Search Results (27)

Background/Objectives: The aim of this study was to classify cows with respect to different diets, dry period (DP) lengths, and lactation weeks based on body weight, milk variables, and plasma metabolites measured in early lactation. Methods: Holstein–Friesian cows (n = 95) were randomly assigned to three DP lengths (0, 30, or 60 d; n = 31, 34, and 30) and two early-lactation diets (lipogenic: n = 47; glucogenic: n = 48) in a 3 × 2 factorial design. From 10 d pre-calving to 8 weeks postpartum, cows received experimental diets. An XGBoost model was trained for classification using weekly body weight, milk variables, and plasma metabolites, validated via 1000 repeated hold-out partitions with stratified sampling. Results: Classification performance for lactation week, relative to week 1 in lactation, was good, with an area under the curve (AUC) > 0.9, independent of diet or DP length. The classification for 0 d vs. 60 d DP length was better than that for 0 d vs. 30 d or 30 d vs. 60 d DP length, showing an AUC > 0.8, independent of diet or lactation week. The top features to classify diet were plasma urea and milk fat content. Milk yield and protein content were the important features for classifying lactation weeks regardless of diet, while milk fat content was a critical predictor specific to the glucogenic diet. Conclusions: Our findings demonstrate that milk and plasma features can retrospectively classify management groups in early lactation using machine learning approaches. Full article

Traditional dairy products remain an essential yet underutilized component of Lebanon’s food system. Amid economic instability, supply chain fragility, and heavy reliance on imported dairy inputs (≈80% of demand), these products offer resilient, low-input alternatives rooted in centuries-old practices. This review analyzes key traditional Lebanese dairy products, including Labneh, Labneh–Anbaris, Akkawi, Shanklish, Halloumi, Karishi, Pressed–Brined Karishi (Lebanese Double-Cream), Qishta, and Kishk, using Codex Alimentarius and Tetra Pak classification frameworks. It examines their compositional attributes, milk-to-product conversion efficiency, preservation methods, and economic characteristics. The findings reveal a continuum from high-yield fresh cheeses to lower-yield preserved forms with extended shelf life, demonstrating diversified strategies for food security and resilience. Unlike prior studies focused mainly on composition or culinary aspects, this review integrates classification systems with cultural geography to map Lebanon’s traditional dairy landscape. It highlights strategies grounded in rural milk availability and artisanal know-how, revealing overlooked food system functions. These practices exemplify circular models that valorize whey, minimize waste, and preserve quality without refrigeration, aligning with sustainability goal SDG-12.3. This review calls for integrating these products into national food strategies, regulatory frameworks, and innovation systems, recognizing traditional Lebanese dairy as both cultural heritage and a strategic resource for a more self-sufficient and resilient food sector. Full article

This study analyzes the use of a lightweight image-based deep learning model to classify dairy cows into low-, medium-, and high-milk-yield categories by automatically detecting the udder region of the cow. The implemented model was based on the YOLOv11 architecture, which enables efficient object detection and classification with real-time performance. The model is trained on a public dataset of cow images labeled with 305-day milk yield records. Thresholds were established to define the three yield classes, and a balanced subset of labeled images was selected for training, validation, and testing purposes. To assess the robustness and consistency of the proposed approach, the model was trained 30 times following the same experimental protocol. The system achieves precision, recall, and mean Average Precision (mAP@50) of 0.408 ± 0.044, 0.739 ± 0.095, and 0.492 ± 0.031, respectively, across all classes. The highest precision (0.445 ± 0.055), recall (0.766 ± 0.107), and mAP@50 (0.558 ± 0.036) were observed in the low-yield class. Qualitative analysis revealed that misclassifications mainly occurred near class boundaries, emphasizing the importance of consistent image acquisition conditions. The resulting model was deployed in a mobile application designed to support field-level assessment by non-specialist users. These findings demonstrate the practical feasibility of applying vision-based models to support decision-making in dairy production systems, particularly in settings where traditional data collection methods are unavailable or impractical. Full article

The determination of the live body weight of camels (required for their successful breeding) is a rather difficult task due to the problems with handling and restraining these animals. Therefore, the main aim of this study was to predict the ABW of eight indigenous camel (Camelus dromedarius) breeds of Pakistan (Bravhi, Kachi, Kharani, Kohi, Lassi, Makrani, Pishin, and Rodbari). Selected productive (hair production, milk yield per lactation, and lactation length) and reproductive (age of puberty, age at first breeding, gestation period, dry period, and calving interval) traits served as the predictors. Six data mining methods [classification and regression trees (CARTs), chi-square automatic interaction detector (CHAID), exhaustive CHAID (EXCHAID), multivariate adaptive regression splines (MARSs), MLP, and RBF] were applied for ABW prediction. Additionally, hierarchical cluster analysis with Euclidean distance was performed for the phenotypic characterization of the camel breeds. The highest Pearson correlation coefficient between the observed and predicted values (0.84, p < 0.05) was obtained for MLP, which was also characterized by the lowest root-mean-square error (RMSE) (20.86 kg), standard deviation ratio (SD_ratio) (0.54), mean absolute percentage error (MAPE) (2.44%), and mean absolute deviation (MAD) (16.45 kg). The most influential predictor for all the models was the camel breed. The applied methods allowed for the moderately accurate prediction of ABW (average R² equal to 65.0%) and the identification of the most important productive and reproductive traits affecting its value. However, one important limitation of the present study is its relatively small dataset, especially for training the ANN (MLP and RBF). Hence, the obtained preliminary results should be validated on larger datasets in the future. Full article

Metritis is one of the most common postpartum diseases in dairy cows, associated with impaired reproductive performance and substantial economic losses. In this study, we investigated the potential of machine learning (ML) techniques applied to physiological, behavioural, and milk quality parameters for the early detection of metritis in dairy cows during the postpartum period. A total of 2707 daily observations were collected from 94 cows in early lactation, of which 11 cows (275 records) were diagnosed with metritis. The dataset included daily measurements of body weight, rumination time, milk yield, milk composition (fat, protein, lactose), somatic cell count (SCC), and feed intake. Five classification models—partial least squares discriminant analysis (PLS-DA), random forest (RF), support vector machine (SVM), neural network (NN), and an Ensemble model—were developed using standardised features and stratified 80/20 training/test splits. To address class imbalance, model loss functions were adjusted using class weights. Models were evaluated based on accuracy, sensitivity, specificity, positive and negative predictive values (PPV, NPV), area under the receiver operating characteristic (ROC) area under the curve (AUC), and Matthews correlation coefficient (MCC). The NN model demonstrated the highest overall performance (accuracy = 96.1%, AUC = 96.3%, MCC = 0.79), indicating strong capability in distinguishing both healthy and diseased animals. The SVM achieved the highest sensitivity (90.9%), while RF and Ensemble models showed high specificity (>98%) and PPV. This study provides novel evidence that ML methods can effectively detect metritis using routinely collected, non-invasive on-farm data. Our findings support the integration of neural and Ensemble learning models into automated health monitoring systems to enable earlier disease detection and improved animal welfare. Although external validation was not performed, internal cross-validation demonstrated consistent performance across models, suggesting suitability for application in multi-farm settings. To the best of our knowledge, this is among the first studies to apply ML for early metritis detection based exclusively only automated herd data. Full article

This study introduces a novel method for classifying whole and lactose-free milk and the detection of water adulteration through analyzing dried droplets. The key innovation is the addition of NaCl, which modulates crystallization to enhance structural differentiation and facilitate the classification of milk types and detection of adulteration. Dried droplets of milk containing NaCl concentrations of $0\%$, $2\%$, and $4\%$ were analyzed, revealing distinct morphologies, including amorphous, cross-shaped, and dendritic crystals. These structures were quantitatively characterized using lacunarity to assess their discriminatory power. Two classification approaches were evaluated: one based on lacunarity analysis alone and another incorporating deep learning. Both methods yielded high classification accuracies, with lacunarity achieving $95.04\%\pm 6.66\%$, while deep learning reached $95.22\%\pm 4.47\%$. Notably, the highest performance was obtained with $2\%$ NaCl, where lacunarity reached $97.08\%\pm 2.27\%$ and deep learning $96.88\%\pm 2.8\%$, indicating improved precision and stability. While deep learning demonstrated more consistent performance across test cases, lacunarity alone captured highly discriminative structural features, making it a valuable complementary tool. The integration of NaCl and lacunarity analysis offers a robust and interpretable methodology for ensuring the quality and authenticity of dairy products, particularly in detecting adulteration, where morphological contrast is less evident. Full article

Sixty Holstein cows were enrolled at −76 days from calving (DFC) and classified based on the daily SCC during the previous week from an automated milking system. The separation thresholds for low (L, n = 46) and high (H, n = 14) classifications were 100 K/mL for primiparous and 200 K/mL for multiparous cows. Cows were then assigned to two homogeneous groups to receive diets supplemented with 19 g/d of a Saccharomyces cerevisiae fermentation product (TRT; NutriTek, Diamond V, Cedar Rapids, IA, USA) or without supplementation (CTR) until 60 DFC. Cows were dried off at −56 DFC and monitored for disease incidence, milk yield and composition, plasma metabolic profile, and whole blood count from −76 to 60 DFC. Data were analyzed utilizing ANOVA and mixed models for repeated measures. During the dry period, TRT cows had greater plasma thiol and albumin compared to CTR. TRT-L cows had greater plasma protein and globulin than CTR-L. TRT-H cows had heightened hematocrit; reduced plasma globulin and haptoglobin; and higher albumin, albumin to globulin ratio, and thiol than CTR-H. TRT-H cows had greater concentrations of leukocytes and lymphocytes and lower plasma protein and ceruloplasmin at −54 DFC; lower reactive oxygen species to ferric ion-reducing antioxidant power ratios at −44 DFC; and greater concentrations of lymphocytes and plasma gamma glutamyl transferase at −7 DFC than CTR-H. After calving, TRT cows had a lower incidence of mastitis and higher butterfat, as well as greater plasma haptoglobin and aspartate amino transferase (AST) and reduced Mg compared to CTR. TRT cows had lower SCC between 1 and 7 DFC and a greater ECM between 41 and 60 DFC compared to CTR. TRT-H cows had lower SCC between 1 and 7 DFC and greater hemoglobin and plasma AST than CTR-H. Ameliorated immune system functions due to Saccharomyces cerevisiae fermentation product administration lowered the SCC in TRT-H cows and prevented the onset of new intramammary infections across both L and H SCC groups, supporting the improved productive performance of dairy cows. Full article

Previous studies have primarily focused on the extraction of highland barley crops using single phenological images, which ignored the selection of the optimal phenological period for classification. Utilizing the multiple phenological images from Sentinel-2 to construct 25 features, including spectral, red edge, vegetation, and texture features, the recursive feature elimination algorithm and the random forest algorithm (RF) were employed to optimize feature datasets for different phenological stages, which were then used for the identification and classification of high-land barley by RF. The main results were as follows: (1) Information extraction based on feature optimization combinations yielded good overall classification accuracy, with classification accuracies for highland barley being 92.56% (jointing stage), 90.90% (heading stage), 90.74% (flowering stage), 91.55% (milk ripening stage), and 90.51% (maturity stage), respectively. (2) NDVIre1 had the highest importance score (0.1792) in the feature selection combination, indicating that the red edge index contributed significantly to crop information extraction and classification. (3) The five feature variables—GLCM_Mean, RVI, homogeneity, MAX, and GLCM_Correlation—showed stability and universality in the extraction of highland barley. These results demonstrated that the images that derived from the jointing and milk ripening phenological stages had the best applicability for highland barley extraction, and the optimized feature datasets that composed of NDVIre1 were conductive to detect and monitor of highland barley crops in the mountainous regions of northwest China. Full article

The degradation of pastures and meadows is a global problem with a wide range of impacts. It affects farmers in different ways, such as decreases in cattle production, milk yield, and forage quality. Still, it also has other side effects, such as loss of biodiversity, loss of resources, etc. In this study, the degradation of a semi-natural pasture near the village of Obichnik, Bulgaria, was evaluated using machine learning algorithms, and an unmanned aerial vehicle (UAV) obtained visual spectrum images. A high-quality (HQ) orthomosaic of the area was created and numerous regions of interest were manually marked for training and validation purposes. Three machine learning algorithms were used—Maximum likelihood, Random trees (RT), and Support Vector Machine (SVM). Furthermore, object-based and pixel-based approaches were utilized. The obtained results indicate that the object-based RT and SVM models provide significantly better accuracy, with their Cohen’s Kappa reaching 0.86 and 0.82, respectively. The performed classification showed that approximately 61% of the investigated pasture area is covered with grass, which indicates light-to-medium degradation. Full article

The Podolica cattle breed is widespread in southern Italy, and its productivity is characterized by low yields and an extraordinary quality of milk and meats. Most of the milk produced is transformed into “Caciocavallo Podolico” cheese, which is made with 100% Podolica milk. Fourier Transform Infrared Spectroscopy (FTIR) is the technique that, in this research work, was applied together with machine learning to discriminate 100% Podolica milk from contamination of other Calabrian cattle breeds. The analysis on the test set produced a misclassification percentage of 6.7%. Among the 15 non-Podolica samples in the test set, 2 were misclassified and recognized as Podolica milk even though the milk was from other species. The correct classification rate improved to 100% when the same method was applied to the recognition of Podolica and Pezzata Rossa milk produced by the same farm. Furthermore, this technique was tested for the recognition of Podolica milk mixed with milk from other bovine species. The multivariate model and the respective confusion matrices obtained showed that all the 14 Podolica samples (test set) mixed with 40% non-Podolica milk were correctly classified. In addition, Pezzata Rossa milk produced by the same farm was detected as a contaminant in Podolica milk from the same farm down to concentrations as little as 5% with a 100% correct classification rate in the test set. The method described yielded higher accuracy values when applied to the discrimination of milks from different breeds belonging to the same farm. One of the reasons for this phenomenon could be linked to the elimination of the environmental variable. However, the results obtained in this work demonstrate the possibility of using FTIR to discriminate between milks from different breeds. Full article

Leptospirosis is a zoonotic bacterial disease affecting mammalian species worldwide. Cattle are a major susceptible host; infection with pathogenic Leptospira spp. represents a public health risk and results in reproductive failure and reduced milk yield, causing economic losses. The characterisation of outer membrane proteins (OMPs) from disease-causing bacteria dissects pathogenesis and underpins vaccine development. As most leptospire pathogenesis research has focused on Leptospira interrogans, this study aimed to characterise novel OMPs from another important genomospecies, Leptospira borgpetersenii, which has global distribution and is relevant to bovine and human diseases. Several putative L. borgpetersenii OMPs were recombinantly expressed, refolded and purified, and evaluated for function and immunogenicity. Two of these unique, putative OMPs (rLBL0972 and rLBL2618) bound to immobilised fibronectin, laminin and fibrinogen, which, together with structural and functional data, supports their classification as leptospiral adhesins. A third putative OMP (rLBL0375), did not exhibit saturable adhesion ability but, together with rLBL0972 and the included control, OmpL1, demonstrated significant cattle milk IgG antibody reactivity from infected cows. To dissect leptospire host–pathogen interactions further, we expressed alleles of OmpL1 and a novel multi-specific adhesin, rLBL2618, from a variety of genomospecies and surveyed their adhesion ability, with both proteins exhibiting divergences in extracellular matrix component binding specificity across synthesised orthologs. We also observed functional redundancy across different L. borgspetersenii OMPs which, together with diversity in function across genomospecies orthologs, delineates multiple levels of plasticity in adhesion that is potentially driven by immune selection and host adaptation. These data identify novel leptospiral proteins which should be further evaluated as vaccine and/or diagnostic candidates. Moreover, functional redundancy across leptospire surface proteins together with identified adhesion divergence across genomospecies further dissect the complex host–pathogen interactions of a genus responsible for substantial global disease burden. Full article

The characterization of dairy farming is fundamental for the sector, as the information obtained directs institutional and public policy actions, which contribute to the development of the milk production chain. The objective of this research was to highlight and analyze two points: identify the spatial concentration of production and investigate the existence of centers specializing in milk production; evaluate the sources of growth in dairy farming in micro-regions of Pará and verify their participation in the growth and productivity of the herd. Regarding specialization in milk production, in the initial year of the study, there were nine specialized micro-regions; however, in the final year, only six fell into this classification, being Parauapebas, Marabá, Tucuruí, Redenção, São Félix do Xingu, and Altamira. Southeastern Pará stands out as the main dairy hub in the state, which encompasses municipalities with a tradition in dairy farming, such as Água Azul do Norte, the largest state producer since 2012. The effective growth in milk production from the 1990s to 2020 showed an increase in state production of 3.23% per year, with a greater contribution to this growth in herd productivity gains than in relation to the expansion of the herd; however, ten micro-regions presented a negative average annual growth rate, being located in the Northeast of Pará, Marajó, and the Metropolitan Region of Belém, a result resulting from the reduction of the herd expansion effect, as the productivity effect of all micro-regions exhibited positive rates, with the exception of Cametá and Arari. The sharpest decline occurred in Arari, with a sharp drop in milk production, number of animals milked, and cow yield. The twelve micro-regions with positive annual rates are located in the mesoregions of Southeast Pará, Southwest Pará, and Baixo Amazonas, nine associated with intensive growth and three more linked to extensive growth. In general, the results show that the regions specialized in the activity are more articulated, presenting the highest percentages in terms of quantity produced, herd milked, and financial movement, compared to non-specialized locations. Through analyses, it is possible to obtain a better understanding of the regional growth process, with a focus on dairy activity, as the information and particularities of properties are fundamental to guide public and private institutions on the reality and existing problems, enabling readjustment and new policy formulations with the aim of alleviating producers’ limitations, as well as enhancing growth and reducing intra- and inter-regional imbalances. Full article

The aim of the present study was to compare the predictive performance of decision trees, artificial neural networks, and logistic regression used for the classification of daily body weight gains in beef calves. A total of 680 pure-breed Simmental and 373 Limousin cows from the largest farm in the West Pomeranian Province, whose calves were fattened between 2014 and 2016, were included in the study. Pre-weaning daily body weight gains were divided into two categories: A—equal to or lower than the weighted mean for each breed and sex and B—higher than the mean. Models were developed separately for each breed. Sensitivity, specificity, accuracy, and area under the curve on a test set for the best model (random forest) were 0.83, 0.67, 0.76, and 0.82 and 0.68, 0.86, 0.78, and 0.81 for the Limousin and Simmental breeds, respectively. The most important predictors were daily weight gains of the dam when she was a calf, daily weight gains of the first calf, sex of the third calf, milk yield at first lactation, birth weight of the third calf, dam birth weight, dam hip height, and second calving season. The selected machine learning models can be used quite effectively for the classification of calves based on their daily weight gains. Full article

Natural selection and domestication have shaped modern sheep populations into a vast range of phenotypically diverse breeds. Among these breeds, dairy sheep have a smaller population than meat sheep and wool sheep, and less research is performed on them, but the lactation mechanism in dairy sheep is critically important for improving animal-production methods. In this study, whole-genome sequences were generated from 10 sheep breeds, including 57 high-milk-yield sheep and 44 low-milk-yield sheep, to investigate the genetic signatures of milk production in dairy sheep, and 59,864,820 valid SNPs (Single Nucleotide Polymorphisms) were kept after quality control to perform population-genetic-structure analyses, gene-detection analyses, and gene-function-validation analyses. For the population-genetic-structure analyses, we carried out PCA (Principal Component Analysis), as well as neighbor-joining tree and structure analyses to classify different sheep populations. The sheep used in our study were well distributed in ten groups, with the high-milk-yield-group populations close to each other and the low-milk-yield-group populations showing similar classifications. To perform an exact signal-selection analysis, we used three different methods to find SNPs to perform gene-annotation analyses within the 995 common regions derived from the fixation index (F_ST), nucleotide diversity (Ɵπ), and heterozygosity rate (ZHp) results. In total, we found 553 genes that were located in these regions. These genes mainly participate in the protein-binding pathway and the nucleoplasm-interaction pathway, as revealed by the GO- and KEGG-function-enrichment analyses. After the gene selection and function analyses, we found that FCGR3A, CTSK, CTSS, ARNT, GHR, SLC29A4, ROR1, and TNRC18 were potentially related to sheep-milk-production traits. We chose the strongly selected genes, FCGR3A, CTSK, CTSS, and ARNT during the signal-selection analysis to perform a RT-qPCR (Reale time Quantitative Polymerase Chain Reaction) experiment to validate their expression-level relationship with milk production, and the results showed that FCGR3A has a significant negative relationship with sheep-milk production, while other three genes did not show any positive or negative relations. In this study, it was discovered and proven that the candidate gene FCGR3A potentially contributes to the milk production of dairy sheep and a basis was laid for the further study of the genetic mechanism underlying the strong milk-production traits of sheep. Full article

Adaptative responses of cows to an automatic milking system (AMS) could depend on their temperament, i.e., cows with certain temperament profiles could be able to cope more successfully with the AMS. The relationships between dairy cows’ temperament, behaviour, and productive parameters during the changeover from a conventional milking system (CMS) to an AMS were investigated. Thirty-three multiparous cows were classified as ‘calm’ or ‘reactive’ based on each of the temperament tests conducted: race time, flight speed (FS), and flight distance, at 5, 25, and 45 days in milk at CMS, then the cows were moved from the CMS to the AMS. During the first five milkings in AMS, the number of steps and kicks during each milking were recorded. The daily milk yield was automatically recorded. The number of steps did not vary by temperament classification, but the number of kicks per milking was greater for calm (0.45 ± 0.14) than for reactive cows (0.05 ± 0.03) when they were classified by FS (p < 0.01). During the first seven days in the AMS, reactive cows for the FS test produced more milk than calm cows (36.5 ± 1.8 vs. 33.2 ± 1.6 L/day; p = 0.05). In conclusion, behavioural and productive parameters were influenced by cows´ temperament during the milking system changeover since the calm cows kicked more and produced less than the reactive ones. Full article