Abstract The global pork industry has made significant genetic improvements over the last 30 years and nearly doubled the number of piglets born alive per sow; however, the percentage of pigs weaned has not increased proportionally with the number of live-born piglets. This pre-weaning loss represents a major economic and welfare challenge. While most pre-weaning mortalities are primarily attributed to crushing, it is well understood that chilling, undernutrition, and dehydration also have substantial impacts, offering a pathway to potentially mitigate pre-weaning mortalities with nutritional strategies. A systematic review was conducted of the available literature regarding the provision of liquid milk supplements to pre-weaned piglets in addition to sow milk. The review included only peer-reviewed articles in English with the full-text available and all years of publication and geographic origin were included. The search was conducted using Google Scholar and Web of Science. After screening, a total of 40 articles were selected for review, of which a subset of 21 articles pertaining specifically to milk product supplementation were included in this abstract. In the resultant literature body, supplemental milk was provided in either reconstituted liquid or powdered form. Results reported that supplying supplemental liquid milk replacer reduced pre-weaning mortality in large litters (≥15 piglets) and increased average weaning weights, with differences ranging from .2 to 2.0 kg per pig. The milk supplement may also aid in reducing incidence of diarrhea in both the pre-weaning and early post-weaning period. Liquid milk replacer improved intestinal immune function, microbiota composition, and metabolite concentrations. There were mixed effects of milk replacer on organ weights, intestinal length, and ratio of villus height to crypt depth, though no negative effects were reported. Nine of the 21 articles pertaining to milk supplementation measured post-weaning parameters. It was generally reported that there were no observed effects of pre-weaning milk supplementation on post-weaning growth performance. In conclusion, providing liquid milk replacer to pre-weaned piglets has the potential benefit of reducing pre-weaning mortality and increasing growth performance during the pre-weaning stage, resulting in more and heavier piglets weaned that will potentially be better adapted to manage the stressors of weaning.

Piglet preweaning mortality (PWM) in the United States averages ≈14–15%, with sow overlaying causing about one third proportion of these losses. This research aimed to develop and evaluate deep learning models to classify six sow postures using depth images to monitor behaviors linked to overlaying risk. Top-down depth images were captured with Kinect V2® cameras at 10 frames min⁻¹ for five consecutive days (2 days before to 2 days after farrowing), yielding 26,506 training images from 18 sows, 17,901 testing images from 12 sows, and 4,697 additional images from three sows in diagonal stalls for external validation. Three transfer learning architectures (YOLOv11m-cls, ResNet-50, and Inception v3) were trained and evaluated on two different depth data transformed images (grayscale and Jet-colormap). Jet colormap images consistently outperformed grayscale, with YOLOv11m-cls achieving the highest accuracy (precision = 0.98, recall = 0.98, F1 = 0.98). External validation confirmed robust performance in diagonal stalls (F1 = 0.94), and cross-validation across stall designs and heat-lamp configurations demonstrated strong generalizability of the models. These findings show that depth imaging combined with deep learning provides a reliable, non-invasive method for sow posture classification. Such model can generate continuous behavioral data streams to improve understanding of postural transitions, stall design, and reduce piglet mortality.

Abstract Automated behavior analytics can make continuous welfare and productivity monitoring feasible on a commercial scale. However, independent field validation against human observers in commercial-type settings remains limited. The objective of this study was to validate a commercial AI-driven, computer vision behavioral analytics platform (PigGuard, Serket. Amsterdam, Netherlands) by comparison with manual human classification (ground truth) and assess performance across various pig ages. A 13-week growing-finishing pig study was conducted in 2 rooms at the North Carolina State University swine nutrition barn. Each room contained 12 pens, with seven pigs placed in each pen at approximately 10 weeks of age. Rooms followed a weekly schedule that randomly cycled 3 thermal conditions (thermoneutral, moderated heat, and moderated cold) for 2 consecutive days each. Continuous overhead Red-Green-Blue RGB video surveillance was collected for each pen at 20 fps. For the behavioral validation subset, week 1 (early finishing), week 6 (mid), and week 12 (late) were selected. One room was analyzed per week of interest. For every week and each thermal condition, a single 30-minute segment was extracted at 2:00, 8:00, 14:00, and 20:00 h. As each condition was applied for 2 consecutive days, the sampled day for each segment was chosen at random, except for the 08:00 segment, which was always selected from day 2 to ensure consistent thermal conditions were applied. Trained human observers used BORIS (Behavioral Observation Research Interactive Software) to annotate videos using a predefined ethogram, capturing 4 main behaviors: active, inactive, feeding, and drinking. Human labels will be compared to software outputs from PigGuard. Analysis is ongoing. Results will be compared using precision, recall, and F1 scoring. Insights will inform accuracy of the computer vision program across grow-finish pig age and thermal conditions. Computer vision systems such as PigGuard are a promising tool for commercial settings; this validation will quantify PigGuard’s level of agreement with human annotations and demonstrate its potential capabilities and limitations as an innovative swine management tool.

The integration of precision livestock technologies facilitates identification of animals with superior productivity and efficiency traits despite exposure to environmental stressors. The objective of this study was to evaluate changes in nutritional intake and thermoregulatory response in heifers consuming an endophyte-infected (EI) ration. Angus heifers (216.3 ± 6.1 kg; 9-11 mo of age; n = 36) were randomly separated and fed either an EI or endophyte-free (EF) ration for 49 days. On day 1, temperature data loggers were inserted intravaginally to record vaginal temperature (VT) on a 20-minute-frequency throughout the entire study. Weekly measurements were collected to monitor growth and physiological responses of both treatment groups. Infrared thermography (IRT) of the ocular globe (OGT) and rib skin area (RIBT) posterior to the left scapula were recorded weekly. The comprehensive climate index (CCI) was used to assess exposure to environmental stress and determine its impact on physiological measurements. Individual feed and water intake was measured utilizing the Vytelle® Sense system, and the final residual feed intake (RFI) rankings were used for a post hoc analysis to identify cattle as either feed efficient (LRFI; n = 6) or inefficient (HRFI; n = 6) in both groups and determine its correlation to the VT and thermography results. Data were analyzed using a MIXED procedure of SAS with repeated measures. The effects of treatment and time were evaluated for Body Weight (BW), ADG, Body Condition Score (BCS), Hair Shedding Score (HSS), VT, OGT, RIBT, Feed Intake (FI), and Water Intake (WI). The EI heifers had lower BW, ADG, and BCS, and greater HSS over time (P< 0.0001), and also had greater VT (40.1 ± 0.1 vs 39.5 ± 0.1 ̊ C; P< 0.0001), RIBT (36.6 ± 0.1 vs 35.5 ± 0.1 ̊ C; P< 0.0001), and OGT (34.9 ± 0.1 vs 34.5 ± 0.1 ̊ C; P< 0.0001) than EF heifers. Moreover, an interaction between treatment and efficiency was observed where EI-LRFI and EI-HRFI had greater VT (P< 0.0001) and RIBT (P< 0.0001), and tended to have greater OGT (P=0.0671) than their EF pairs. However, no differences were observed within treatments between LRFI and HRFI heifers. In terms of nutritional intake, EF heifers had greater FI (P< 0.0001) but lower WI (P=0.0144) than EI heifers over time, and differences (P< 0.0001) were also observed in the duration and frequency of visits to the feed bunks and water troughs of both groups that were correlated to increased CCI values. Exposure to ergot alkaloids negatively impacts the physiological status and production efficiency of growing heifers by altering the animal’s thermoregulatory ability. Developing a better understanding of the mechanisms controlling these symptoms will improve beef cattle production and provide potential therapeutic interventions for disease treatment.

The objectives of this study were to develop and evaluate a novel algorithm for image extraction of structural conformation traits and estimate variance components among skeletal conformation, growth, and herd retention traits. An Intel RealSense D435i camera was used to obtain left-side-view RGB images on individual purebred Duroc pigs (n = 846) at 156 d of age. Frames were selected by a trained swine evaluator when either the left front leg (n = 1056), left back leg (n = 888), or both left legs (n = 728) were present in the field of view and the respective foot pads from toe to heel were in contact with the ground. Selected images were processed through Apple Inc's image segmentation algorithm to extract the pig from the background. Segmented pig images were then processed through a novel algorithm developed in this study. The algorithm identified the leg and estimated 21 skeletal conformation traits from each leg. Steps for user intervention were added to assist the algorithm in identifying which leg(s) were present and the general location of each leg to increase the accuracy of leg identification and trait acquisition. The algorithm correctly identified at least one front and one back leg from an image for 99.9% and 98.0% of the pigs, respectively. Heritability estimates ranged from 0.01 to 0.33 for all conformation traits with the quadratic term for the curvature of the anterior side of the front and the height of the back leg having the highest heritability for each location (h2 = 0.33 and 0.30, respectively). Genetic correlations among image feet and leg conformation traits and production traits (finishing average daily gain, weight per day of age, and finishing feed efficiency) ranged from -0.37 to 0.19. Boars that remained in the breeding herd for longer than 200 d tended (P = 0.08) to have greater curvature of the front leg and lower (P = 0.07) angularity between the midpoint of the foot and the anterior point of the pastern and had significantly (P = 0.03) shorter distance between the pastern and the top of the shoulder than those that were removed prior to 200 d. Gilts that remained in the breeding herd for longer than 200 d tended (P = 0.08) to have less curvature of the back leg. The current study presents an algorithm that extracts novel, objective structural conformation traits and reports corresponding genetic and phenotypic parameters.

The swine industry is one of the largest livestock production systems in the world. Therefore, understanding the impact of thermal stress on animal welfare, productivity, and behavior has become crucial to support sustainability in livestock production. Different behaviors can be associated with suboptimal thermal changes in an animal’s environment, which is why the objective of this study is to use precision livestock farming techniques and technologies to collect behavioral activity and physiological measures of pig outcomes under different thermal conditions. A total of 144 feeder pigs will be housed in two rooms. Each room has 12 pens with six pigs per pen. Pigs will be exposed to thermoneutral conditions, as well as moderate heat and cold stress every week. Each thermal condition will be applied for two consecutive observation days. Each room will have its own data acquisition system and sensors will be installed to continuously monitor environmental conditions, including temperature and relative humidity. Additionally, concentrations of gases such as carbon dioxide and ammonia will be measured. Water flow meters will be placed in every pen to measure pen-level water usage. Pig surface temperature will be monitored with a thermal camera. An RGB+IR camera mounted above each pen will collect images to be labeled for detecting lying lateral, lying sternal, sitting, and standing postures, maintenance behaviors, and activities. Changes in behavior budgets will be compared across pens, thermal conditions, and pig age. Data analysis will focus on evaluating the relationships between thermal conditions and both behavioral and physiological changes. Results are expected to provide insights for enhancing animal productivity and welfare in a controlled environment. A deeper understanding of animal behavior will guide the industry toward optimizing swine production and indoor environmental conditions.

In swine production, it is broadly recognized that ventilation rates and indoor environmental conditions influence pig productivity. However, sparse scientific data are available on the combined effects and potential interactions of these factors in commercial production systems. This study investigated indoor environmental and management factors influencing wean-to-finish pig mortality in a commercial system. Temperature, relative humidity (RH), and carbon dioxide (CO2) were recorded every 10 min in the front and back of 16 barns across five grow-finish sites in eastern North Carolina for two turns (four barns) or three turns (12 barns) for a total of 44 pig groups. Proportional weekly mortality was modeled using a generalized linear mixed model. Results showed that pigs in environments warmer than the desired room temperature had lower mortality (p < 0.001), suggesting cold stress was more detrimental than heat stress. Elevated RH and CO2 at the back of the barn were linked to increased mortality (p < 0.001), highlighting air exchange rates as a key indicator. Mortality was greatest in pig groups placed during Spring and lowest in Summer (p < 0.05), and mortality declined as pigs aged (p = 0.0134). Surprisingly, greater barn occupancy correlated with lower mortality (p = 0.0012), potentially related to piglet quality at placement. The predictive power of the model varied with the turn of pigs, with R2 averaging 0.24 (ranging from 0.001 to 0.61) and an average RMSE of 0.36% (ranging from 0.17% to 0.77%). Ammonia (NH3) was recorded at the back of six barns, and concentrations were modeled. Greater NH3 concentrations were associated with increased pig age, RH, and CO2, as well as lower deviation from desired room temperature and lower barn occupancy. Collectively, these findings highlight the importance of proper ventilation and management on swine productivity.

Abstract The modern livestock industry is increasingly adopting data, technologies, and automation into daily husbandry and management routines and decisions. These advances in precision livestock farming (PLF) enable improved financial margins, sustainability, efficiency, and animal productivity and welfare. However, there is currently a gap between the engineers and data scientists designing the technologies and the animal scientists and caretakers using them. At North Carolina State University a novel course on PLF Systems for undergraduate and graduate students was developed in the Department of Animal Science. Through lecture delivery, livestock production scenarios, scientific literature, and data-based homework assignments students explored data collection, management, analysis, and data-based decision making. Students gained hands-on experience with a variety of sensor types and signal processing through lab-based activities. Basic hardware and software development concepts were explored during an Arduino-based microcontroller activity. The course was developed and refined using student feedback to include additional sensor and lab-based days and additional in-class supported activities utilizing Excel for data manipulation, processing, and presentation. Self-reported student learning results were collected across two semesters (19 students; 18 Animal Science, 1 Biological Engineering) with84% of students indicated the course was effective in increasing their ability to evaluate and implement technology in livestock production systems and 74% of students reported increased knowledge of coding and software, as well as their ability to clean, analyze, and make sense of raw data. The topics and delivery methods implemented in this course could inform the basis for development of similar interdisciplinary PLF courses at other academic institutions.

Abstract Water is an essential nutrient to sustain life and a vital component of biological functioning, impacting regulation of pig body temperature along with transporting nutrients to the body. Drinker availability, position, design, water flow rate and pressure, and water quality are major components of pig water intake. The ideal water flow rate for wean-to-finish pigs is 1 L m-1. Excessive flow rates could limit pig water intake and increase humidity in the barn, while too little water flow can lead to a decrease in water intake and biological functioning of the pig. Water should not contain harmful substances and should be readily accessible to pigs. Compounds in water are highly variable depending on region, water source, and pH. Quality of water influences feed consumption along with pig health. Water can contain a variety of microorganisms such as bacteria, viruses, algae, and protozoa; while not all microorganisms are harmful a highly contaminated water analysis is an index of poor water quality. In this study water quality and water flow rates were analyzed across five wean-finish sites comprising 16 barns for three turns of finishing pigs. Water flow rates were measured twice per turn, wk 1 and wk 17. Each barn contained 36 pens and flow rate measurements were collected in 8 pens evenly distributed within the barn. One suspended water source was available per pen, with two nipple drinkers per water source. Water flow rates were averaged over each turn within barns. Average water flow rates were 1.42 L m-1 with standard deviation of 0.44 L m-1. Overall barn water flow rates ranged from 0.78 to 2.19 L m-1. Barn flow rates were compared over time to evaluate performance and maintenance of facilities. Water quality samples were also collected and submitted for standard water analysis. Results will provide information on management strategies to assess water quality and water flow rates in wean-finish facilities.

This study investigated the interaction of sow and engineering factors on shoulder lesion formation. Sows were randomly assigned to three farrowing crate designs: Traditional Stall Layout, Expanded Creep Stall Layout, and Expanded Sow & Creep Stall Layout. Each crate configuration was further differentiated by the inclusion of either one (1HL) or two (2HL) heat lamps. Digital and depth images were collected from an overhead time of flight depth camera (Kinect V2) every 5 s. Computer vision techniques were employed to analyze top-down digital images from the 21st to the 24th day of farrowing to detect and estimate lesion size. Additionally, the study incorporated an analysis of sow lying behaviors on the occurrence and size of lesions using depth images. Sow's environmental and phenotypic data - weight, parity, body condition score, total lying time and number of lying transitions in a day were investigated for impact on shoulder lesion. The results indicated that the interaction of smaller crate sizes and increased heat lamp usage significantly impacted lesion occurrence (p < 0.05). Also, higher parity and lighter weight sows showed higher lesion occurrence (p < 0.05). However, other factors, such as the number of heat lamps alone and detailed metrics of lying postures, did not show a significant impact on lesion occurrence. In contrast, none of the studied factors showed a significant impact on the size of shoulder lesions. This highlights the importance of allocating crate space with respect to heat lamp placement to the sows. Science4Impact Statement (S4IS): This manuscript evaluates shoulder lesions' presence and size in lactating sows housed within farrowing stalls. Shoulder lesions are one of the main causes of premature culling in sows and are a major concern for animal well-being. Understanding the impact of crate design and the number of heat lamps is important for the engineering design of the farrowing environment.

Heat stress has negative impacts on pork production, particularly during the grow-finish phase. During heat stress events, swine alter feeding behavior to reduce heat production, which can negatively affect performance. Recent technology advancements in feed management systems allow for individualized data recording of feeding behavior for group housed pigs during the finishing phase. The objective of this study was to utilize an RFID-based feed management system to determine feeding behavior patterns of finishing pigs during heat stress conditions and identify changes in behavior due to heat stress events. Data included one pen of 29 Duroc boars reared in a mechanically ventilated facility in north central North Carolina. Feed Intake Recording Equipment (FIRE) pig feeders (n = 3; Osborne Technologies) fed individual pigs in the group housed setting using RFID technology and recorded the number of visits, feed intake of each visit, visit duration, and body weight of each pig during each visit. Feeders were calibrated once per week to ensure accuracy of feed intake and body weight measurements. On day 1 of the study, pigs were placed in the experimental pen and body weights were recorded (37.4 kg ± 4.9 kg) using the FIRE feeders. Air temperature, humidity, and dew point data were collected continuously every 5 minutes from day 13 until the end of the finishing period. Pigs exited finishing (134.5 ± 8.6 kg) on day 83. Feeding behavior traits (number of visits and feed intake) were summarized by day. Temperature, humidity, and heat index were summarized by a maximum, minimum, and mean value for each day. Average temperature, humidity, feeder visits a day, and average daily feed intake across the trial was 26.3 ± 1.6 º C, 75.8 ± 6.7%, 6.1 ± 1.0 visits, 2.66 ± 0.39 kg. Models were used to associate feeding behavior traits with the quadratic effects of day and the linear effects of average temperature and humidity and the interaction of temperature and humidity. Temperature and humidity were associated (P < 0.01) number of feeder visits and average daily intake per day. Further, there was an interaction (P < 0.01) between temperature and humidity in relation to number of feeder visits and average daily feed intake. Results suggest substantial variation in feeding behaviors can be explained by temperature and humidity.

This study evaluated the impact of level and solubility of total dietary fiber (TDF) when fed to sows during late gestation and early pre-farrowing on serum chemistry, glucose status and farrowing characteristics. Sows were assigned to a control with no supplement, or a supplement provided once per day at either 0.45 or 0.90 kg. The fiber supplement consisted of either a high soluble dietary fiber (SDF) formulation [9.63% SDF, and 25.25% of insoluble dietary fiber (IDF)] or a high IDF formulation (30.73% IDF and 4.18% SDF). Fiber supplements were formulated using sugar beet pulp and soybean hulls and were provided in addition to a common gestation (12.0% TDF) and lactation diet (11.30% TDF) from day 99 (±1 d) of gestation until parturition. Blood samples were collected from sows on day 110 of gestation immediately before the morning feeding, and 2 and 4 hours after feeding for the analysis of serum chemistry and glucose status, comparing the control and the 0.90 kg SDF and IDF treatments (n = 15 sows). Serological results were within expected ranges. Supplementation with SDF, but not IDF, decreased concentrations of γ-glutamyl transferase (P = 0.003) compared with the control (32.20 vs 39.20 and 44.02 IU/L, respectively) and magnesium tended (P = 0.09) to increase with fiber supplementation. Glucose concentrations measured with a hand-held glucose meter were not affected by time relative to feeding, fiber supplementation, or their interaction (P = 0.94). A pilot study evaluated the impact of the amount of fiber supplemented and the composition of fiber on total duration of fetal expulsion and piglet vitality index (PVI) using video equipment. The PVI scale ranged from 0-3 where 0 = no movement, no breathing; and 3 = good movement, breathing, and able to stand within 1 minute or less. Cameras (n = 12) were placed in the farrowing room the day sows were transferred from gestation (112 ± 1 d). Duration of fetal expulsion ranged from 2.36 to 11.0 hours but was not influenced by fiber supplementation. Partial correlation analysis revealed a negative relationship between the birth interval and PVI (r = -0.24; P = 0.003) and total duration of fetal expulsion and PVI (r = -0.53; P < 0.001), irrespective of treatments. Results suggest that fiber supplementation did not affect serum chemistry and glucose status of sows during late gestation. The pilot study suggested a negative association of duration of fetal expulsion with PVI, but these were not affected by dietary fiber.

The objective was to evaluate the impact of sow location, within farrowing room, on reproduction during periods of heat stress. Data were collected on 1,866 sows at a 3,600-sow commercial farm in eastern North Carolina from May to August 2021. In the farrowing buildings, evaporative cool cell pads cooled the air entering the hallway. Cooled air, from the hallway, then entered the farrowing rooms through inlets at the front of the room and was pulled through the room by fans in the back of the farrowing room. For data analysis, each farrowing room was divided into four zones. Zone 1 included the sows at the front of the farrowing room near the inlets letting in cooled air. Zone 4 included sows at the back of the room where air exited the building through fans embedded within the wall. Zones 2 and 3 were intermediate. Each farrowing room on the farm housed between 18 and 36 sows. After farrowing, sows had ad libitum access to the lactation diet. Traits included piglet survival (number weaned ÷ total number born) the percentage of sows conceiving by 7 days after weaning, subsequent total number born, subsequent number born alive, subsequent stillborns, sow caliper score prefarrow, sow caliper score at weaning and sow caliper lactation loss. Results are shown in Table 1. Piglet survival was greater (P < 0.05) for sows that farrowed at the front of the room near the cool air inlets. Similarly, litter weaning weight was heavier (P < 0.05) near the cool air inlets relative to the back part of the farrowing room. The percentage of sows that conceived by 7 days after weaning, and farrowed, was linearly associated (P < 0.05) with farrowing zone. Sows near the cool air inlets lost less (P < 0.05) body condition and farrowed more (P < 0.05) piglets in the subsequent litter relative to sows in the back of the farrowing room. Results showed sows that farrowed at the front of the farrowing room lost less body condition, had greater piglet survival, heavier litter weaning weights and were more likely to be rebred and conceive by 7 days after weaning relative to sows farrowing in the back of the farrowing room.

Pig manure contains a wide variety of corrosion-inducing chemicals such as ammonia. Ammonia production and its release are influenced by temperature and moisture in the barn environment. Increased concentrations of ammonia can negatively affect pig health and growth, as well as pose a risk to human health. Additionally, even at decreased concentrations, ammonia reacts with humidity and causes premature corrosion of barn equipment and is a threat to the structural integrity of livestock buildings. In this study, ammonia concentrations were monitored and compared between two 880 head wean-finish swine facilities with different types of waste management systems. Both facilities had shallow manure pits, one containing a flush system and one containing a pull plug system to remove manure from the barns into the lagoon. Ammonia, dry-bulb air temperature, and relative humidity levels were measured every0 min for an entire wean-finish cycle (approximately 20 weeks). Data will be compared between the facilities to evaluate the impact of the waste management systems on indoor air quality conditions. Potential implications for pig health and growth and facility maintenance will be explored. Results will provide information on best management strategies for swine facilities.

AbstractThe complex environment surrounding young pigs reared in intensive housing systems directly influences their productivity and livelihood. Much of the seminal literature utilized housing and husbandry practices that have since drastically evolved through advances in genetic potential, nutrition, health, and technology. This review focuses on the environmental interaction and responses of pigs during the first 8 wk of life, separated into pre-weaning (creep areas) and post-weaning (nursery or wean-finish) phases. Further, a perspective on instrumentation and precision technologies for animal-based (physiological and behavioral) and environmental measures documents current approaches and future possibilities. A warm microclimate for piglets during the early days of life, especially the first 12 h, is critical. While caretaker interventions can mitigate the extent of hypothermia, low birth weight remains a dominant risk factor for mortality. Post-weaning, the thermoregulation capabilities have improved, but subsequent transportation, nutritional, and social stressors enhance the requisite need for a warm, low draft environment with the proper flooring. A better understanding of the individual environmental factors that affect young pigs as well as the creation of comprehensive environment indices or improved, non-contact sensing technology is needed to better evaluate and manage piglet environments. Such enhanced understanding and evaluation of pig–environment interaction could lead to innovative environmental control and husbandry interventions to foster healthy and productive pigs.

This large-scale field study evaluated the effects farrowing stall environment on piglet productivity and behavior. Three farrowing stall layouts were tested (T – traditional, C – expanded creep area, S – expanded sow area) in conjunction with one or two heat lamps (1HL or 2HL). Production data were collected on the number of piglets live at birth, percent stillborn, percent preweaning piglet mortality, percent over-lay (crushing), number of piglets weaned, average daily weight gain, and litter uniformity. The only productivity difference found was in percent stillborn (p = 0.045); however, it was of small magnitude and not of practical significance. Piglet behavior data were collected and processed with a custom imaging system. Each farrowing stall was divided into three regions: heated region directly below the heat lamp (Rheated), unheated regions of the creep (Rcreep), and sow stall region (Rsow). The proportion of piglets within each farrowing stall region were analyzed and compared on select days of lactation. Piglets in the 2HL treatment spent a significantly greater amount of time in Rheated compared to the 1Hl treatment (p<0.001). Time in Rheated, Rcreep, and Rsow were all influenced by stall layout (p<0.03). Results from this study indicate that dimensions of farrowing stall components do influence piglet behavior and the provision of a second heat lamp results in piglets increasing time spent in the heated area. These behavioral changes due to the farrowing stall environment did not result in differences in productivity. The addition of a second heat lamp or larger creep or sow stall areas produced changes in piglet behavior, but there were no significant changes in productivity metrics.

An apparent opportunity for improvement in the swine industry is preweaning piglet mortality. Preweaning piglet mortality results in economic loss, decreasing productivity per sow, and food waste. One aspect of preweaning mortality, stillborn piglets, can be reduced with timely caretaker interventions to reduce interbirth interval. However, a single caretaker is often in charge of managing many farrowing events concurrently. To address this labor need, piglet interbirth interval could be monitored using thermal cameras. In the present study the performance of a custom image capturing and processing system was evaluated for its ability to identify piglet births. Thermal images of 4 sows in farrowing stalls were collected once every 2 seconds to compare the image processing algorithm’s ability to identify piglet interbirth interval with human observations. There were 66 piglets born in total. Piglets born less than 2 minutes apart were classified as one birthing event, resulting in 49 birthing events total. When the algorithm detected piglet birthing events, they were considered correct if they were within 2 minutes of the human timestamp. The algorithm correctly identified 27 out of 49 birthing events. The algorithm resulted in 22 false negatives and 27 false positives. Results show that 55% of birthing events were accurately detected. With further refinement, the algorithm has the potential to increase accuracy of piglet birthing event identification. The present study demonstrates that computer vision systems can be implemented to monitor piglet birthing events in real-time, allowing caretakers to target their efforts on the most at-risk animals in the farrowing room. This continuous monitoring system has the potential to change the view of farrowing in the swine industry.

To combat the stress of weaning, we utilized novel gruel creep feeders to supplement suckling pigs with divergent soluble (n = 6 litters) versus insoluble (n = 6) diets compared with un-supplemented controls (n = 6). Post-weaning, pigs were fed a common phase 1 diet. Average daily weight gains of pigs fed soluble and insoluble creep diets were 53% and 17% greater than control pigs, respectively (p < 0.01). Creep intake was higher (82%) for pigs fed the soluble diet, and the accompanying weight increase was sustained post-weaning (p < 0.02). Villus measures were prematurely altered in soluble-creep-fed pigs (p < 0.01), with decreases in villi length, crypt depth, and villus area pre-weaning. No effects of treatment were detected for VFA concentrations and pH in the cecum. There was an interaction between treatment and age for several pro- and anti-inflammatory cytokines (p < 0.01), where soluble-creep-fed pigs had increased cytokine levels with age, whereas cytokine levels in the insoluble and control groups decreased over time. We conclude that a soluble creep diet fed in a gruel state during the pre-weaning period has a positive impact on weaning weight that is sustained post-weaning, and is accompanied by alterations in the intestinal health of young pigs.

HighlightsA calibration procedure was conducted using a Kinect V2 to convert image pixels to physical measurements.A total of 61 sows were observed, and their static and dynamic space usage was measured from depth images.Equations were developed to predict the length, width, and height of sow space usage.Abstract. The amount of space provided to individually housed sows has both financial and animal welfare implications. Many U.S. swine producers use stall dimensions based on recommendations published in the 1980s (length × width × height: 2.13 m × 0.61 m × 1.00 m). Limited empirical data are available concerning the space allocation needed to accommodate modern sows housed in stalls during breeding, gestation, or farrowing. This study used a time-of-flight depth sensor to quantify static and dynamic space usage of 61 modern sows in late gestation. A calibration equation was developed to convert image pixels to physical dimensions. Statistical models were developed to relate the length, width, and height of sow space usage to body weight. The dimensions of sow space usage were then predicted. Results showed that free choice space usage of average (228 kg) sows was 1.96 m × 1.15 m × 0.93 m (length × width × height). For 95th percentile (267 kg) sows, space usage was 2.04 m × 1.12 m × 0.95 m. The width of space usage was primarily attributed to sow body depth when lying recumbent and the dynamic space used for transitioning between postures. These results help to inform future gestating and farrowing sow housing designs. Further work is needed to understand how restrictions on sow space usage may impact sow welfare and production performance, as well as the space needed to perform behaviors such as defecating, feeding, and turning around. Keywords: Animal welfare, Computer vision, Farrowing stall, Gestation stall, Kinect V2, Space allowance.

Providing appropriate thermal conditions for young piglets is critical to growth and welfare, especially during stressful periods after transportation and relocation. When preheating an empty facility prior to the arrival of piglets, raising the air temperature to the desired setpoint can be achieved relatively quickly but heating of other barn components, namely the concrete slat flooring, requires additional time and heat input. In this study, the heat transfer rates to concrete slats in a bench-scale model commercial facility environment were measured under high temperature heating conditions. Temperatures were recorded in multiple locations, including air above the slats, pit head space below the slats, and inside the slats. Results from this study can advise producers on the time and heating input required to preheat facilities prior to piglet arrival to reduce piglet stress and discomfort.