Search Results (248)

The automatic recognition of animal vocalizations is a valuable tool for monitoring pigs’ behavior, health, and welfare. This study investigates the feasibility of implementing a convolutional neural network (CNN) model for classifying pig vocalizations using tiny machine learning (TinyML) on a low-cost, resource-constrained embedded system. The dataset was collected in 2011 at the University of Illinois at Urbana-Champaign on an experimental pig farm. In this experiment, 24 piglets were housed in environmentally controlled rooms and exposed to gradual thermal variations. Vocalizations were recorded using directional microphones, processed to reduce background noise, and categorized into “agonistic” and “social” behaviors using a CNN model developed on the Edge Impulse platform. Despite hardware limitations, the proposed approach achieved an accuracy of over 90%, demonstrating the potential of TinyML for real-time behavioral monitoring. These findings underscore the practical benefits of integrating TinyML into swine production systems, enabling early detection of issues that may impact animal welfare, reducing reliance on manual observations, and enhancing overall herd management. Full article

Background/Objectives: Lawsonia intracellularis is a bacterium that causes Proliferative Enteropathy, an enteric infection characterized mainly by diarrhea and growth retardation, leading to important economic losses. Acute and chronic infections are easily diagnosed, and their control by vaccination has been proven efficacious. However, subclinical infections, despite being very prevalent, often remain underdiagnosed and uncontrolled in practice. Scarce research is available on the control of subclinical infections by vaccination, and the benefit in these scenarios remains to be elucidated. Two field trials were carried out to (1) determine the association between the growth and fecal shedding of L. intracellularis in unvaccinated and intramuscularly vaccinated pigs in a farm with subclinical infection and (2) assess the impact of intradermal vaccination against L. intracellularis on clinical performance and carcass quality in a herd with subclinical infection. Methods: A pig herd with subclinical infection was selected. Pigs were vaccinated intramuscularly (study 1) or intradermally (study 2) at weaning. Fecal shedding, performance, clinical parameters, and carcass quality were investigated. Results: Growth was negatively associated with the fecal load of L. intracellularis in non-vaccinated pigs, whereas in vaccinated pigs, growth performance was not impacted by fecal load (study 1). Vaccinated pigs presented a significantly lower fecal load, lower prevalence of tail biting (31.7%) compared with controls (54.2%), less back fat, and a greater Lean Meat percentage (study 2). Conclusions: Vaccination against L. intracellularis in a herd with subclinical infection and low fecal bacterial shedding led to a reduction in fecal shedding, a lower prevalence of tail biting, and an improvement in carcass quality. Full article

Mycoplasma suis infects pig red blood cells and is linked to anemia, weakened immunity, and production losses. Infected animals may remain subclinical carriers, contributing to pathogen dissemination. This study aimed to investigate the prevalence of M. suis in commercial pig farms in the state of Espírito Santo, Brazil. A total of 416 blood samples from 55 farms were analyzed using conventional PCR targeting the hemotropic Mycoplasmas (16S rRNA) and a species-specific PCR for M. suis (23S rRNA). Among the samples, 131 (31.49%) tested positive for hemoplasmas and 58 (13.94%) for M. suis with a significantly higher frequency in sows (p < 0.01). The Metropolitan microregion showed the highest prevalence (23.53%). The discrepancy between the prevalence for the genus and the species suggests the possible presence of other hemotropic Mycoplasma species and highlights the limitations of 16S rRNA-based assays. These findings emphasize the need for more specific molecular targets and continuous monitoring strategies to control infection in pig farming. Full article

Climate change has emerged as one of the most pressing global challenges in recent decades. Agricultural activities significantly influence climate dynamics, necessitating thorough investigation of their emission patterns. Using the FAO datasets, the objectives of this study were to assess agricultural GHG emissions, identify influencing factors, and explore potential mitigation strategies. The results show that emissions related to crop production are strongly correlated with the yields of predominant crops. Maize production had the largest impact on crop emissions (0.023), followed by potato (0.021) and rice (0.007). Notably, these three crops accounted for substantial portions of total crop-related emissions, with maize contributing 11.70%, potatoes (Solanum tuberosum L.) 10.21%, and rice 9.25%. In the livestock sector, cattle herds generated 10.75% of emissions, with pigs and sheep contributing 9.82% and 10.03%, respectively. Multivariate analysis revealed the cattle/buffalo population as the dominant emission driver (0.32), followed by sheep/goat (0.21) and swine (0.10) populations. Simultaneously, emissions from livestock operations were closely associated with the populations of key livestock species. Thus, from a climate mitigation perspective, prioritizing yield-optimized agronomic approaches for maize and potato cultivation, along with strategic population management of cattle and sheep, represents a critical pathway toward achieving emission reduction targets in global agricultural systems. Full article

Follicle stimulating hormone (FSH) stands as one of the most prevalently used reproductive hormones in the field of animal-assisted reproduction. Conventionally, pituitary FSH is sourced from the heterologous pituitary glands of pigs and sheep procured from slaughterhouses, and it typically exists in the form of crude FSH. The specific challenges inherent in FSH-based assisted reproduction drugs has significantly spurred the interest in exploring novel alternatives, aiming to reduce the reliance on these traditional sources in relevant production processes. In this study, the α- and β-FSH genes were retrieved from pituitary cDNA libraries. These genes were selected to construct a recombinant protein—the novel cow recombinant FSH (CrFSH)—through the application of the homologous recombination method. Notably, the β-subunit was extended by a carboxy-terminal peptide (CTP). After successfully integrating the two genes into Chinese hamster ovary (CHO) cells, the recombinant protein (approximately 33 kDa) in the culture supernatant was detected using Western blotting (WB). The results of the GCs proliferation experiment indicated that both 1.2 µg/mL pFSH and 20–20,000 ng/mL CrFSH could significantly promote the proliferation of GCs in vitro. Remarkably, on the 4th day after treatment, 20 ng/mL of CrFSH had a higher GCs proliferation rate than 1.2 μg/mL of pFSH (p < 0.001). Additionally, cyclic adenosine monophosphate (cAMP) induction assay in GCs unequivocally confirmed that CrFSH possesses superior activity compared to pFSH. These findings underscore that this recombinant protein holds great potential as a promising candidate for FSH production in assisted reproduction approaches for dairy herds. Full article

The intensifying global demand for food presents significant challenges for sustainable pig production, particularly in the context of escalating input costs, environmental degradation, and resource scarcity. Life cycle assessment provides a comprehensive framework for quantifying environmental impacts and identifying production hotspots within pig production systems. Feed production and manure management are consistently identified as major contributors, emphasising the need for targeted interventions. Although soybean meal remains a key protein source, its association with deforestation and biodiversity loss is driving an interest in more sustainable alternatives. In temperate climates, faba beans offer a promising, locally sourced option, though their wider adoption is limited by amino acid imbalances and anti-nutritional factors. Grain preservation is another critical consideration, as post-harvest losses and fungal contamination compromise feed quality and animal health. Organic acid preservation has emerged as an energy-efficient, cost-effective alternative to industrial drying, improving storage stability and reducing fossil fuel dependence. Additional nutritional strategies, including dietary crude protein reduction, carbohydrate source modification, feed additive inclusion, and maternal nutritional interventions, can enhance nutrient utilisation, intestinal health, and herd resilience while mitigating environmental impact. This review explores practical feed-based strategies to support sustainable, resilient, and resource-efficient pig production and contribute to global food security. Full article

Porcine circoviruses (PCVs), encompassing porcine circovirus type 1 (PCV1), porcine circovirus type 2 (PCV2), porcine circovirus type 3 (PCV3), and porcine circovirus type 4 (PCV4), have been documented in China and represent a significant threat to the swine industry. Nevertheless, there is a paucity of data regarding the infection characteristics of PCVs across different age groups within intensive pig farming operations. In this investigation, a systematic cross-sectional methodology was employed to collect 415 testicular processing fluid samples and 1583 serum samples from 30 breeding farms and 27 fattening farms in China. All samples underwent analysis using real-time quantitative polymerase chain reaction (qPCR). Among the testicular fluid samples from suckling pigs, the detection rates for PCV1, PCV2, PCV3, and PCV4 were 56.9%, 31.1%, 75.4%, and 2.2%, respectively. The lowest mean cycle threshold (Ct) values for PCV1 and PCV3 were observed in testicular fluid as opposed to serum samples. At the individual level, the detection rate of PCV1 was significantly higher in fattening pigs (28.7%) and sows (28.7%) compared to nursery pigs (8.5%). The detection rate of PCV2 was highest in fattening pigs (43.1%) and lowest in sows (19.2%). The infection profile of PCV3 contrasted markedly with that of PCV2, exhibiting the lowest prevalence in fattening pigs (8.1%) and the highest in sows (46.1%). PCV4 was infrequently detected across all age groups, with prevalence rates ranging from 0% to 1.7%. Furthermore, the incidence of mixed infections involving the four PCV types was observed to be 12.7% in nursery pigs, 16.8% in fattening pigs, and 22.4% in sows. Notably, no strong correlation was identified between any two co-detected PCV types across all pig age categories. The findings of this study contribute valuable insights into the infection dynamics of PCVs across different pig age groups. Additionally, this research offers critical reference information for devising strategies to prevent PCV infections in intensive pig farming operations in China. Full article

With the rise of smart agriculture and the expansion of pig farming, pig aggressive behavior recognition is crucial for maintaining herd health and improving farming efficiency. The differences in background and light variation in different barns can lead to the missed detection and false detection of pig aggressive behaviors. Therefore, we propose a deep learning-based pig aggressive behavior recognition model, in order to improve the adaptability of the model in complex pig environments. This model, combined with MobileNetV2 and Autoformer, can effectively extract local detail features of pig aggression and temporal correlation information of video frame sequences. Both Convolutional Block Attention Module (CBAM) and Advanced Filtering Feature Fusion Pyramid Network (HS-FPN) are integrated into the lightweight convolutional network MobileNetV2, which can more accurately capture key visual features of pig aggression and enhance the ability to detect small targets. We extract temporal correlation information between consecutive frames by the improved Autoformer. The Gate Attention Unit (GAU) is embedded into the Autoformer encoder in order to focus on important features of pig aggression while reducing computational latency. Experimental validation was implemented on public datasets, and the results showed that the classification recall, precision, accuracy, and F1-score of the model proposed in this paper reach 98.08%, 94.44%, 96.23%, and 96.23%, and the parameter quantity is optimized to 10.41 M. Compared with MobileNetV2-LSTM and MobileNetV2-GRU, the accuracy has been improved by 3.5% and 3.0%, respectively. Therefore, this model achieves a balance between recognition accuracy and computational complexity and is more suitable for automatic pig aggression recognition in practical farming scenarios, providing data support for scientific feeding and management strategies in pig farming. Full article

Leptospirosis is one of the world’s major neglected tropical zoonotic diseases (NTZDs), implicated in animal health and welfare with economic consequences for livestock production. This study aims to estimate the seroprevalence of Leptospira spp. and identify potential risk factors in small ruminant herds. This epidemiological cross-sectional study was conducted in Nuevo León, a semi-arid region of Mexico. A total of 389 blood samples from goats and 385 from sheep older than eight months were randomly collected from 128 herds. Anti-Leptospira antibodies were detected using the microscopic agglutination test (MAT), and univariate and multivariate logistic regression analyses were performed to determine their association with leptospirosis infection. The overall prevalence was 13.5% (105/774), with 14.4% (56/389) in goats and 12.7% (49/385) in sheep. Sejroe was the most predominant serogroup. The main risk factors in sheep were contact with domestic cattle, ≥100 animals per herd, congenital abnormalities, contact with feral pigs, meat production system, absence of veterinary care, and abortions with odds ratios (OR) between 1.7 and 4.1. In goats, the main risk factors included lack of quarantine measures, contact with feral pigs, absence of veterinary care, and abortions where the OR ranged from 1.7 to 3.3. These findings indicate that Leptospira spp. is present in small ruminant herds. This is the first study aimed at understanding leptospirosis epidemiology in the northeastern region of Mexico, as goats and sheep may act as potential reservoirs. Continuous monitoring of Leptospira infections is imperative, as well as developing educational initiatives for farmers to implement biosecurity and prevention measures to prevent infections within herds and protect public health. Full article

Background: Since 2011, re-emerging pseudorabies virus (PRV) variant strains have been widespread in swine herds immunized with the classical PRV vaccine in China, suggesting that it is necessary to develop a new vaccine against these PRV variant strains. Methods: Here, based on a PRV mutant strain isolated in Jinmen (JM), two recombinant strains were constructed using CRISPR/Cas9 technology, including PRV-JM-ΔEK with the deletion of the gE and TK genes and PRV-JM-ΔEI92K with the deletion of the gE, gI, US2, US9, and TK genes. Results: A one-step growth curve and plaque assay revealed that the cell-to-cell transmission ability of PRV-JM-ΔEI92K was lower than that of PRV-JM-ΔEK. However, the replication ability of PRV-JM-ΔEI92K was approximately 10 times higher than that of PRV-JM-ΔEK, similar to wild-type PRV-JM. The intramuscular injection of 10⁶ TCID₅₀ of PRV-JM-ΔEK or PRV-JM-ΔEI92K could not cause death in mice, and both could produce specific antibodies against gB and gD. The survival rate of mice immunized with both recombinant viruses was 100% when the mice were challenged by the PRV-JM strain. Histopathological sections from the PRV-JM-ΔEK group showed milder pathological changes compared to the PRV-JM-ΔEI92K group, proving that PRV-JM-ΔEK provided more effective protection. In pigs injected with 10⁶ TCID₅₀ of PRV-JM-ΔEK or PRV-JM-ΔEI92K, their body temperature did not rise, and their weight gain was not affected. Both recombinant viruses could induce the production of gB- and gD-specific antibodies and neutralizing antibodies. After the challenge of the PRV-JM virus, neutralizing antibody production was rapidly induced and lasted for at least 3 weeks. Pigs immunized with both PRV-JM-ΔEI92K and PRV-JM-ΔEK had a 100% survival rate, demonstrating that both recombinant viruses could provide effective protection. Conclusions: Compared with PRV-JM-ΔEK, PRV-JM-ΔEI92K had better safety. In conclusion, we constructed two PRV recombinant viruses, which have the potential to be used as a live carrier vaccine. Full article

Nipah virus (NiV) is a severe zoonotic pathogen that substantially threatens public health. Pigs are the natural hosts of NiV and can potentially transmit this disease to humans. Establishing a rapid, sensitive, and accurate point-of-care detection method is critical in the timely identification of infected pig herds. In this study, we developed an NiV detection method based on reverse transcription–recombinase polymerase amplification (RT-RAA) and the clustered regularly interspaced short palindromic repeats (CRISPR)-associated protein 13a (Cas13a) system for the precise detection of NiV. The highly conserved region of the NiV gene was selected as the detection target. We first designed eleven pairs of RT-RAA primers, and the optimal primer combination and reaction temperature were identified on the basis of RT-RAA efficiency. Additionally, the most efficient crRNA sequence was selected on the basis of the fluorescence signal intensity. The results revealed that the optimal reaction temperature for the developed method was 37 °C. The detection limit was as low as 1.565 copies/μL. Specificity testing revealed no cross-reactivity with nucleic acids from six common swine viruses, including Seneca virus A (SVA), foot-and-mouth disease virus (FMDV), classical swine fever virus (CSFV), porcine epidemic diarrhea virus (PEDV), African swine fever virus (ASFV), and pseudorabies virus (PRV). A validation test using simulated clinical samples revealed a 100% concordance rate. The detection results can be visualized via a fluorescence reader or lateral flow strips (LFSs). Compared with conventional detection methods, this RT-RAA-CRISPR/Cas13a-based method is rapid and simple and does not require scientific instruments. Moreover, the reagents can be freeze-dried for storage, eliminating the need for cold-chain transportation. This detection technology provides a convenient and efficient new tool for the point-of-care diagnosis of NiV and for preventing and controlling outbreaks. Full article

Hepatitis E viruses (HEV) cause hepatitis E in humans. In industrialized countries, sporadic HEV infections, typically caused by HEV genotypes 3 or 4, can become chronic and progress to liver cirrhosis in immunocompromised individuals. Pigs are a significant animal reservoir, implicating raw or undercooked pork products as potential sources of human infection. To better understand HEV dissemination in the Belgian pig population, potential risk factors were investigated by linking farm-level HEV serological status to biosecurity questionnaire data. Farrow-to-finish herd type, free-range systems, and poor boot hygiene were significantly associated with higher within-herd prevalences. This enabled an initial risk profiling of various farming types and the development of predictions for all Belgian pig farms. When combined with the census of the Belgian wild boar population, the predicted HEV status of all professional Belgian pig farms (based on these associations) does not suggest that the proximity of wild boars is a main source of HEV in free-ranging herds. Identifying risk factors for increased circulation of HEV between and within pig farms is critical to controlling its spread and reducing human infection. Full article

Effective pig farming relies on precise and adaptable animal identification methods, particularly in dynamic environments where new pigs are regularly added to the herd. However, pig face recognition is challenging due to high individual similarity, lighting variations, and occlusions. These factors hinder accurate identification and monitoring. To address these issues under Open-Set conditions, we propose a three-phase Pig Face Open-Set Recognition (PFOSR) system. In the Training Phase, we adopt a decoupled design, first training a YOLOv8-based pig face detection model on a small labeled dataset to automatically locate pig faces in raw images. We then refine a Vision Transformer (ViT) recognition model via a dual-loss strategy—combining Sub-center ArcFace and Center Loss—to enhance both inter-class separation and intra-class compactness. Next, in the Known Pig Registration Phase, we utilize the trained detection and recognition modules to extract representative embeddings from 56 identified pigs, storing these feature vectors in a Pig Face Feature Gallery. Finally, in the Unknown and Known Pig Recognition and Registration Phase, newly acquired pig images are processed through the same detection–recognition pipeline, and the resulting embeddings are compared against the gallery via cosine similarity. If the system classifies a pig as unknown, it dynamically assigns a new ID and updates the gallery without disrupting existing entries. Our system demonstrates strong Open-Set recognition, achieving an AUROC of 0.922, OSCR of 0.90, and F1-Open of 0.94. In the closed set, it attains a precision@1 of 0.97, NMI of 0.92, and mean average precision@R of 0.96. These results validate our approach as a scalable, efficient solution for managing dynamic farm environments with high recognition accuracy, even under challenging conditions. Full article

Porcine viral diarrhea has always been one of the main obstacles to the healthy development of the pig industry in China with its variety of pathogens and complexity of co-infections. Analysis of the dominant mixed-infection model is a fundamental step in boosting the prevention and control of porcine diarrhea. In this study, 3256 porcine fecal samples were collected from 17 pig herds in Shanghai, China, from 2015 to 2023 to identify novel pathogenic infection patterns. The results confirmed that porcine astrovirus (PAstV), porcine sapelovirus (PSV), and porcine epidemic diarrhea virus (PEDV) were the top three agents with positive rates of 28.47%, 20.71%, and 20.23%, respectively. Porcine rotavirus (PoRV) and transmissible gastroenteritis virus (TGEV) accounted for only 8.12% and 1.12%, respectively. Importantly, mixed infection rates were high and complicated. The double infection rate was higher than that of a single infection. Next, the mixed-infection model of PEDV and emerging diarrheal pathogens was explored. The predominant dual-infection models were PEDV/PKoV (porcine kobuvirus) (14.18%), PEDV/PAstV (10.02%), and PEDV/PSV (9.29%). The predominant triple infection models were PEDV/PKoV/PAstV (18.93%), PEDV/PSV/PAstV (10.65%), and PEDV/PKoV/PSV (7.10%). The dominant quadruple-infection model was PEDV/PAstV/PSV/PKoV (46.82%). In conclusion, PEDV is mainly mix-infected with PAstV, PSV, and PKoV in clinical settings. Furthermore, multiple-factor logistic regression analysis confirmed that PAstV, PKoV, bovine viral diarrhea virus (BVDV), and PEDV were closely related to porcine diarrhea. PEDV/PKoV, PEDV/porcine sapovirus (PoSaV), PKoV/BVDV, PoSaV/BVDV, and porcine deltacoronavirus (PDCoV)/PoSaV had great co-infection dominance, which will be helpful for porcine co-infection research. Full article

Background/Objectives: Porcine reproductive and respiratory syndrome virus (PRRSV) is classified into various lineages based on the phylogenetic variation of orf5, which encodes a major surface glycoprotein GP5 containing both neutralizing and non-neutralizing linear epitopes. Several positively selected sites have been identified on the GP5 ectodomain, indicating host immune pressure on these sites. This present study aimed to investigate the kinetics of antibody responses to GP5 and to map the epitope-specific response to the GP5 ectodomain from different PRRSV lineages after vaccination with commercially available modified live virus (MLV) vaccines. Methods: Post-weaning pigs were vaccinated with MLV vaccines derived from either lineage 1D (Prevacent PRRS^®) or lineage 5 (Ingelvac PRRS^®). Animals were challenged with a heterologous (lineage 1A) strain at 64 days post-vaccination (dpv). Blood samples were collected at various times post-vaccination and challenge. Kinetics of antibody response to different PRRSV antigens were monitored and virus neutralization against archetypal and contemporary strains belonging to lineage 5 and 1A were evaluated. In addition, antibody responses to peptides derived from the GP5 ectodomain of different viral lineages were assessed. Results: Our results showed that the GP5-specific antibody response observed between 18 and 35 dpv was delayed compared to responses to the viral nucleocapsid protein. The polyclonal antibody response in both vaccinated groups showed similar levels of binding to variant GP5 peptides from different sub-lineages. Notably, in both vaccinated groups, the antibody directed to a peptide representing the GP5 ectodomain of a lineage 1C strain (variant 1C.5) displayed a rise in titer at 64 dpv, which was further increased by the challenge with the lineage 1A strain. Less than 50% of animals developed heterologous neutralizing antibodies post-vaccination with both MLV vaccines. However, higher neutralization titers were observed in all vaccinated animal post-challenge. Conclusions: Together, these data provide insights into the antibody responses to the GP5 ectodomain in MLV-vaccinated swine herds. Full article