics, metabolomics, and advanced biostatistics, this work serves as a guide for researchers, breeders, and policymakers. For example, incorporating DGAT1 markers into dairy cattle programs could elevate milk fat content by 15-20%, directly improving farm profitability. The current analysis underscores the need to harmonize high-yield breeding with ethical practices, such as conserving heat-tolerant cattle breeds, like Sahiwal. Full article

Sensor-enabled digital twins (DTs) are reshaping precision dairy nutrition by seamlessly integrating real-time barn telemetry with advanced biophysical simulations in the cloud. Drawing insights from 122 peer-reviewed studies spanning 2010–2025, this systematic review reveals how DT architectures for dairy cattle are conceptualized, validated, and deployed. We introduce a novel five-dimensional classification framework—spanning application domain, modeling paradigms, computational topology, validation protocols, and implementation maturity—to provide a coherent comparative lens across diverse DT implementations. Hybrid edge–cloud architectures emerge as optimal solutions, with lightweight CNN-LSTM models embedded in collar or rumen-bolus microcontrollers achieving over 90% accuracy in recognizing feeding and rumination behaviors. Simultaneously, remote cloud systems harness mechanistic fermentation simulations and multi-objective genetic algorithms to optimize feed composition, minimize greenhouse gas emissions, and balance amino acid nutrition. Field-tested prototypes indicate significant agronomic benefits, including 15–20% enhancements in feed conversion efficiency and water use reductions of up to 40%. Nevertheless, critical challenges remain: effectively fusing heterogeneous sensor data amid high barn noise, ensuring millisecond-level synchronization across unreliable rural networks, and rigorously verifying AI-generated nutritional recommendations across varying genotypes, lactation phases, and climates. Overcoming these gaps necessitates integrating explainable AI with biologically grounded digestion models, federated learning protocols for data privacy, and standardized PRISMA-based validation approaches. The distilled implementation roadmap offers actionable guidelines for sensor selection, middleware integration, and model lifecycle management, enabling proactive rather than reactive dairy management—an essential leap toward climate-smart, welfare-oriented, and economically resilient dairy farming. Full article