Validation of accelerometers to automatically record sow postures and stepping behaviour

Integrating computer vision algorithms and RFID system for identification and tracking of group-housed animals: an example with pigs

Precision livestock farming aims to individually and automatically monitor animal activity to ensure their health, well-being, and productivity. Computer vision has emerged as a promising tool for this purpose. However, accurately tracking individuals using imaging remains challenging, especially in group housing where animals may have similar appearances. Close interaction or crowding among animals can lead to the loss or swapping of animal IDs, compromising tracking accuracy. To address this challenge, we implemented a framework combining a tracking-by-detection method with a radio frequency identification (RFID) system. We tested this approach using twelve pigs in a single pen as an illustrative example. Three of the pigs had distinctive natural coat markings, enabling their visual identification within the group. The remaining pigs either shared similar coat color patterns or were entirely white, making them visually indistinguishable from each other. We employed the latest version of the You Only Look Once (YOLOv8) and BoT-SORT algorithms for detection and tracking, respectively. YOLOv8 was fine-tuned with a dataset of 3,600 images to detect and classify different pig classes, achieving a mean average precision of all the classes of 99%. The fine-tuned YOLOv8 model and the tracker BoT-SORT were then applied to a 166.7-min video comprising 100,018 frames. Results showed that pigs with distinguishable coat color markings could be tracked 91% of the time on average. For pigs with similar coat color, the RFID system was used to identify individual animals when they entered the feeding station, and this RFID identification was linked to the image trajectory of each pig, both backward and forward. The two pigs with similar markings could be tracked for an average of 48.6 min, while the seven white pigs could be tracked for an average of 59.1 min. In all cases, the tracking time assigned to each pig matched the ground truth 90% of the time or more. Thus, our proposed framework enabled reliable tracking of group-housed pigs for extended periods, offering a promising alternative to the independent use of image or RFID approaches alone. This approach represents a significant step forward in combining multiple devices for animal identification, tracking, and traceability, particularly when homogeneous animals are kept in groups.

Sow serenity: automatic long-term measurement of lying behavior in crates and free-farrowing pens using 3D accelerometers

Accelerometers are useful in analyzing lying behavior in farm animals. The effect of the farrowing system on sow lying behavior has been studied around parturition, but not long-term. In a natural environment, sows increase activity 14 d post parturition, which we expected to be also evident in housed sows when they can move freely. The objective of this study was (1) to validate the methodology to automatically measure sow lying bouts and duration with accelerometers and (2) to apply it to crated and free-farrowing sows 24-h pre-parturition until weaning. We used videos with manual behavior coding as the gold standard for validation and calculated the agreement with an intraclass correlation coefficient (ICC), which was 0.30 (95% CI: -0.10 to 0.64) for the number of lying bouts. When transitional sitting bouts were excluded from the video dataset, the ICC for lying bouts increased to 0.86 (95% CI: 0.40 to 0.95). For lying duration, the ICC was 0.93 (95% CI: 0.26 to 0.98). We evaluated the effects of housing, day relative to parturition, and time of day on lying using the accelerometer data and linear mixed models. In crated sows, the number of lying bouts increased toward parturition, peaking at about five bouts per 6 h, and decreased to almost zero bouts after parturition. Then, it increased again (P = 0.001). In free-farrowing sows, the number of lying bouts gradually decreased from a high level towards parturition and was lowest after parturition. It remained constant, as in the crated sows, until day 15, when the number of bouts increased to eight bouts on day 20 (P = 0.001). Sows in both systems were lying almost all of the time between 18:00 and 00:00 hours and on all days (P = 0.001). The crated sows showed a very similar pattern in the other three-quarters of the day with a reduced lying time before parturition, a peak after parturition, reduced lying time from days 5 to 20, and an increase again towards weaning (P = 0.001). Free-farrowing sows had a similar pattern to the crated sows from 00:00 to 06:00 hours, but without the reduction in lying time from days 5 to 20. They showed an increase in lying time toward parturition, which remained constant with a final decrease toward weaning, especially during the day (P = 0.001). This study proves the accuracy of accelerometer-based sow lying behavior classification and shows that free-farrowing systems benefit lactating sows around parturition but also towards weaning in the nest-leaving phase by facilitating activity.

Research on the Recognition and Tracking of Group-Housed Pigs' Posture Based on Edge Computing

The existing algorithms for identifying and tracking pigs in barns generally have a large number of parameters, relatively complex networks and a high demand for computational resources, which are not suitable for deployment in embedded-edge nodes on farms. A lightweight multi-objective identification and tracking algorithm based on improved YOLOv5s and DeepSort was developed for group-housed pigs in this study. The identification algorithm was optimized by: (i) using a dilated convolution in the YOLOv5s backbone network to reduce the number of model parameters and computational power requirements; (ii) adding a coordinate attention mechanism to improve the model precision; and (iii) pruning the BN layers to reduce the computational requirements. The optimized identification model was combined with DeepSort to form the final Tracking by Detecting algorithm and ported to a Jetson AGX Xavier edge computing node. The algorithm reduced the model size by 65.3% compared to the original YOLOv5s. The algorithm achieved a recognition precision of 96.6%; a tracking time of 46 ms; and a tracking frame rate of 21.7 FPS, and the precision of the tracking statistics was greater than 90%. The model size and performance met the requirements for stable real-time operation in embedded-edge computing nodes for monitoring group-housed pigs.

ASAS-NANP SYMPOSIUM: MATHEMATICAL MODELING IN ANIMAL NUTRITION: Opportunities and Challenges of Confined and Extensive Precision Livestock Production

Modern animal scientists, industry, and managers have never faced a more complex world. Precision livestock technologies have altered management in confined operations to meet production, environmental, and consumer goals. Applications of precision technologies have been limited in extensive systems such as rangelands due to lack of infrastructure, electrical power, communication, and durability. However, advancements in technology have helped to overcome many of these challenges. Investment in precision technologies is growing within the livestock sector, requiring the need to assess opportunities and challenges associated with implementation to enhance livestock production systems. In this review, precision livestock farming and digital livestock farming are explained in the context of a logical and iterative five-step process to successfully integrate precision livestock measurement and management tools, emphasizing the need for precision system models (PSMs). This five-step process acts as a guide to realize anticipated benefits from precision technologies and avoid unintended consequences. Consequently, the synthesis of precision livestock and modeling examples and key case studies help highlight past challenges and current opportunities within confined and extensive systems. Successfully developing PSM requires appropriate model(s) selection that aligns with desired management goals and precision technology capabilities. Therefore, it is imperative to consider the entire system to ensure that precision technology integration achieves desired goals while remaining economically and managerially sustainable. Achieving long-term success using precision technology requires the next generation of animal scientists to obtain additional skills to keep up with the rapid pace of technology innovation. Building workforce capacity and synergistic relationships between research, industry, and managers will be critical. As the process of precision technology adoption continues in more challenging and harsh, extensive systems, it is likely that confined operations will benefit from required advances in precision technology and PSMs, ultimately strengthening the benefits from precision technology to achieve short- and long-term goals.

Effects of a Multi-Suckling System Combined With Enriched Housing Post-Weaning on Response and Cognitive Resilience to Isolation

Improving welfare is still a critical issue in pig husbandry. Upgrades of the housing environment seem to be a promising solution to optimise resilience as a whole, and therefore improve animal welfare. The objective of this study was to evaluate the effect of an alternative housing system to enhance cognitive resilience and also to promote the pigs' welfare. A total of 96 piglets from two contrasted housing systems [alternative housing system (AHS) vs. conventional system (CONV)] was used. The major upgrades of the alternative system were multi-litter housing during lactation, delayed weaning, extra space allowance, and environmental enrichment from birth onwards. To estimate welfare, weight, and feed intake (as a general indicator of performances), the tear staining area (as a chronic stress indicator), behavioural postures, heart rate traits, and saliva cortisol concentration were measured over a 21 h-isolation. To assess cognitive resilience, the pigs were subjected to a maze with a social reward both before and after the isolation challenge and indicators of cognitive abilities were followed. The AHS pigs showed lower cortisol levels and tear staining area before the challenge, demonstrating overall better welfare due to the alternative housing conditions. During the challenge, AHS pigs had a lower heart rate, higher heart rate variability, and higher vagal activity than the CONV pigs, which might indicate a reduced sensitivity to the stressor. AHS pigs appeared to have a better long-term memory tested in a maze. Providing social and environmental enrichments, that fit the satisfaction of the essential needs of the pigs better, appears to be beneficial for pig welfare as a whole. Its effects on cognitive resilience still need to be proven.

Feed restriction and type of forage influence performance and behaviour of outdoor gestating sows

Forages can contribute to the nutrient supply for sows but the extent to which they can replace concentrate feeding is not well known. The objective of this study was to assess the effect of level of feed restriction and type of forage on the performance and activity of gestating sows under outdoor conditions. A total of 45 sows were distributed among three treatments, with five replicates of three sows/treatment, from week 5 of gestation until farrowing. Treatments differed in the daily level of concentrate feed provided and the type of forage offered during gestation: 90% of metabolisable energy (ME) requirements provided by concentrates and free access to a pasture (P90); 40% of ME requirements provided by concentrates and free access to a pasture (P40); and 40% of ME requirements provided by concentrates and free access to a bare paddock with hay ad libitum (H40). From farrowing to weaning (5 weeks), concentrate feed was offered to all sows ad libitum. Body weight and backfat thickness (BF) were measured seven times during gestation and lactation. Postures of sows and time spent in the pasture were assessed at the beginning, middle and end of gestation. Forage intake was estimated with a method based on sow performance using the InraPorc® model. At farrowing, P90 sows were heavier and had greater BF than P40 and H40 sows. At weaning, P90 sows maintained a higher BW and tended to have greater BF than H40 sows, but no longer differed from P40 sows. Treatments did not influence litter size, but piglets from P40 sows were lighter at birth than those from P90 sows (1.44 vs. 1.69 kg, P = 0.004). In late gestation, P90 sows spent less time standing over 24 h and less time in the pasture during daytime than P40 sows, suggesting less foraging behaviour. Sows fed concentrates to meet 40% of ME requirements during gestation did not consume enough forage to maintain the same body condition as sows fed at 90% of ME requirements. Despite their inability to fully compensate for concentrate restriction during gestation by consuming more forage, P40 sows reached a similar body condition to P90 sows at weaning. In conclusion, forage intake for outdoor gestating sows can compensate a concentrate feed reduction of 10% and possibly more, but not as much as 60%.

Bottlenose dolphin habitat and management factors related to activity and distance traveled in zoos and aquariums

High-resolution non-invasive cetacean tagging systems can be used to investigate the influence of habitat characteristics and management factors on behavior by quantifying activity levels and distance traveled by bottlenose dolphins (Tursiops truncatus and Tursiops aduncus) in accredited zoos and aquariums. Movement Tags (MTags), a bio-logging device, were used to record a suite of kinematic and environmental information outside of formal training sessions as part of a larger study titled "Towards understanding the welfare of cetaceans in zoos and aquariums" (colloquially called the Cetacean Welfare Study). The purpose of the present study was to explore if and how habitat characteristics, environmental enrichment programs, and training programs were related to the distance traveled and energy expenditure of dolphins in accredited zoos and aquariums. Bottlenose dolphins in accredited zoos and aquariums wore MTags one day per week for two five-week data collection periods. Overall dynamic body acceleration (ODBA), a proxy for energy expenditure, and average distance traveled per hour (ADT) of 60 dolphins in 31 habitats were examined in relation to demographic, habitat, and management factors. Participating facilities were accredited by the Alliance for Marine Mammal Parks and/or Aquariums and the Association of Zoos & Aquariums. Two factors were found to be related to ADT while six factors were associated with ODBA. The results showed that enrichment programs were strongly related to both ODBA and ADT. Scheduling predictable training session times was also positively associated with ADT. The findings suggested that habitat characteristics had a relatively weak association with ODBA and were not related to ADT. In combination, the results suggested that management practices were more strongly related to activity levels than habitat characteristics.

A Systematic Review on Validated Precision Livestock Farming Technologies for Pig Production and Its Potential to Assess Animal Welfare

Several precision livestock farming (PLF) technologies, conceived for optimizing farming processes, are developed to detect the physical and behavioral changes of animals continuously and in real-time. The aim of this review was to explore the capacity of existing PLF technologies to contribute to the assessment of pig welfare. In a web search for commercially available PLF for pigs, 83 technologies were identified. A literature search was conducted, following systematic review guidelines (PRISMA), to identify studies on the validation of sensor technologies for assessing animal-based welfare indicators. Two validation levels were defined: internal (evaluation during system building within the same population that were used for system building) and external (evaluation on a different population than during system building). From 2,463 articles found, 111 were selected, which validated some PLF that could be applied to the assessment of animal-based welfare indicators of pigs (7% classified as external, and 93% as internal validation). From our list of commercially available PLF technologies, only 5% had been externally validated. The more often validated technologies were vision-based solutions (n = 45), followed by load-cells (n = 28; feeders and drinkers, force plates and scales), accelerometers (n = 14) and microphones (n = 14), thermal cameras (n = 10), photoelectric sensors (n = 5), radio-frequency identification (RFID) for tracking (n = 2), infrared thermometers (n = 1), and pyrometer (n = 1). Externally validated technologies were photoelectric sensors (n = 2), thermal cameras (n = 2), microphone (n = 1), load-cells (n = 1), RFID (n = 1), and pyrometer (n = 1). Measured traits included activity and posture-related behavior, feeding and drinking, other behavior, physical condition, and health. In conclusion, existing PLF technologies are potential tools for on-farm animal welfare assessment in pig production. However, validation studies are lacking for an important percentage of market available tools, and in particular research and development need to focus on identifying the feature candidates of the measures (e.g., deviations from diurnal pattern, threshold levels) that are valid signals of either negative or positive animal welfare. An important gap identified are the lack of technologies to assess affective states (both positive and negative states).

Pig-Posture Recognition Based on Computer Vision: Dataset and Exploration

Posture changes in pigs during growth are often precursors of disease. Monitoring pigs' behavioral activities can allow us to detect pathological changes in pigs earlier and identify the factors threatening the health of pigs in advance. Pigs tend to be farmed on a large scale, and manual observation by keepers is time consuming and laborious. Therefore, the use of computers to monitor the growth processes of pigs in real time, and to recognize the duration and frequency of pigs' postural changes over time, can prevent outbreaks of porcine diseases. The contributions of this article are as follows: (1) The first human-annotated pig-posture-identification dataset in the world was established, including 800 pictures of each of the four pig postures: standing, lying on the stomach, lying on the side, and exploring. (2) When using a deep separable convolutional network to classify pig postures, the accuracy was 92.45%. The results show that the method proposed in this paper achieves adequate pig-posture recognition in a piggery environment and may be suitable for livestock farm applications.

Welfare Health and Productivity in Commercial Pig Herds

In recent years, there have been very dynamic changes in both pork production and pig breeding technology around the world. The general trend of increasing the efficiency of pig production, with reduced employment, requires optimisation and a comprehensive approach to herd management. One of the most important elements on the way to achieving this goal is to maintain animal welfare and health. The health of the pigs on the farm is also a key aspect in production economics. The need to maintain a high health status of pig herds by eliminating the frequency of different disease units and reducing the need for antimicrobial substances is part of a broadly understood high potential herd management strategy. Thanks to the use of sensors (cameras, microphones, accelerometers, or radio-frequency identification transponders), the images, sounds, movements, and vital signs of animals are combined through algorithms and analysed for non-invasive monitoring of animals, which allows for early detection of diseases, improves their welfare, and increases the productivity of breeding. Automated, innovative early warning systems based on continuous monitoring of specific physiological (e.g., body temperature) and behavioural parameters can provide an alternative to direct diagnosis and visual assessment by the veterinarian or the herd keeper.

Evaluation of the FitBark Activity Monitor for Measuring Physical Activity in Dogs

Accelerometers track changes in physical activity which can indicate health and welfare concerns in dogs. The FitBark 2 (FitBark) is an accelerometer for use with dogs; however, no studies have externally validated this tool. The objective of this study was to evaluate FitBark criterion validity by correlating FitBark activity data to dog step count. Dogs (n = 26) were fitted with a collar-mounted FitBark and individually recorded for 30 min using a three-phase approach: (1) off-leash room explore; (2) human-dog interaction; and (3) on-leash walk. Video analysis was used to count the number of times the front right paw touched the ground (step count). Dog step count and FitBark activity were moderately correlated across all phases (r = 0.65, p < 0.001). High correlations between step count and FitBark activity were observed during phases 1 (r = 0.795, p < 0.001) and 2 (r = 0.758, p < 0.001), and a low correlation was observed during phase 3 (r = 0.498, p < 0.001). In conclusion, the FitBark is a valid tool for tracking physical activity in off-leash dogs; however, more work should be done to identify the best method of tracking on-leash activity.

Accelerometer systems as tools for health and welfare assessment in cattle and pigs - A review

Welfare assessment has traditionally been performed by direct observation by humans, providing information at only selected points in time. Recently, this assessment method has been questioned, as 'Precision Livestock Farming' technologies may be able to deliver more valid, reliable and feasible real-time data at the individual level and serve as early monitoring systems for animal welfare. The aim of this paper is to describe how accelerometers can be used for welfare assessment based on the principles of the Welfare Quality assessment protocol. Algorithm development is based mainly on the detection of behavioural traits. So far, high accuracies have been found for movement and resting behaviours in cows and pigs, while algorithm development for feeding and drinking behaviours in pigs lag behind progress in cows where valid algorithms are already available. Welfare studies have used accelerometer technology to address the effects on behaviour of diet, daily cycle, enrichment, housing, social mixing, oestrus, lameness and disease. Additional aspects to consider before a decision is made upon its use in research and in practical applications include battery life and sensor location. While accelerometer systems for cows are already being used by farmers, application in pigs has mainly remained at the research level.

Review of Livestock Welfare Indicators Relevant for the Australian Live Export Industry

Animal welfare is an important issue for the live export industry (LEI), in terms of economic returns, community attitudes and international socio-political relations. Mortality has traditionally been the main welfare measure recorded within the LEI; however, high mortality incidents are usually acted upon after adverse events occur, reducing the scope for proactive welfare enhancement. We reviewed 71 potential animal welfare measures, identifying those measures that would be appropriate for use throughout the LEI for feeder and slaughter livestock species, and categorised these as animal-, environment- and resource-based. We divided the live export supply chain into three sectors: (1) Australian facilities, (2) vessel and (3) destination country facilities. After reviewing the relevant regulations for each sector of the industry, we identified 38 (sector 1), 35 (sector 2) and 26 (sector 3) measures already being collected under current practice. These could be used to form a 'welfare information dashboard': a LEI-specific online interface for collecting data that could contribute towards standardised industry reporting. We identified another 20, 25 and 28 measures that are relevant to each LEI sector (sectors 1, 2, 3, respectively), and that could be developed and integrated into a benchmarking system in the future.

Precision Livestock Farming in Swine Welfare: A Review for Swine Practitioners

Simple Summary

The increasing implementation of technological advances originally developed for video gaming (PlayStation, Xbox) is helping to progress livestock production so that it is both more efficient and more focused on the welfare of the animals. Such advances are necessary to ensure that innovations can emerge from applications using cameras, microphones and sensors to enhance the farmers’ eyes, ears and nose in everyday farming. This technology for remote monitoring of livestock, termed precision livestock farming, is the ability to automatically track individual livestock in real time. The goal of this review is to apprise swine veterinarians and their clientele on precision livestock farming with a general introduction to the technology available, a review of research and commercially available technology and the implications and opportunities for swine practitioners and farmers. Drawing from pig welfare criteria in the Common Swine Industry Audit, this review explains how these applications can be used to improve swine welfare within current pork production stakeholder expectations. Swine veterinarians and specialists, by virtue of their animal advocacy role, interpretation of benchmarking data, and stewardship in regulatory and commodity programs, can play a broader role in facilitating the transfer of precision livestock farming and technology to their clients.

Abstract

The burgeoning research and applications of technological advances are launching the development of precision livestock farming. Through sensors (cameras, microphones and accelerometers), images, sounds and movements are combined with algorithms to non-invasively monitor animals to detect their welfare and predict productivity. In turn, this remote monitoring of livestock can provide quantitative and early alerts to situations of poor welfare requiring the stockperson’s attention. While swine practitioners’ skills include translation of pig data entry into pig health and well-being indices, many do not yet have enough familiarity to advise their clients on the adoption of precision livestock farming practices. This review, intended for swine veterinarians and specialists, (1) includes an introduction to algorithms and machine learning, (2) summarizes current literature on relevant sensors and sensor network systems, and drawing from industry pig welfare audit criteria, (3) explains how these applications can be used to improve swine welfare and meet current pork production stakeholder expectations. Swine practitioners, by virtue of their animal and client advocacy roles, interpretation of benchmarking data, and stewardship in regulatory and traceability programs, can play a broader role as advisors in the transfer of precision livestock farming technology, and its implications to their clients.

Validity of Micro-Data Loggers to Determine Walking Activity of Turkeys and Effects on Turkey Gait

Accelerometers have the potential to provide objective, non-invasive methods for detecting changes in animal behavior and health. Our objectives were to: (1) determine the effects of micro-acceleration data loggers (accelerometers) and habituation to accelerometers on turkey gait and health status, (2) determine age-related changes in gait and health status, and (3) assess the validity and reliability of the accelerometers. Thirty-six male commercial turkeys were randomly assigned to one of five groups: accelerometer and habituation period (AH), accelerometer and no habituation period (AN), VetRap bandage (no accelerometer) and habituation period (VH), bandage (no accelerometer) and no habituation period (VN), and nothing on either leg (C). Health status and body condition were assessed prior to video-recording birds as they walked across a Tekscan® pressure pad at 8, 12, and 16 weeks to determine effects of treatment on number of steps, cadence, gait time, gait distance, gait velocity, impulse, gait cycle time, maximum force, peak vertical pressure, single support time, contact time, step length, step time, step velocity, stride length, total double support time, and duty factor. Accelerometer validity and reliability were determined by comparing the number of steps detected by the accelerometer to the number of steps determined from video recordings. Several age-related changes in turkey gait were found regardless of habituation including a slower cadence at 16 weeks, shorter gait distance at 8 weeks, and slower gait velocity at 16 weeks. When comparing bandaged vs. unbandaged limbs, both treatment and age-treatment interactions were found depending on the gait parameter. Accelerometer validity and reliability were affected by both age and treatment. False discovery rate increased, while accuracy and specificity decreased with age. Validity and reliability were lowest for non-habituated birds (AN and VN). Results demonstrated that micro-data loggers do not adversely affect turkey health status, but habituation to wearing accelerometers greatly affects accelerometer reliability and validity. Accelerometer validity and turkey gait are also greatly affected by the age of the turkeys.

Smart Animal Agriculture: Application of Real-Time Sensors to Improve Animal Well-Being and Production

Consumption of animal products such as meat, milk, and eggs in first-world countries has leveled off, but it is rising precipitously in developing countries. Agriculture will have to increase its output to meet demand, opening the door to increased automation and technological innovation; intensified, sustainable farming; and precision livestock farming (PLF) applications. Early indicators of medical problems, which use sensors to alert cattle farmers early concerning individual animals that need special care, are proliferating. Wearable technologies dominate the market. In less-value-per-animal systems like sheep, goat, pig, poultry, and fish, one sensor, like a camera or robot per herd/flock/school, rather than one sensor per animal, will become common. PLF sensors generate huge amounts of data, and many actors benefit from PLF data. No standards currently exist for sharing sensor-generated data, limiting the use of commercial sensors. Technologies providing accurate data can enhance a well-managed farm. Development of methods to turn the data into actionable solutions is critical.

Locomotion Disorders and Skin and Claw Lesions in Gestating Sows Housed in Dynamic versus Static Groups

Lameness and lesions to the skin and claws of sows in group housing are commonly occurring indicators of reduced welfare. Typically, these problems are more common in group housing than in individual housing systems. Group management type (dynamic versus static) and stage of gestation influence the behavior of the animals, which in turn influences the occurrence of these problems. The present study compared prevalence, incidence and mean scores of lameness and skin and claw lesions in static versus dynamic group housed sows at different stages of gestation during three consecutive reproductive cycles. A total of 10 Belgian sow herds were monitored; 5 in which dynamic groups and 5 in which static groups were utilized. All sows were visually assessed for lameness and skin lesions three times per cycle and the claws of the hind limbs were assessed once per cycle. Lameness and claw lesions were assessed using visual analogue scales. Static groups, in comparison with dynamic groups, demonstrated lower lameness scores (P<0.05) and decreased skin lesion prevalence (24.9 vs. 47.3%, P<0.05) at the end of gestation. There was no difference between treatment group regarding claw lesion prevalence with 75.5% of sows demonstrating claw lesions regardless of group management. Prevalences of lameness (22.4 vs. 8.9%, P<0.05) and skin lesions (46.6 vs. 4.4%, P<0.05) were highest during the group-housed phase compared to the individually housed phases. Although the prevalence of lameness and skin lesions did not differ three days after grouping versus at the end of the group-housing phase, their incidence peaked during the first three days after moving from the insemination stalls to the group. In conclusion, the first three days after grouping was the most risky period for lameness incidence, but there was no significant difference between static or dynamic group management.

Porcine lie detectors: Automatic quantification of posture state and transitions in sows using inertial sensors

This paper presents a novel approach to automated classification and quantification of sow postures and posture transitions that may enable large scale and accurate continuous behaviour assessment on farm. Automatic classification and quantification of postures and posture transitions in domestic animals has substantial potential to enhance their welfare and productivity. Analysis of such behaviours in farrowing sows can highlight the need for human intervention or lead to the prediction of movement patterns that are potentially dangerous for their piglets, such as crushing when the sow lies down. Data were recorded by a tri-axial accelerometer secured to the hind-end of each sow, in a deployment that involved six sows over the period around parturition. The posture state (standing, sitting, lateral and sternal lying) was automatically classified for the full dataset with a mean F₁ score (a measure of predictive performance between 0 and 1) of 0.78. Sitting was shown to present a greater challenge to classification with a F₁ score of 0.54, compared to the lateral lying postures, which were classified with an average F₁ score of 0.91. Posture transitions were detected with a F₁ score of 0.79. We automatically extracted and visualized a range of features that characterise the manner in which the sows changed posture in order to provide comparative descriptors of sow activity and lying style that can be used to assess the influence of genetics or housing design. The methodology presented in this paper can be applied in large scale deployments with potential for enhancing animal welfare and productivity on farm.

The Use of Acceleration to Code for Animal Behaviours; A Case Study in Free-Ranging Eurasian Beavers Castor fiber

Recent technological innovations have led to the development of miniature, accelerometer-containing electronic loggers which can be attached to free-living animals. Accelerometers provide information on both body posture and dynamism which can be used as descriptors to define behaviour. We deployed tri-axial accelerometer loggers on 12 free-ranging Eurasian beavers Castor fiber in the county of Telemark, Norway, and on four captive beavers (two Eurasian beavers and two North American beavers C. canadensis) to corroborate acceleration signals with observed behaviours. By using random forests for classifying behavioural patterns of beavers from accelerometry data, we were able to distinguish seven behaviours; standing, walking, swimming, feeding, grooming, diving and sleeping. We show how to apply the use of acceleration to determine behaviour, and emphasise the ease with which this non-invasive method can be implemented. Furthermore, we discuss the strengths and weaknesses of this, and the implementation of accelerometry on animals, illustrating limitations, suggestions and solutions. Ultimately, this approach may also serve as a template facilitating studies on other animals with similar locomotor modes and deliver new insights into hitherto unknown aspects of behavioural ecology.

Effect of locomotion score on sows' performances in a feed reward collection test

Sows housed in groups have to move through their pen to fulfil their behavioural and physiological needs such as feeding and resting. In addition to causing pain and discomfort, lameness may restrict the ability of sows to fulfil such needs. The aim of our study was to investigate the extent to which the mobility of sows is affected by different degrees of lameness. Mobility was measured as the sow's willingness or capability to cover distances. Feed-restricted hybrid sows with different gait scores were subjected to a feed reward collection test in which they had to walk distances to obtain subsequent rewards. In all, 29 group-housed sows at similar gestation stage (day 96.6 ± 7 s.d.) were visually recorded for gait and classified as non-lame, mildly lame, moderately lame or severely lame. All sows received 2.6 kg of standard commercial gestation feed per day. The test arena consisted of two feeding locations separated from each other by a Y-shaped middle barrier. Feed rewards were presented at the two feeders in turn, using both light and sound cues to signal the availability of a new feed reward. Sows were individually trained during 5 non-consecutive days for 10 min/day with increasing barrier length (range: 0 to 3.5 m) each day. After training, sows were individually tested once per day on 3 non-consecutive days with the maximum barrier length such that they had to cover 9.3 m to walk from one feeder to the other. The outcome variable was the number of rewards collected in a 15-min time span. Non-lame and mildly lame sows obtained more rewards than moderately lame and severely lame sows (P<0.01). However, no significant difference was found between non-lame and mildly lame sows (P=0.69), nor between moderately lame and severely lame sows (P=1.00). This feed reward collection test indicates that both moderately lame and severely lame sows are limited in their combined ability and willingness to walk, but did not reveal an effect of mild lameness on mobility. These findings suggest that moderately and more severely lame sows, but not mildly lame sows, might suffer from reduced access to valuable resources in group housing systems.

Measure and characterization of lameness in gestating sows using force plate, kinematic, and accelerometer methods

The objective was to assess sows' lameness by measuring weight distribution on limbs using a force plate made up of 4 individual platforms each resting on 4 single-ended beam load cells. The weight was recorded at an average rate of 14 readings per s over a 15 min period. Ten sows (5 lame sows and 5 sound sows) were weighed twice on 2 different days to assess the repeatability of the measure. Sixty-one sows were then selected in 2 different sites and visually scored for lameness, using a 3-point scoring system (0=normal gait; 1=abnormal gait, and/or stiffness; and 2=shortened stride, and/or the sow puts less weight or avoids putting weight on 1 leg). Various measures were recorded from each sow using the force plate (percentage of weight, the ratio between the weights applied by contralateral legs, weight shifting, and amplitude of weight bearing and weight removing), kinematics (speed, stride length, swing time, stance time, foot height, and carpal and tarsal joints angle average and amplitude), and accelerometers (time spent standing during 24 h, frequency of stepping behavior during feeding, and latency to lie down after feed delivery). The within-sow CV for each measure taken from the force plate were lower than 15%, which reflects a good repeatability. Among force plate measures, only the weight shifting frequency and the ratio between the weights applied by contralateral legs differed between lameness scores. Sows that scored 2 had a higher frequency of weight shifting for fore legs (P=0.0003) and hind legs (P=0.0007) than sows scored 0 and 1. The ratio between the weights applied by contralateral legs decreased with the increase of lameness score for the hind limbs (P=0.014). However, these measures also differed between sites (P<0.01). These differences may be due to various reasons, including but not limited to genetics and housing systems. Nevertheless, the results suggest that force plate measures such as the asymmetry in the weight applied between a pair of legs and weight shifting are good indicators of lameness. Multivariate analysis on fore and hind legs showed independency between variables related to animals in movement (measures from kinematics) and variables related to static animals (measures from the force plate and accelerometers). Therefore, both static and dynamic methods need to be used to detect various lame sows.

On-farm evaluation of methods to assess welfare of gestating sows

The objectives were to evaluate quantitative animal-based measures of sow welfare (lameness, oral stereotypies and reactivity to humans) under commercial farm conditions, and to estimate the influence of housing, sow parity and stage of gestation on the outcome of these measures. Across 10 farms, 311 sows were used. Farms differed in terms of housing design (pen v. stall), space allowance, floor type in stalls (partially v. fully slatted), and feeding system in pens (floor v. trough). Lameness was assessed in terms of gait score, walking speed, stride length, stepping behaviour, response to a stand-up test and latency to lie down after feeding. The presence of oral stereotypies and saliva foam were recorded. Reactivity to humans was assessed by approach (attempt to touch the sow between the ears) and handling tests (exit of the stall for stall-housed sows, or isolation of the animal for pen-housed sows). Only stride length and walking speed were associated with lameness in stall-housed sows (P<0.05 and P<0.01). In stalls, the probability that a sow was lame when it presented a short stride length (<83 cm) or a low speed (<1 m/s) was high (69% and 72%, respectively), suggesting that these variables were good indicators of lameness, but were not sufficient to detect every lame sow in a herd (sensitivity of 0.39 and 0.71, respectively). The stage of gestation and parity also influenced measures of stride length and walking speed (P<0.05). Saliva foam around the mouth was associated with the presence of sham chewing and fixture biting (P<0.05). The probability that a sow presents sham chewing behaviour when saliva foam around her mouth was observed was moderate (63%) but was not sufficient to detect all sows with stereotypies (41%). A high discrimination index was obtained for behavioural measures (aggressions, escapes) and vocalisations during the approach test (stalls: 78.0 and 64.0; pens: 71.9 and 75.0, respectively), the number of interventions needed to make the sow exit the stall during the handling test for stall-housed sows (74.9), and attempts to escape during the handling test for pen-housed sows (96.9). These results suggest that these measures have a good power to discriminate between sows with low and high reactivity to humans. Finally, the outcome of several measures of lameness, stereotypies and reactivity to humans were influenced by the housing characteristics, sow parity and stage of gestation. Therefore, these factors should be considered to avoid misinterpretations of these measures in terms of welfare.

Identification of behaviour in freely moving dogs (Canis familiaris) using inertial sensors

Monitoring and describing the physical movements and body postures of animals is one of the most fundamental tasks of ethology. The more precise the observations are the more sophisticated the interpretations can be about the biology of a certain individual or species. Animal-borne data loggers have recently contributed much to the collection of motion-data from individuals, however, the problem of translating these measurements to distinct behavioural categories to create an ethogram is not overcome yet. The objective of the present study was to develop a “behaviour tracker”: a system composed of a multiple sensor data-logger device (with a tri-axial accelerometer and a tri-axial gyroscope) and a supervised learning algorithm as means of automated identification of the behaviour of freely moving dogs. We collected parallel sensor measurements and video recordings of each of our subjects (Belgian Malinois, N=12; Labrador Retrievers, N=12) that were guided through a predetermined series of standard activities. Seven behavioural categories (lay, sit, stand, walk, trot, gallop, canter) were pre-defined and each video recording was tagged accordingly. Evaluation of the measurements was performed by support vector machine (SVM) classification. During the analysis we used different combinations of independent measurements for training and validation (belonging to the same or different individuals or using different training data size) to determine the robustness of the application. We reached an overall accuracy of above 90% perfect identification of all the defined seven categories of behaviour when both training and validation data belonged to the same individual, and over 80% perfect recognition rate using a generalized training data set of multiple subjects. Our results indicate that the present method provides a good model for an easily applicable, fast, automatic behaviour classification system that can be trained with arbitrary motion patterns and potentially be applied to a wide range of species and situations.