Individual Pigs Research Articles

PSV-17 Threonine Requirements for Post-Weaning Pig in Individual Precision Nutrition Programs: a Meta-Analysis

Abstract Threonine (Thr) is generally the second limiting amino acid (AA) in growing pig diets, and it has a vital role in supporting intestinal functions and the immune system. Additionally, providing pigs with the correct AA requirements decreases nitrogen excretion and improves growth performance. This study aimed to determine standardized ileal digestibility (SID) Thr requirements for individual post-weaned pigs. Additionally, the Thr supplementation effect on average daily gain (ADG) of weaning and growing [7.3 – 51.5 kg of body weight (BW)] pigs under a sanitary challenge was evaluated. Eleven papers published from 1993 to 2015 composed the dataset used to determine the SID Thr requirement in the nursery phase, and five studies conducted from 2014 to 2020 composed the enteric sanitary challenge dataset. The SID Thr was obtained from publications when available or estimated based on the ingredient composition using EvaPig software. The average individual pig SID Thr requirements were estimated by bootstrapping 1,000 repetitions of a linear-plateau mixed model where all parameters were considered random as a function of the trial code. A general positive-definite matrix was used to represent the between-factors covariance using the nlme package of the R software. The effect of supplementing SID Thr above the requirement to attenuate ADG losses during a challenge was evaluated by an effect size analysis using a mixed model of the R Metafor package. Due to the low number of studies assessing pigs’ response to enteric challenges, a P < 0.25 was considered significant. In the post-weaning (14 kg average BW), the estimated ADG was 457 g/d (411 to 493 g/d) as a function of SID Thr individual requirement, which was 4.71 g/d for the average pig, with the least demanding pig requiring 4.4 g/d and the most demanding one requiring 5.1 g/d. For challenged pigs, the across-study heterogeneity was moderate (Higgs index = 36%). Increasing Thr intake by 18% above the estimated requirement attenuated (P = 0.15) ADG losses by 0.7 standard deviations (60 g) compared with pigs fed diets meeting Thr requirements. For pigs in individual precision feeding, the SID Thr requirement is estimated to be 1.03 g per 100 g of ADG for post-weaned pigs. The increase of SID Thr intake by 18% attenuated the ADG losses by 19% compared with non-supplemented pigs with enteric challenges.

PSII-16 Comparison of Microencapsulated Zinc Oxide and Conventional Zinc Oxide on Weanling Pig Small Intestinal Morphology

Abstract A total of 300 pigs (DNA 200 × 400; initially 6.04 ± 0.08 kg BW) were weaned at an average of 21 d of age and used in a 42-d experiment with 12 replications per treatment. At weaning (experiment d 0), pigs were randomly allotted to one of five dietary treatments: 1) negative control (standard nursery diet containing 110 ppm Zn from trace mineral premix); 2) control diet with 3,000 ppm added Zn in the form of ZnO in phase 1 and 2,000 ppm added Zn in the form of ZnO in phase 2 (High-ZnO); 3) control diet with 400 ppm added Zn in the form of ZnO in phases 1 and 2 (Low-ZnO); 3) 3,000 ppm added Zn in the form of microencapsulated ZnO in phase 1 and 2,000 ppm added Zn in the form of microencapsulated ZnO in phase 2 (High-MZnO); 5) 400 ppm added Zn in the form of microencapsulated ZnO in phases 1 and 2 (Low-MZnO). Pigs were fed dietary treatments from d 0 to 28. On d 28, a subset of pigs with a BW closest to the treatment mean (n = 30 total; 6 per treatment) were euthanized via captive bolt and necropsied for collection of small intestinal tissue to evaluate morphology at the Kansas State University Veterinary Diagnostic Laboratory. Briefly, after pigs were slaughtered, they were opened viscerally, and the small intestine was identified. Two samples (approximately 2 cm long) were cut from the proximal and distal ends of the ileum and fixed in formalin. Samples were then embedded in paraffin and 4 µm cross-sections were cut and stained with hematoxylin and eosin. Slides were analyzed using a microscope at 10× magnification. Measurements [villus height (VH), crypt depth (CD), and villus height:crypt depth ration (VH:CD)] were evaluated from 10 unbroken villi and their corresponding crypts. Data were analyzed using the GLIMMIX procedure of SAS (version 9.4) with individual pig as the experimental unit. No evidence of differences in proximal ileal VH (P = 0.34), proximal ileal CD (P = 0.52), and proximal ileal VH:CD (P = 0.49) were observed between dietary treatments (Table 1). Likewise, there was no evidence of differences in distal ileal VH (P = 0.63), CD (P = 0.53), or VH:CD (P = 0.80) between dietary treatments. In summary, feeding a microencapsulated form of ZnO did not appear to alter small intestinal morphology in weanling pigs compared with conventional, unprotected ZnO.

69 Monoglycerides of Butyric, Caprylic, and Capric Fatty Acids Promote Intestinal Integrity and Host Defenses in Health-Challenged Weanling Pigs

Abstract Frequent incidence of post-weaning enterotoxigenic Escherichia coli (ETEC) diarrhea in the swine industry contributes to high mortality rates and associated economic losses. In this study, the effects of butyric, caprylic, and capric monoglycerides (MG) were investigated as a way to promote intestinal integrity and host defenses in weanling pigs infected with ETEC. A total of 160 pigs of equal sex were allotted to treatment groups based on body weight and sex. Throughout the 17-d study, three treatment groups were maintained: sham-inoculated pigs fed a control diet (NC, n = 40), ETEC-inoculated pigs fed the same control diet (PC, n = 60), and ETEC-inoculated pigs fed the control diet supplemented with the test article included at 3% of the diet (Test, n = 60). Following a 7-d adaptation period, pigs were orally inoculated on each of 3 consecutive days with either 3 mL of a sham-control (saline) or live ETEC culture (3 × 109 CFU/mL). The first day of inoculation was designated as 0 d post-inoculation (DPI), and all study outcomes reference this time-point. Fecal, tissue, and blood samples were collected from 48 individual pigs (NC, n = 12; PC and Test, n = 18) on 5 and 10 DPI for analysis of dry mater (DM), bacterial enumeration, inflammatory markers, and a practical assessment of intestinal permeability. All data were analyzed by ANOVA using the MIXED procedure of SAS. During the peak infection period (5 DPI) the NC group had greater (P < 0.05) fecal DM and lower (P < 0.05) rectal temperatures, total bacteria, total E. coli, and total F18 ETEC. By 9 DPI, the NC and Test groups had numerically decreased lactulose:mannitol ratios in blood plasma compared with the PC group, which indicated possible benefits to intestinal barrier function. Overall, MG supplementation did not appear to influence differences in fecal outcomes that were altered by ETEC infection, but some benefits in intestinal integrity were observed.

199 Effects of an Additional Injection of Iron Administered to Piglets on Hemoglobin Concentration, Growth Performance, and Carcass Characteristics Through Market Weight

Abstract An experiment was conducted to evaluate the effects of an additional injection of iron dextran (Uniferon, Pharmacosmos Inc.) administered at d 6 to 8 of age. Crossbred pigs [n = 144; equal barrows and gilts; initial body weight (BW) = 2.86 ± 0.01 kg] from 21 litters were assigned to either the control (CON) or an added-injection treatment (+Fe). Pigs were paired by sex and BW within a litter and randomly assigned to the iron treatment within each pair. All pigs had received a 200 mg Fe intramuscular (IM) injection < 24 h after birth. All pigs were weaned at 22 to 24 days, housed 6 pigs/pen for a total of 12 pens/treatment, and received a common corn-soybean meal diet formulated to meet or exceed the NRC (2012) requirement estimates relative to BW until slaughter. Body weight and feed disappearance were recorded at least biweekly to determine average daily gain (ADG) and feed intake (ADFI). Hemoglobin (Hb) concentrations were measured at birth, initiation of experiment (d 6 to 8), weaning, and at the end of the nursery and finisher periods. At the time of slaughter, 1 pig/pen (n = 12 pigs/treatment) was selected and slaughtered for carcass characteristic measures. Data were subjected to ANOVA by the GLM procedure of SAS; the individual pig served as the experimental unit for BW, Hb, ADG, and carcass characteristics whereas pen served as the experimental unit for ADFI, and gain/feed ratio data. The statistical model included sex, treatment, sex × treatment, and allotment pair for Hb and ADG. There were expected sex effects for ADG but no sex × treatment interactions for any response measures. The +Fe pigs had a greater Hb at weaning (13.1 vs. 10.7 g/dL, P < 0.0001) and end of the nursery (12.1 vs. 11.7 g/dL, P = 0.01) compared with CON pigs (Table 1). During the finisher period, +Fe pigs had a greater ADG (P = 0.05) compared with CON pigs. Overall, pigs receiving the added iron injection had an ~ 4% increase in ADG (P = 0.04) from weaning to slaughter. The cumulative improvement in ADG from weaning to slaughter observed for +Fe group resulted in +Fe pigs having a heavier BW at the end of the experiment (115.77 vs. 112.79 kg; P = 0.04). Following slaughter, +Fe pigs had ~ 2.5% heavier cold carcass weight (82.99 vs. 80.93 kg; P = 0.34) and trimmed loin (10.67 vs. 9.95 kg; P = 0.04) compared with the CON pigs. In conclusion, administering an additional iron injection resulted in greater Hb at weaning and the end of the nursery as well as improved growth performance from weaning to slaughter weight and increased carcass measures at slaughter.

38 The Effects of Lysine and Antibiotic Usage on Early Nursery Pig Performance

Abstract Weaning transition, early nursery environment, and the diet is critical for nursery pig performance and health. Nutritional interventions (i.e., low crude protein diets achieved via decreased SID lysine) and water or in-feed antibiotics are often used to aid in this transition in pig flows prone to endemic enteric pathogens. Therefore, the objective of this study was to investigate the effects of high or low dietary lysine curves, with or without antibiotics, in the first two phases of production on early nursery pig performance. A total of 384 weaned nursery pigs (starting body weight of 5.3 ± 1.6 kg) were randomly assigned to split sex pens (8 pigs/pen) over a 21-day study. Using a 2x2 factorial arrangment, pens were fed one of two dietary treatments over phase 1 (P1) and 2 (P2), with or without antibiotics (n = 12 pens/treatment). The treatments consisted of: 1) low lysine curve (1.15% and 1.2% SID Lys, respectively; LLys); 2) high lysine curve (1.45% and 1.375% SID Lys, respectively; HLys); 3) LLys + antibiotics (LLys+); and 4) HLys + antibiotics (HLys+). During P1, LLys+ and HLys+ received water soluble gentamicin for 5 days, while 50 g/ton Mecadox was added to the LLys+ and HLys+ P2 diets. Four days post-placement, pigs were confirmed positive for Rotavirus and hemolytic E. coli. Individual pig body weights and pen feed disappearance were collected on day 7, 14 and 21 to calculate ADG, ADFI, and G:F. Fecal consistency was scored daily by pen. Data were analyzed with pen as the experimental unit and least squares means reported with the fixed effects of lysine, antibiotics, and their interaction. Regardless of dietary treatment or antibiotic usage, LLys, HLys, LLys+, and HLys+ ADG (0.21, 0.22, 0.20, and 0.21 kg/d, respectively) or ADFI (0.30, 0.28, 0.28, and 0.28 kg/d, respectively) were not different over the 21-day period (P > 0.05). No lysine by antibiotic interactions were reported for any variable measured (P > 0.05). Pig removals and mortalities ranged from 1-4% and did not differ between treatments (P > 0.05). No fixed effects were observed in P1 variables. Although growth rates did not differ, G:F was greater in HLys compared with LLys fed pigs in P2 (0.78 vs. 0.73, P = 0.016) and overall (0.75 vs. 0.69, P = 0.031). Antibiotic usage had no effect on P1, P2, or overall performance parameters. In conclusion, feeding pigs on a high lysine curve or utilizing water soluble and in-feed antibiotics shows minimal benefit to young pigs with a natural enteric pathogen burden.

Visual Detection of Lost Ear Tags in Breeding Pigs in a Production Environment Using the Enhanced Cascade Mask R-CNN

As the unique identifier of individual breeding pigs, the loss of ear tags can result in the loss of breeding pigs’ identity information, leading to data gaps and confusion in production and genetic breeding records, which can have catastrophic consequences for breeding efforts. Detecting the loss of ear tags in breeding pigs can be challenging in production environments due to factors such as overlapping breeding pig clusters, imbalanced pig-to-tag ratios, and relatively small-sized ear tags. This study proposes an improved method for the detection of lost ear tags in breeding pigs based on Cascade Mask R-CNN. Firstly, the model utilizes ResNeXt combined with a feature pyramid network (FPN) as the feature extractor; secondly, the classification branch incorporates the online hard example mining (OHEM) technique to improve the utilization of ear tags and low-confidence samples; finally, the regression branch employs a decay factor of Soft-NMS to reduce the overlap of redundant bounding boxes. The experiment employs a sliding window detection method to evaluate the algorithm’s performance in detecting lost ear tags in breeding pigs in a production environment. The results show that the accuracy of the detection can reach 92.86%. This improvement effectively enhances the accuracy and real-time performance of lost ear tag detection, which is highly significant for the production and breeding of breeding pigs.

Agar Contact Method as a Valuable Tool to Identify Slaughter Hygiene Deficiencies along the Slaughter Process by Longitudinally Sampling Pig Skin Surfaces.

Examinations of total viable counts (TVCs) and Salmonella spp. on the skin of individual pigs during the slaughter process are useful to identify abattoir-specific risk factors for (cross-)contamination. At seven process stages (lairage to before chilling), pigs were bacteriologically investigated by repeatedly sampling the same animals using the agar contact method. The mean TVC of all pigs increased significantly at the first three tested process stages (mean count, after delivery: 5.70 log cfu/cm2, after showering: 6.27 log cfu/cm2, after stunning: 6.48 log cfu/cm2). Significant mean TVC reductions occurred after scalding/dehairing (mean count: 3.71 log cfu/cm2), after singeing/flaming (2.70 log cfu/cm2), and after evisceration (2.44 log cfu/cm2) compared with the respective preceding process stages. At the end of the slaughter line and before chilling, the mean TVC was 2.33 log cfu/cm2, showing that the slaughter process reduced contamination significantly. The slaughter process effectively reduced even very high levels of incoming TVCs, since at the individual animal level, at the end of the slaughter process, there was no difference in the TVCs of animals with initially high and initially low TVCs. Additionally, 12 Salmonella spp. isolates were recovered from 12 different pigs, but only until the stage after scalding/dehairing. Overall, the agar contact method used is valuable for detecting hygiene deficiencies at slaughter, and is animal-equitable, practical, and suitable for use on live animals.

Does Vaccine-Induced Maternally-Derived Immunity Protect Swine Offspring against Influenza a Viruses? A Systematic Review and Meta-Analysis of Challenge Trials from 1990 to May 2021.

It is unclear if piglets benefit from vaccination of sows against influenza. For the first time, methods of evidence-based medicine were applied to answer the question: "Does vaccine-induced maternally-derived immunity (MDI) protect swine offspring against influenza A viruses?". Challenge trials were reviewed that were published from 1990 to April 2021 and measured at least one of six outcomes in MDI-positive versus MDI-negative offspring (hemagglutination inhibition (HI) titers, virus titers, time to begin and time to stop shedding, risk of infection, average daily gain (ADG), and coughing) (n = 15). Screening and extraction of study characteristics was conducted in duplicate by two reviewers, with data extraction and assessment for risk of bias performed by one. Homology was defined by the antigenic match of vaccine and challenge virus hemagglutinin epitopes. Results: Homologous, but not heterologous MDI, reduced virus titers in piglets. There was no difference, calculated as relative risks (RR), in infection incidence risk over the entire study period; however, infection hazard (instantaneous risk) was decreased in pigs with MDI (log HR = -0.64, 95% CI: -1.13, -0.15). Overall, pigs with MDI took about a ½ day longer to begin shedding virus post-challenge (MD = 0.51, 95% CI: 0.03, 0.99) but the hazard of infected pigs ceasing to shed was not different (log HR = 0.32, 95% CI: -0.29, 0.93). HI titers were synthesized qualitatively and although data on ADG and coughing was extracted, details were insufficient for conducting meta-analyses. Conclusion: Homology of vaccine strains with challenge viruses is an important consideration when assessing vaccine effectiveness. Herd viral dynamics are complex and may include concurrent or sequential exposures in the field. The practical significance of reduced weaned pig virus titers is, therefore, not known and evidence from challenge trials is insufficient to make inferences on the effects of MDI on incidence risk, time to begin or to cease shedding virus, coughing, and ADG. The applicability of evidence from single-strain challenge trials to field practices is limited. Despite the synthesis of six outcomes, challenge trial evidence does not support or refute vaccination of sows against influenza to protect piglets. Additional research is needed; controlled trials with multi-strain concurrent or sequential heterologous challenges have not been conducted, and sequential homologous exposure trials were rare. Consensus is also warranted on (1) the selection of core outcomes, (2) the sizing of trial populations to be reflective of field populations, (3) the reporting of antigenic characterization of vaccines, challenge viruses, and sow exposure history, and (4) on the collection of non-aggregated individual pig data.

Circadian rhythms and diurnal patterns in the feed intake behaviour of growing-finishing pigs

The feeding behaviour of growing-finishing pigs is an important indicator of performance, health and welfare, but this use is limited by its large, poorly-understood variation. We explored the variation in basal feed intake of individual pigs by detecting circadian rhythms, extracting features of diurnal patterns and assessing consistency over time, from day-to-day and across age. Hourly feed intake data of individual pigs (n = 110) was obtained during one growing-finishing phase, using electronic feeding stations. We applied wavelet analysis to assess rhythms and a hurdle generalised additive model to extract features of diurnal patterns. We found that circadian rhythms could be detected during 58 ± 3% (mean ± standard error) of days in the growing-finishing phase (range 0–100%), predominantly at older ages. Although the group diurnal intake pattern was alternans (small morning peak, larger afternoon peak), individual pigs showed a range of diurnal patterns that changed with age, differing mostly in the extent of night fasting and day-to-day consistency. Our results suggest that the type, day-to-day consistency and age development of diurnal patterns in feed intake show general group patterns but also differ between pigs. Using this knowledge, promising features may be selected to compare against production, health and welfare parameters.

The effects of antibiotic use on the dynamics of the microbiome and resistome in pigs

Antibiotics are widely used in pig farming across the world which has led to concerns about the potential impact on human health through the selection of antibiotic resistant pathogenic bacteria. This worry has resulted in the development of a production scheme known as pigs Raised Without Antibiotics (RWA), in which pigs are produced in commercial farms, but are ear-tagged as RWA until slaughter unless they receive treatment, thus allowing the farmer to sell the pigs either as premium priced RWA or as conventional meat. Development of antibiotic resistance in pig farming has been studied in national surveys of antibiotic usage and resistance, as well as in experimental studies of groups of pigs, but not in individual pigs followed longitudinally in a commercial pig farm. In this study, a cohort of RWA designated pigs were sampled at 10 time points from birth until slaughter along with pen-mates treated with antibiotics at the same farm. From these samples, the microbiome, determined using 16S sequencing, and the resistome, as determined using qPCR for 82 resistance genes, was investigated, allowing us to examine the difference between RWA pigs and antibiotic treated pigs. We furthermore included 176 additional pigs from six different RWA farms which were sampled at the slaughterhouse as an endpoint to substantiate the cohort as well as for evaluation of intra-farm variability. The results showed a clear effect of age in both the microbiome and resistome composition from early life up until slaughter. As a function of antibiotic treatment, however, we observed a small but significant divergence between treated and untreated animals in their microbiome composition immediately following treatment, which disappeared before 8 weeks of age. The effect on the resistome was evident and an effect of treatment could still be detected at week 8. In animals sampled at the slaughterhouse, we observed no difference in the microbiome or the resistome as a result of treatment status but did see a strong effect of farm origin. Network analysis of co-occurrence of microbiome and resistome data suggested that some resistance genes may be transferred through mobile genetic elements, so we used Hi-C metagenomics on a subset of samples to investigate this. We conclude that antibiotic treatment has a differential effect on the microbiome vs. the resistome and that although resistance gene load is increased by antibiotic treatment load, this effect disappears before slaughter. More studies are needed to elucidate the optimal way to rear pigs without antibiotics.

PCA 前处理对 KNN 识别猪脸的影响研究

To explore the application of traditional machine learning model in the intelligent management of pigs, in this paper, the influence of the PCA pre-treatment on pig face identification with KNN is studied. With testing method, individual identification test was carried out on 10 different pigs in two testing schemes, in which one adopted KNN alone and the other adopted PCA + KNN, for which the classifier parameter was taken as 3 and 5, respectively. In the optimized scheme, the operating efficiency got significantly increased, also the training time and testing time were reduced to 4.8% and 7% of the original value in the KNN alone scheme, though the accuracy got lowered to a certain extent. With all these factors taken into consideration, PCA pre-treatment is beneficial to individual pig identification with KNN. It can provide experimental support for mobile terminals and embedded application of KNN classifiers.

GANPose: Pose estimation of grouped pigs using a generative adversarial network

Pose estimation as an effective method for behaviour detection has attracted wide attention in the field of animal health and welfare detection in recent years. Consequently, we can monitor individual pig behaviour changes over time, which will assist in the early detection of disease, allowing for earlier and more effective intervention. However, a real farming scenario with occlusions and opaque pig clustering may be a challenging computer vision problem. Inspired by human vision, we propose GANPose, a grouped pig pose estimation model based on a generative adversarial network (GAN). This model uses the adversarial game to induce the model to learn prior information about the pig's body structure and output a pose with a reasonable skeleton structure. In addition, we also established a new pig pose estimation dataset, which not only included the basic back keypoints but also small keypoints, such as leg, elbow, and tail, as well as challenging occluded keypoints. This work is the study to tackle the occlusion problem, with a finely tuned GAN structure. Experiments and quantitative results on our dataset show that GANPose can detect keypoints of herd pigs with 74.09 % mAP, and the accuracy of the percentage of correct keypoint (PCK) is 11.37 % higher than the benchmark for occluded keypoints, achieving excellent performance in a real pigsty environment.

102. Synthesis: Genetic predisposition and expression of tail biting behaviour in relation to individual pig characteristics

102. Synthesis: Genetic predisposition and expression of tail biting behaviour in relation to individual pig characteristics

Enhanced camera-based individual pig detection and tracking for smart pig farms

Negative social interactions are harmful for animal health and welfare. It is increasingly important to employ a continuous and effective monitoring system for detecting and tracking individual animals in large-scale farms. Such a system can provide timely alarms for farmers to intervene when damaging behavior occurs. Deep learning combined with camera-based monitoring is currently arising in agriculture. In this work, deep neural networks are employed to assist individual pig detection and tracking, which enables further analyzing behavior at the individual pig level. First, three state-of-the-art deep learning-based Multi-Object Tracking (MOT) methods are investigated, namely Joint Detection and Embedding (JDE), FairMOT, and YOLOv5s with DeepSORT. All models facilitate automated and continuous individual detection and tracking. Second, weighted-association algorithms are proposed for each MOT method, in order to optimize the object re-identification (re-ID), and improve the individual animal-tracking performance, especially for reducing the number of identity switches. The proposed weighted-association methods are evaluated on a large manually annotated pig dataset, and compared with the state-of-the-art methods. FairMOT with the proposed weighted association achieves the highest IDF1, the least number of identity switches, and the fastest execution rate. YOLOv5s with DeepSORT results in the highest MOTA and MOTP tracking metrics. These methods show high accuracy and robustness for individual pig tracking, and are promising candidates for continuous multi-object tracking for real use in commercial farms.

Attention-Guided Instance Segmentation for Group-Raised Pigs.

In the pig farming environment, complex factors such as pig adhesion, occlusion, and changes in body posture pose significant challenges for segmenting multiple target pigs. To address these challenges, this study collected video data using a horizontal angle of view and a non-fixed lens. Specifically, a total of 45 pigs aged 20-105 days in 8 pens were selected as research subjects, resulting in 1917 labeled images. These images were divided into 959 for training, 192 for validation, and 766 for testing. The grouped attention module was employed in the feature pyramid network to fuse the feature maps from deep and shallow layers. The grouped attention module consists of a channel attention branch and a spatial attention branch. The channel attention branch effectively models dependencies between channels to enhance feature mapping between related channels and improve semantic feature representation. The spatial attention branch establishes pixel-level dependencies by applying the response values of all pixels in a single-channel feature map to the target pixel. It further guides the original feature map to filter spatial location information and generate context-related outputs. The grouped attention, along with data augmentation strategies, was incorporated into the Mask R-CNN and Cascade Mask R-CNN task networks to explore their impact on pig segmentation. The experiments showed that introducing data augmentation strategies improved the segmentation performance of the model to a certain extent. Taking Mask-RCNN as an example, under the same experimental conditions, the introduction of data augmentation strategies resulted in improvements of 1.5%, 0.7%, 0.4%, and 0.5% in metrics AP50, AP75, APL, and AP, respectively. Furthermore, our grouped attention module achieved the best performance. For example, compared to the existing attention module CBAM, taking Mask R-CNN as an example, in terms of the metric AP50, AP75, APL, and AP, the grouped attention outperformed 1.0%, 0.3%, 1.1%, and 1.2%, respectively. We further studied the impact of the number of groups in the grouped attention on the final segmentation results. Additionally, visualizations of predictions on third-party data collected using a top-down data acquisition method, which was not involved in the model training, demonstrated that the proposed model in this paper still achieved good segmentation results, proving the transferability and robustness of the grouped attention. Through comprehensive analysis, we found that grouped attention is beneficial for achieving high-precision segmentation of individual pigs in different scenes, ages, and time periods. The research results can provide references for subsequent applications such as pig identification and behavior analysis in mobile settings.

YOLOv5-KCB: A New Method for Individual Pig Detection Using Optimized K-Means, CA Attention Mechanism and a Bi-Directional Feature Pyramid Network.

Individual identification of pigs is a critical component of intelligent pig farming. Traditional pig ear-tagging requires significant human resources and suffers from issues such as difficulty in recognition and low accuracy. This paper proposes the YOLOv5-KCB algorithm for non-invasive identification of individual pigs. Specifically, the algorithm utilizes two datasets-pig faces and pig necks-which are divided into nine categories. Following data augmentation, the total sample size was augmented to 19,680. The distance metric used for K-means clustering is changed from the original algorithm to 1-IOU, which improves the adaptability of the model's target anchor boxes. Furthermore, the algorithm introduces SE, CBAM, and CA attention mechanisms, with the CA attention mechanism being selected for its superior performance in feature extraction. Finally, CARAFE, ASFF, and BiFPN are used for feature fusion, with BiFPN selected for its superior performance in improving the detection ability of the algorithm. The experimental results indicate that the YOLOv5-KCB algorithm achieved the highest accuracy rates in pig individual recognition, surpassing all other improved algorithms in average accuracy rate (IOU = 0.5). The accuracy rate of pig head and neck recognition was 98.4%, while the accuracy rate for pig face recognition was 95.1%, representing an improvement of 4.8% and 13.8% over the original YOLOv5 algorithm. Notably, the average accuracy rate of identifying pig head and neck was consistently higher than pig face recognition across all algorithms, with YOLOv5-KCB demonstrating an impressive 2.9% improvement. These results emphasize the potential for utilizing the YOLOv5-KCB algorithm for precise individual pig identification, facilitating subsequent intelligent management practices.

Evaluation of a Porcine Endogenous Reference Gene (Internal Sample Control) in a Porcine Reproductive and Respiratory Syndrome Virus RT-qPCR.

Endogenous reference genes are used in gene-expression studies to "normalize" the results and, increasingly, as internal sample controls (ISC) in diagnostic quantitative polymerase chain reaction (qPCR). Three studies were conducted to evaluate the performance of a porcine-specific ISC in a commercial porcine reproductive and respiratory syndrome virus (PRRSV) reverse transcription-qPCR. Study 1 evaluated the species specificity of the ISC by testing serum from seven non-porcine domestic species (n = 34). In Study 2, the constancy of ISC detection over time (≥42 days) was assessed in oral fluid (n = 130), serum (n = 215), and feces (n = 132) collected from individual pigs of known PRRSV status. In Study 3, serum (n = 150), oral fluid (n = 150), and fecal samples (n = 75 feces, 75 fecal swabs) from commercial herds were used to establish ISC reference limits. Study 1 showed that the ISC was porcine-specific, i.e., all samples from non-porcine species were ISC negative (n = 34). In Study 2, the ISC was detected in all oral fluid, serum, and fecal samples, but differed in concentration between specimens (p < 0.05; mixed-effects regression model). The results of Study 3 were used to establish ISC reference limits for the 5th, 2.5th and 1.25th percentiles. Overall, the ISC response was consistent to the point that failure in detection is sufficient justification for re-testing and/or re-sampling.

Individual Pig Identification Using Back Surface Point Clouds in 3D Vision.

The individual identification of pigs is the basis for precision livestock farming (PLF), which can provide prerequisites for personalized feeding, disease monitoring, growth condition monitoring and behavior identification. Pig face recognition has the problem that pig face samples are difficult to collect and images are easily affected by the environment and body dirt. Due to this problem, we proposed a method for individual pig identification using three-dimension (3D) point clouds of the pig's back surface. Firstly, a point cloud segmentation model based on the PointNet++ algorithm is established to segment the pig's back point clouds from the complex background and use it as the input for individual recognition. Then, an individual pig recognition model based on the improved PointNet++LGG algorithm was constructed by increasing the adaptive global sampling radius, deepening the network structure and increasing the number of features to extract higher-dimensional features for accurate recognition of different individuals with similar body sizes. In total, 10,574 3D point cloud images of ten pigs were collected to construct the dataset. The experimental results showed that the accuracy of the individual pig identification model based on the PointNet++LGG algorithm reached 95.26%, which was 2.18%, 16.76% and 17.19% higher compared with the PointNet model, PointNet++SSG model and MSG model, respectively. Individual pig identification based on 3D point clouds of the back surface is effective. This approach is easy to integrate with functions such as body condition assessment and behavior recognition, and is conducive to the development of precision livestock farming.

Molecular Signatures in Swine Innate and Adaptive Immune Responses to African Swine Fever Virus Antigens p30/p54/CD2v Expressed Using a Highly Efficient Semliki Forest Virus Replicon System.

African swine fever virus (ASFV) causes a devastating viral hemorrhagic disease in domestic pigs and Eurasian wild boars, posing a foremost threat to the swine industry and pig farming. The development of an effective vaccine is urgently needed, but has been hampered by the lack of an in-depth, mechanistic understanding of the host immune response to ASFV infection and the induction of protective immunity. In this study, we report that immunization of pigs with Semliki Forest Virus (SFV) replicon-based vaccine candidates expressing ASFV p30, p54, and CD2v, as well as their ubiquitin-fused derivatives, elicits T cell differentiation and expansion, promoting specific T cell and humoral immunity. Due to significant variations in the individual non-inbred pigs in response to the vaccination, a personalized analysis was conducted. Using integrated analysis of differentially expressed genes (DEGs), Venn, KEGG and WGCNA, Toll-like receptor, C-type lectin receptor, IL17 receptor, NOD-like receptor and nucleic acid sensor-mediated signaling pathways were demonstrated to be positively correlated to the antigen-stimulated antibody production and inversely correlated to the IFN-γ secreting cell counts in peripheral blood mononuclear cells (PBMCs). An up-regulation of CIQA, CIQB, CIQC, C4BPA, SOSC3, S100A8 and S100A9, and down-regulation of CTLA4, CXCL2, CXCL8, FOS, RGS1, EGR1 and SNAI1 are general in the innate immune response post-the second boost. This study reveals that pattern recognition receptors TLR4, DHX58/DDX58 and ZBP1, and chemokines CXCL2, CXCL8 and CXCL10 may play important roles in regulating this vaccination-stimulated adaptive immune response.

Study on the Influence of PCA Pre-Treatment on Pig Face Identification with Random Forest.

To explore the application of a traditional machine learning model in the intelligent management of pigs, in this paper, the influence of PCA pre-treatment on pig face identification with RF is studied. By this testing method, the parameters of two testing schemes, one adopting RF alone and the other adopting RF + PCA, were determined to be 65 and 70, respectively. With individual identification tests carried out on 10 pigs, accuracy, recall, and f1-score were increased by 2.66, 2.76, and 2.81 percentage points, respectively. Except for the slight increase in training time, the test time was reduced to 75% of the old scheme, and the efficiency of the optimized scheme was greatly improved. It indicates that PCA pre-treatment positively improved the efficiency of individual pig identification with RF. Furthermore, it provides experimental support for the mobile terminals and the embedded application of RF classifiers.