Search Results (886)

The stable physiological structure and rich vascular network of pig ears contribute to distinct thermal characteristics, which can reflect temperature variations. While the temperature of the pig ear does not directly represent core body temperature due to the ear’s role in thermoregulation, thermal infrared imaging offers a feasible approach to analyzing individual pig status. Based on this background, a dataset comprising 23,189 thermal infrared images of pig ears (TIRPigEar) was established. The TIRPigEar dataset was obtained through a pig house inspection robot equipped with an infrared thermal imaging device, with post-processing conducted via manual annotation. By labeling pig ears within these images, a total of 69,567 labeled files were generated, which can be directly used for training pig ear detection models and enabling the analysis of pig temperature information by integrating the corresponding thermal imaging data. To validate the dataset’s utility, it was evaluated across various object detection algorithms. Experimental results show that the dataset achieves the highest precision, recall, and mAP50 on the YOLOv9m model, reaching 97.35%, 98.1%, and 98.6%, respectively. Overall, the TIRPigEar dataset demonstrates optimal performance when applied to the YOLOv9m algorithm. Utilizing thermal infrared imaging technology to detect pig ear information provides a non-contact, rapid, and effective method. Establishing the TIRPigEar dataset is highly significant, as it allows for a valuable resource for AI and precision livestock farming researchers to validate and improve their algorithms. This dataset will support many researchers in advancing precision livestock farming by enabling an efficient way for pig ear temperature analysis. Full article

The chicken is the world’s most farmed animal. In this work, we introduce the Chicks4FreeID dataset, the first publicly available dataset focused on the reidentification of individual chickens. We begin by providing a comprehensive overview of the existing animal reidentification datasets. Next, we conduct closed-set reidentification experiments on the introduced dataset, using transformer-based feature extractors in combination with two different classifiers. We evaluate performance across domain transfer, supervised, and one-shot learning scenarios. The results demonstrate that transfer learning is particularly effective with limited data, and training from scratch is not necessarily advantageous even when sufficient data are available. Among the evaluated models, the vision transformer paired with a linear classifier achieves the highest performance, with a mean average precision of 97.0%, a top-1 accuracy of 95.1%, and a top-5 accuracy of 100.0%. Our evaluation suggests that the vision transformer architecture produces higher-quality embedding clusters than the Swin transformer architecture. All data and code are publicly shared under a CC BY 4.0 license. Full article

Sandflies, small insects primarily from the Psychodidae family, are commonly found in sandy, tropical, and subtropical regions. Most active during dawn and dusk, female sandflies feed on blood to facilitate egg production. In doing so, they can transmit infectious diseases that may cause symptoms such as fever, headaches, muscle pain, anemia, skin rashes, and ulcers. Importantly, sandflies are species-specific in their disease transmission. Determining the gender and species of sandflies typically involves examining their morphology and internal anatomy using established identification keys. However, this process requires expert knowledge and is labor-intensive, time-consuming, and prone to misidentification. In this paper, we develop a highly accurate and efficient convolutional network model that utilizes pharyngeal and genital images of sandfly samples to classify the sex and species of three sandfly species (i.e., Phlebotomus sergenti, Ph. alexandri, and Ph. papatasi). A detailed evaluation of the model’s structure and classification performance was conducted using multiple metrics. The results demonstrate an excellent sex-species classification accuracy exceeding 95%. Hence, it is possible to develop automated artificial intelligence-based systems that serve the entomology community at large and specialized professionals. Full article

The aim of this study was to evaluate the ultrasonographic measurement of the subcutaneous fat and muscle layers at two different body locations as an objective tool with which to determine the nutritional status of alpacas. The results of ultrasonographic measurement were related to body weight, determined by scale, and body condition score (BCS), determined by a scoring system. Differences between gender (female/male) and different reproductive statuses (castrated/intact males, pregnant, and early or non-pregnant females) were evaluated. In total, 160 alpacas were examined. Ultrasonography was performed first at the lumbar region, positioning a linear probe (8 MHz) between the second and third lumbar vertebrae perpendicular to the spinal column, and in the gluteal region, measuring the distance between skin, the subcutaneous fat layer, and the muscle layer. The results showed that the gender and pregnancy status of females had a significant influence on the ultrasonographic measurements at both localizations. Significant associations were found between body weight and the BCS. The BCS and ultrasonographic-measured soft-tissue thicknesses at both localizations were significantly associated for males and early or non-pregnant females. According to these results, ultrasonography can be recommended as an objective method with which to determine the nutritional status of alpacas. Full article

Sustainable and climate-resilient livestock systems are increasingly necessary to balance food production demands with environmental conservation. Breeds such as Galloway (Ga) and Highland (Hi) cattle are recognized for their adaptability to extensive grazing systems, low input requirements, and ability to thrive on marginal lands. Despite their potential, research on the performance of Ga and Hi cattle in low-resource, extensive grazing systems, particularly in Romania, remains scarce. This study evaluated the performance of Ga and Hi beef cattle raised under low-input conditions with a focus on the following: (1) the average daily gain (ADG) on low- and medium-quality forage and (2) the cattle’s adaptability to extensive grazing systems. The study, conducted at Cojocna Farm, Transylvania, Romania (2023–2024), involved five male and three female calves from each breed. Calves were weighed five times in the entire observation period, and feed quality was analyzed. The results showed that Ga calves, especially males, had a higher ADG than Hi calves (Ga = 676.91 g, Hi = 581.14 g), while females showed more consistent performance during winter feeding. Both breeds demonstrated strong adaptability and satisfactory performance under the extensive conditions of Transylvania, as evidenced by the comparison of the obtained ADG with the values provided by the National Breed Register. Future research should explore the long-term sustainability of these breeds in varying environmental conditions, to investigate genetic factors influencing performance, and assess the broader ecological and economic benefits of integrating Galloway and Highland cattle into diverse farming systems. Full article

The development and utilization of unconventional forage resources is crucial to alleviating the current situation of shortage of forage resources. Giant reed (Arundo donax) is a promising forage resource from the Poaceae family, one of the largest herbaceous plants globally, with fast growth, high biomass yield, and strong ecological adaptability. However, there are still very few reports on the use of giant reed in livestock and poultry production. The purpose of this study was to evaluate the effects of adding giant reed instead of wheat straw in total mixed ration (TMR) diets on growth performance, blood biochemical indexes, nutrient digestibility, and antioxidant properties of sheep, thereby providing a theoretical basis for the development and utilization of giant reed herbage resources. A total of 24 fattening sheep (Han × Duper) with similar body weight (20 kg), age (2 months), and health status were randomly divided into four groups with six replicates per group. Sheep in the control group were fed a basal diet (CON), and those in the experimental groups were fed giant reed Lvzhou No. 1 instead of wheat straw, with replacement proportions of 10% (GR10), 20% (GR20), and 30% (GR30) of the total diet, respectively. The results showed that (1) the body weight (FBW) and average daily gain (ADG) of sheep in the GR20 and GR30 groups were higher than those of sheep in the CON and GR10 groups (p < 0.05). Meanwhile, the feed to gain ratio (F/G) of sheep in the GR20 and GR30 groups was lower than those sheep in the CON and GR10 groups (p < 0.05), and the F/G of the GR30 group was lower than that of the GR20 group (p < 0.05). (2) The apparent digestibility of DM and CP in groups GR10, GR20 and GR30 was significantly higher than that in group CON (p < 0.005). The digestibility of NDF and ADF in groups GR20, and GR30 was significantly higher than that in the CON and GR10 groups (p < 0.05). (3) dietary substitution of giant reed for wheat straw had no effect on serum biochemical indices, except serum glucose (GLU, p = 0.014) of sheep. In addition, the substitution of giant reed for wheat straw had a tendency to decrease serum urea content of sheep (p = 0.098). (4) Dietary substitution of giant reed for wheat straw significantly improved serum T-SOD (p < 0.001) and T-AOC (p < 0.001), and significantly decreased MDA (p < 0.001) of sheep. In conclusion, replacing wheat straw with giant reed can significantly enhance growth performance, nutrient digestibility, and antioxidant capacity in sheep without adverse effects on their normal physiological functions. Full article

Monitoring the body condition of dairy cows is essential for ensuring their health and productivity, but traditional BCS methods—relying on visual or tactile assessments by skilled personnel—are subjective, labor-intensive, and impractical for large-scale farms. To overcome these limitations, we present BCS-YOLO, a lightweight and automated BCS framework built on YOLOv8, which enables consistent, accurate scoring under complex conditions with minimal computational resources. BCS-YOLO integrates the Star-EMA module and the Star Shared Lightweight Detection Head (SSLDH) to enhance the detection accuracy and reduce model complexity. The Star-EMA module employs multi-scale attention mechanisms that balance spatial and semantic features, optimizing feature representation for cow hindquarters in cluttered farm environments. SSLDH further simplifies the detection head, making BCS-YOLO viable for deployment in resource-limited scenarios. Additionally, channel-based knowledge distillation generates soft probability maps focusing on key body regions, facilitating effective knowledge transfer and enhancing performance. The results on a public cow image dataset show that BCS-YOLO reduces the model size by 33% and improves the mean average precision (mAP) by 9.4%. These advances make BCS-YOLO a robust, non-invasive tool for consistent and accurate BCS in large-scale farming, supporting sustainable livestock management, reducing labor costs, enhancing animal welfare, and boosting productivity. Full article

Livestock behavior serves as a crucial indicator of physiological health. Leveraging deep learning techniques to automatically recognize dairy goat behaviors, particularly abnormal ones, enables early detection of potential health and environmental issues. To address the challenges of recognizing small-target behaviors in complex environments, a multi-scale and lightweight behavior recognition model for dairy goats called GSCW-YOLO was proposed. The model integrates Gaussian Context Transformation (GCT) and the Content-Aware Reassembly of Features (CARAFE) upsampling operator, enhancing the YOLOv8n framework’s attention to behavioral features, reducing interferences from complex backgrounds, and improving the ability to distinguish subtle behavior differences. Additionally, GSCW-YOLO incorporates a small-target detection layer and optimizes the Wise-IoU loss function, increasing its effectiveness in detecting distant small-target behaviors and transient abnormal behaviors in surveillance videos. Data for this study were collected via video surveillance under varying lighting conditions and evaluated on a self-constructed dataset comprising 9213 images. Experimental results demonstrated that the GSCW-YOLO model achieved a precision of 93.5%, a recall of 94.1%, and a mean Average Precision (mAP) of 97.5%, representing improvements of 3, 3.1, and 2 percentage points, respectively, compared to the YOLOv8n model. Furthermore, GSCW-YOLO is highly efficient, with a model size of just 5.9 MB and a frame per second (FPS) of 175. It outperforms popular models such as CenterNet, EfficientDet, and other YOLO-series networks, providing significant technical support for the intelligent management and welfare-focused breeding of dairy goats, thus advancing the modernization of the dairy goat industry. Full article

Inspired by the effects of solar or UV radiation on the decay of airborne bacteria during their transport, this study investigated the effect of UVA on the decay of airborne bacteria from cattle houses and analyzed the potential use of UVA to reduce indoor airborne bacteria under laboratory conditions. Airborne bacteria from the cattle source were generated and released into a small-scale test chamber (1.5 m³) with different strategies according to the different objectives in decay tests and simulated sterilization tests. Increasing with the UVA radiation gradients (0, 500, 1000, 1500 μW cm⁻²), the average decay rate of total curable airborne bacteria ranged from 2.7% to 61.6% in decay tests. Under the combination of different UVA radiation intensities (2000 μW cm⁻² in maximum) and radiation durations (60 min in maximum), simulated sterilization tests were conducted to examine the potential use of UVA radiation for air sterilization in animal houses. With the dynamic inactive rate (DIR) ranging from 17.2% to 62.4%, we proved that UVA may be an alternative way to reduce the indoor airborne bacteria in cattle houses if applied properly. Similar effects would be achieved using either a high radiation intensity with a short radiation duration or a low radiation intensity with a long radiation duration. Full article

A critical issue in image analysis for analyzing animal behavior is accurate object detection and tracking in dynamic and complex environments. This study introduces a novel preprocessing algorithm to bridge the gap between computational efficiency and segmentation fidelity in object-based image analysis for machine learning applications. The algorithm integrates convolutional operations, quantization strategies, and polynomial transformations to optimize image segmentation in complex visual environments, addressing the limitations of traditional pixel-level and unsupervised methods. This innovative approach enhances object delineation and generates structured metadata, facilitating robust feature extraction and consistent object representation across varied conditions. As empirical validation shows, the proposed preprocessing pipeline reduces computational demands while improving segmentation accuracy, particularly in intricate backgrounds. Key features include adaptive object segmentation, efficient metadata creation, and scalability for real-time applications. The methodology’s application in domains such as Precision Livestock Farming and autonomous systems highlights its potential for high-accuracy visual data processing. Future work will explore dynamic parameter optimization and algorithm adaptability across diverse datasets to further refine its capabilities. This study presents a scalable and efficient framework designed to advance machine learning applications in complex image analysis tasks by incorporating methodologies for image quantization and automated segmentation. Full article

Non-typhoidal Salmonella (NTS) infections in poultry, particularly in commercial-layer chickens, pose a critical risk to food safety and public health worldwide. NTS bacteria can remain undetected in poultry flocks, contaminating products and potentially leading to gastroenteritis in humans. This review examines pre-harvest control strategies for NTS in layer chickens, including biosecurity protocols, vaccinations, feed additives, genetic selection, and environmental management. These strategies have substantially reduced Salmonella colonization and product contamination rates in the commercial layer industry. By evaluating these strategies, this review highlights the importance of integrated control measures to limit NTS colonization, reduce antimicrobial resistance, and improve poultry health. This review aims to provide producers, researchers, and policymakers with insights into effective practices to minimize Salmonella contamination and enhance both animal and human health outcomes. Full article

In Colombia, research on Salmonella concerning animal health, veterinary diagnostics, and epidemiology within the primary production chain is limited. This study aimed to analyze the published data about Salmonella in the Colombian primary pig production chain from 2009 to mid-2024. This involved an exploratory literature review using systematic search strategies, including articles, graduate studies, conference presentations, and technical reports from the selected period. Of the 35 studies reviewed, 30 met the inclusion criteria, with eleven being from the grey literature. The pooled prevalence of Salmonella spp. on Colombian farms was 8.9%, while the seroprevalence ranged from 27 to 40%. Risk factors associated with the presence of this bacterium on farms included aspects such as water sources, pest control, the farm type, and management practices. Few scientific publications address the presence of this pathogen in primary pig production in Colombia, underscoring the need to raise awareness within the academic and production communities about the importance of conducting and reporting new studies and cases. Full article

This study aims to quantify enteric methane (CH₄) emission and dry matter intake (DMI) in beef steers under two rotational grazing systems: (i) a mixture of cover crops (vetch + ryegrass + forage radish) (CC) and (ii) alfalfa and fescue pasture (AFP). Eighteen Hereford steers were divided into two groups (nine steers per group), assigned to either the CC or AFP. Methane emissions were measured using the SF₆ tracer technique. The results showed that steers grazing CC produced 29% less CH₄ in g/d compared to those on the AFP (119.1 vs. 167.1 g/d for CC and AFP, p < 0.05) and 36% less CH₄ yield (4.3 vs. 6.7% of gross energy intake). However, average daily gain (ADG), DMI, and CH₄ intensity (gCH₄/kg ADG) did not significantly differ between treatments. The integration of CC in a cattle grazing system has the potential to reduce CH₄ emissions by improving forage quality. Full article

This study investigates antimicrobial-resistant (AMR) Salmonella Typhimurium in poultry, focusing on how class I integrons contribute to AMR and virulence. Using whole genome sequencing, researchers analyzed 26 S. Typhimurium isolates from U.S. poultry, finding that three isolates contained integrons (1000 base pairs each). These integron-positive isolates exhibited significantly higher resistance to beta-lactams, phenicols, and tetracyclines compared to integron-free isolates (p = 0.004, 0.009, and 0.02, respectively) and harbored genes like ges, imp, and oxa, which are linked to extended-spectrum beta-lactamase resistance. Most AMR gene classes (64%) were chromosome-based, with integron-positive isolates showing a broader array of resistance genes, including catB and tetA. Integron-bearing isolates had higher occurrences of bacteriocin genes and specific AMR genes like aminoglycoside and beta-lactam resistance genes, while integron-free isolates had more fimbrial and pilus genes. The presence of integrons may trend with increased AMR genes and virulence factors, highlighting the role of integron screening in enhancing AMR surveillance and reducing the need for high-priority antimicrobial treatments in poultry. These findings could support better AMR stewardship practices in poultry production, potentially lowering infection risks in humans and livestock. Full article

Poultry farming in Ethiopia is crucial for food security and income, but it faces significant challenges due to gaps in farmer awareness. A cross-sectional study was conducted using the Biocheck.UGent™ biosecurity scoring system and a questionnaire to evaluate poultry farmers’ basic and practical knowledge concerning salmonellosis and mycotoxins. The questionnaire revealed substantial gaps in basic and practical knowledge regarding Salmonella spp infections and mycotoxin among 38 poultry farmers in Jimma. About 68.4% of farmers were unaware of the impact of salmonellosis on both poultry and human health. Moreover, 78.9% had limited basic knowledge of how salmonellosis affects production and the economy. Farmers also showed limited practical knowledge of farm management and hygiene practices essential for preventing Salmonella spp. infections. Regarding mycotoxins, 63.2% of farmers lacked awareness of poultry feed management, 60.5% were unaware of the health risks mycotoxins pose, and 73.7% did not recognize signs of mycotoxin contamination. Although 55.3% of farmers demonstrated acceptable practical knowledge of strategies to reduce the impact of mycotoxin contaminations, there are still concerns, particularly since 65.8% and 55.3% only showed moderate practical knowledge of feed storage and mycotoxin prevention, respectively. The overall biosecurity scores of poultry farms were below the global average, with a score of 41.7 compared to the worldwide average of 64. The overall mean score for external biosecurity was 44.9, below the global average of 63. All 3 scoring platforms and biosecurity parameters indicated that internal biosecurity was the weakest aspect, with a score of 31.6, well below the global standard of 64. The results showed a weak correlation (rₛ = 0.06) between farmers’ basic and practical knowledge scores about Salmonella spp. infections and mycotoxins. Similarly, there was a weak correlation between the poor biosecurity score of poultry farms and the basic and practical knowledge of poultry farmers on Salmonella spp. infections (rₛ = 0.17) and mycotoxins (rₛ = 0.25). In conclusion, the study found that poultry farmers in Jimma had poor basic and practical knowledge scores on Salmonella, mycotoxins, and biosecurity measures. Thus, awareness creation is paramount to improve these gaps to reduce the impact of mycotoxin contamination and poultry diseases and consequently to improve food security and food safety. Full article