Early detection of health and welfare compromises through automated detection of behavioural changes in pigs

Description of Behavioral Patterns Displayed by a Recently Weaned Cohort of Healthy Dairy Calves

Simple Summary

Modern technology has allowed researchers to track the movement patterns of cattle with increasing accuracy in order to gain a greater understanding of both overt and subtle activity trends. The aim of this study was to describe and analyze movement patterns displayed by recently weaned and healthy dairy calves. Three movement pattern clusters were identified, and calves in this study were more active in the afternoon and at night. There was a correlation between the rate of movement, linearity ratio, and the distance traveled. However, turning angles do not have any influence on the distance traveled and the rate of movement across the three cluster-type movements. The findings reported in this study could be used to further develop the interpretation of movement and behavior patterns of calves in order to establish an early detection system for poor health and welfare on dairy farms.

Abstract

Animals display movement patterns that can be used as health indicators. The movement of dairy cattle can be characterized into three distinct cluster types. These are cluster type 1 (resting), cluster type 2 (traveling), and cluster type 3 (searching). This study aimed to analyze the movement patterns of healthy calves and assess the relationship between the variables that constitute the three cluster types. Eleven Holstein calves were fitted with GPS data loggers, which recorded their movement over a two week period during spring. The GPS data loggers captured longitude and latitude coordinates, distance, time and speed. It was found that the calves were most active during the afternoon and at night. Slight inconsistencies from previous studies were found in the cluster movements. Cluster type 2 (traveling) reported the fastest rate of movement, whereas cluster type 1 (resting) reported the slowest. These diverse movement patterns could be used to enhance the assessment of dairy animal health and welfare on farms.

Investigation of Pig Activity Based on Video Data and Semi-Supervised Neural Networks

The activity level of pigs is an important stress indicator which can be associated to tail-biting, a major issue for animal welfare of domestic pigs in conventional housing systems. Although the consideration of the animal activity could be essential to detect tail-biting before an outbreak occurs, it is often manually assessed and therefore labor intense, cost intensive and impracticable on a commercial scale. Recent advances of semi- and unsupervised convolutional neural networks (CNNs) have made them to the state of art technology for detecting anomalous behavior patterns in a variety of complex scene environments. In this study we apply such a CNN for anomaly detection to identify varying levels of activity in a multi-pen problem setup. By applying a two-stage approach we first trained the CNN to detect anomalies in the form of extreme activity behavior. Second, we trained a classifier to categorize the detected anomaly scores by learning the potential activity range of each pen. We evaluated our framework by analyzing 82 manually rated videos and achieved a success rate of 91%. Furthermore, we compared our model with a motion history image (MHI) approach and a binary image approach using two benchmark data sets, i.e., the well established pedestrian data sets published by the University of California, San Diego (UCSD) and our pig data set. The results show the effectiveness of our framework, which can be applied without the need of a labor intense manual annotation process and can be utilized for the assessment of the pig activity in a variety of applications like early warning systems to detect changes in the state of health.

Estimating individuals' genetic and non-genetic effects underlying infectious disease transmission from temporal epidemic data

Individuals differ widely in their contribution to the spread of infection within and across populations. Three key epidemiological host traits affect infectious disease spread: susceptibility (propensity to acquire infection), infectivity (propensity to transmit infection to others) and recoverability (propensity to recover quickly). Interventions aiming to reduce disease spread may target improvement in any one of these traits, but the necessary statistical methods for obtaining risk estimates are lacking. In this paper we introduce a novel software tool called SIRE (standing for "Susceptibility, Infectivity and Recoverability Estimation"), which allows for the first time simultaneous estimation of the genetic effect of a single nucleotide polymorphism (SNP), as well as non-genetic influences on these three unobservable host traits. SIRE implements a flexible Bayesian algorithm which accommodates a wide range of disease surveillance data comprising any combination of recorded individual infection and/or recovery times, or disease diagnostic test results. Different genetic and non-genetic regulations and data scenarios (representing realistic recording schemes) were simulated to validate SIRE and to assess their impact on the precision, accuracy and bias of parameter estimates. This analysis revealed that with few exceptions, SIRE provides unbiased, accurate parameter estimates associated with all three host traits. For most scenarios, SNP effects associated with recoverability can be estimated with highest precision, followed by susceptibility. For infectivity, many epidemics with few individuals give substantially more statistical power to identify SNP effects than the reverse. Importantly, precise estimates of SNP and other effects could be obtained even in the case of incomplete, censored and relatively infrequent measurements of individuals' infection or survival status, albeit requiring more individuals to yield equivalent precision. SIRE represents a new tool for analysing a wide range of experimental and field disease data with the aim of discovering and validating SNPs and other factors controlling infectious disease transmission.

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.

Transforming the Adaptation Physiology of Farm Animals through Sensors

Despite recent scientific advancements, there is a gap in the use of technology to measure signals, behaviors, and processes of adaptation physiology of farm animals. Sensors present exciting opportunities for sustained, real-time, non-intrusive measurement of farm animal behavioral, mental, and physiological parameters with the integration of nanotechnology and instrumentation. This paper critically reviews the sensing technology and sensor data-based models used to explore biological systems such as animal behavior, energy metabolism, epidemiology, immunity, health, and animal reproduction. The use of sensor technology to assess physiological parameters can provide tremendous benefits and tools to overcome and minimize production losses while making positive contributions to animal welfare. Of course, sensor technology is not free from challenges; these devices are at times highly sensitive and prone to damage from dirt, dust, sunlight, color, fur, feathers, and environmental forces. Rural farmers unfamiliar with the technologies must be convinced and taught to use sensor-based technologies in farming and livestock management. While there is no doubt that demand will grow for non-invasive sensor-based technologies that require minimum contact with animals and can provide remote access to data, their true success lies in the acceptance of these technologies by the livestock industry.

Weber Texture Local Descriptor for Identification of Group-Housed Pigs

The individual identification of group-housed pigs plays an important role in breeding process management and individual behavior analysis. Recently, livestock identification methods based on the side view or face image have strict requirements on the position and posture of livestock, which poses a challenge for the application of the monitoring scene of group-housed pigs. To address the issue above, a Weber texture local descriptor (WTLD) is proposed for the identification of group-housed pigs by extracting the local features of back hair, skin texture, spots, and so on. By calculating the differential excitation and multi-directional information of pixels, the local structure features of the main direction are fused to enhance the description ability of features. The experimental results show that the proposed WTLD achieves higher recognition rates with a lower feature dimension. This method can identify pig individuals with different positions and postures in the pig house. Without limitations on pig movement, this method can facilitate the identification of individual pigs with greater convenience and universality.

Automated recognition of postures and drinking behaviour for the detection of compromised health in pigs

Changes in pig behaviours are a useful aid in detecting early signs of compromised health and welfare. In commercial settings, automatic detection of pig behaviours through visual imaging remains a challenge due to farm demanding conditions, e.g., occlusion of one pig from another. Here, two deep learning-based detector methods were developed to identify pig postures and drinking behaviours of group-housed pigs. We first tested the system ability to detect changes in these measures at group-level during routine management. We then demonstrated the ability of our automated methods to identify behaviours of individual animals with a mean average precision of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.989 \pm 0.009$$\end{document}0.989±0.009, under a variety of settings. When the pig feeding regime was disrupted, we automatically detected the expected deviations from the daily feeding routine in standing, lateral lying and drinking behaviours. These experiments demonstrate that the method is capable of robustly and accurately monitoring individual pig behaviours under commercial conditions, without the need for additional sensors or individual pig identification, hence providing a scalable technology to improve the health and well-being of farm animals. The method has the potential to transform how livestock are monitored and address issues in livestock farming, such as targeted treatment of individuals with medication.

Large-Scale Phenotyping of Livestock Welfare in Commercial Production Systems: A New Frontier in Animal Breeding

Genomic breeding programs have been paramount in improving the rates of genetic progress of productive efficiency traits in livestock. Such improvement has been accompanied by the intensification of production systems, use of a wider range of precision technologies in routine management practices, and high-throughput phenotyping. Simultaneously, a greater public awareness of animal welfare has influenced livestock producers to place more emphasis on welfare relative to production traits. Therefore, management practices and breeding technologies in livestock have been developed in recent years to enhance animal welfare. In particular, genomic selection can be used to improve livestock social behavior, resilience to disease and other stress factors, and ease habituation to production system changes. The main requirements for including novel behavioral and welfare traits in genomic breeding schemes are: (1) to identify traits that represent the biological mechanisms of the industry breeding goals; (2) the availability of individual phenotypic records measured on a large number of animals (ideally with genomic information); (3) the derived traits are heritable, biologically meaningful, repeatable, and (ideally) not highly correlated with other traits already included in the selection indexes; and (4) genomic information is available for a large number of individuals (or genetically close individuals) with phenotypic records. In this review, we (1) describe a potential route for development of novel welfare indicator traits (using ideal phenotypes) for both genetic and genomic selection schemes; (2) summarize key indicator variables of livestock behavior and welfare, including a detailed assessment of thermal stress in livestock; (3) describe the primary statistical and bioinformatic methods available for large-scale data analyses of animal welfare; and (4) identify major advancements, challenges, and opportunities to generate high-throughput and large-scale datasets to enable genetic and genomic selection for improved welfare in livestock. A wide variety of novel welfare indicator traits can be derived from information captured by modern technology such as sensors, automatic feeding systems, milking robots, activity monitors, video cameras, and indirect biomarkers at the cellular and physiological levels. The development of novel traits coupled with genomic selection schemes for improved welfare in livestock can be feasible and optimized based on recently developed (or developing) technologies. Efficient implementation of genetic and genomic selection for improved animal welfare also requires the integration of a multitude of scientific fields such as cell and molecular biology, neuroscience, immunology, stress physiology, computer science, engineering, quantitative genomics, and bioinformatics.

Storing, combining and analysing turkey experimental data in the Big Data era

With the increasing availability of large amounts of data in the livestock domain, we face the challenge to store, combine and analyse these data efficiently. With this study, we explored the use of a data lake for storing and analysing data to improve scalability and interoperability. Data originated from a 2-day animal experiment in which the gait score of approximately 200 turkeys was determined through visual inspection by an expert. Additionally, inertial measurement units (IMUs), a 3D-video camera and a force plate (FP) were installed to explore the effectiveness of these sensors in automating the visual gait scoring. We deployed a data lake using the IMU and FP data of a single day of that animal experiment. This encompasses data from 84 turkeys for which we preprocessed by performing an ‘extract, transform and load’ (ETL-) procedure. To test scalability of the ETL-procedure, we simulated increasing volumes of the available data from this animal experiment and computed the ‘wall time’ (elapsed real time) for converting FP data into comma-separated files and storing these files. With a simulated data set of 30 000 turkeys, the wall time reduced from 1 h to less than 15 min, when 12 cores were used compared to 1 core. This demonstrated the ETL-procedure to be scalable. Subsequently, a machine learning (ML) pipeline was developed to test the potential of a data lake to automatically distinguish between two classses, that is, very bad gait scores v. other scores. In conclusion, we have set up a dedicated customized data lake, loaded data and developed a prediction model via the creation of an ML pipeline. A data lake appears to be a useful tool to face the challenge of storing, combining and analysing increasing volumes of data of varying nature in an effective manner.

Panoptic Segmentation of Individual Pigs for Posture Recognition

Behavioural research of pigs can be greatly simplified if automatic recognition systems are used. Systems based on computer vision in particular have the advantage that they allow an evaluation without affecting the normal behaviour of the animals. In recent years, methods based on deep learning have been introduced and have shown excellent results. Object and keypoint detector have frequently been used to detect individual animals. Despite promising results, bounding boxes and sparse keypoints do not trace the contours of the animals, resulting in a lot of information being lost. Therefore, this paper follows the relatively new approach of panoptic segmentation and aims at the pixel accurate segmentation of individual pigs. A framework consisting of a neural network for semantic segmentation as well as different network heads and postprocessing methods will be discussed. The method was tested on a data set of 1000 hand-labeled images created specifically for this experiment and achieves detection rates of around 95% (F1 score) despite disturbances such as occlusions and dirty lenses.

Prospects for sustainability of pig production in relation to climate change and novel feed resources

Pig production systems provide multiple benefits to humans. However, the global increase in meat consumption has profound consequences for our earth. This perspective describes two alternative scenarios for improving the sustainability of future pig production systems. The first scenario is a high input-high output system based on sustainable intensification, maximizing animal protein production efficiency on a limited land surface at the same time as minimizing environmental impacts. The second scenario is a reduced input-reduced output system based on selecting animals that are more robust to climate change and are better adapted to transform low quality feed (local feeds, feedstuff co-products, food waste) into meat. However, in contrast to the first scenario, the latter scenario results in reduced predicted yields, reduced production efficiency and possibly increased costs to the consumer. National evaluation of the availability of local feed and feedstuff co-product alternatives, determination of limits to feed sourced from international markets, available land for crop and livestock production, desired production levels, and a willingness to politically enforce policies through subsidies and/or penalties are some of the considerations to combine these two scenarios. Given future novel sustainable alternatives to livestock animal protein, it may become reasonable to move towards an added general premium price on 'protein from livestock animals' to the benefit of promoting higher incomes to farmers at the same time as covering the extra costs of, politically enforced, welfare of livestock animals in sustainable production systems. © 2020 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Pérez L. Long-Term Tracking of Group-Housed Livestock Using Keypoint Detection and MAP Estimation for Individual Animal Identification

Tracking individual animals in a group setting is a exigent task for computer vision and animal science researchers. When the objective is months of uninterrupted tracking and the targeted animals lack discernible differences in their physical characteristics, this task introduces significant challenges. To address these challenges, a probabilistic tracking-by-detection method is proposed. The tracking method uses, as input, visible keypoints of individual animals provided by a fully-convolutional detector. Individual animals are also equipped with ear tags that are used by a classification network to assign unique identification to instances. The fixed cardinality of the targets is leveraged to create a continuous set of tracks and the forward-backward algorithm is used to assign ear-tag identification probabilities to each detected instance. Tracking achieves real-time performance on consumer-grade hardware, in part because it does not rely on complex, costly, graph-based optimizations. A publicly available, human-annotated dataset is introduced to evaluate tracking performance. This dataset contains 15 half-hour long videos of pigs with various ages/sizes, facility environments, and activity levels. Results demonstrate that the proposed method achieves an average precision and recall greater than 95% across the entire dataset. Analysis of the error events reveals environmental conditions and social interactions that are most likely to cause errors in real-world deployments.

Toward better estimates of the real-time individual amino acid requirements of growing-finishing pigs showing deviations from their typical feeding patterns

Pigs exposed to stressors might change their daily typical feeding intake pattern. The objective of this study was to develop a method for the early identification of deviations from an individual pig's typical feeding patterns. In addition, a general approach was proposed to model feed intake and real-time individual nutrient requirements for pigs with atypical feeding patterns. First, a dynamic linear model (DLM) was proposed to model the typical daily feed intake (DFI) and daily gain (DG) patterns of pigs. Individual DFI and DG dynamics are described by a univariate DLM in conjunction with Kalman filtering. A standardized tabular cumulative sum (CUMSUM) control chart was applied to the forecast errors generated by DLM to activate an alarm when a pig showed deviations from its typical feeding patterns. The relative feed intake (RFI) during a challenge period was calculated. For that, the forecasted individual pig DFI is expressed as its highest DFI relative to the intake during pre-challenge period. Finally, the DLM and RFI approaches were integrated into the actual precision-feeding model (original model) to estimate real-time individual nutrient requirements for pigs with atypical feeding patterns. This general approach was evaluated with data from two studies (130 pigs, at 35.25 ± 3.9 kg of initial BW) that investigated during 84 days the effect of precision-feeding systems for growing-finishing pigs. The proposed general approach to estimating real-time individual nutrient requirements (updated model) was evaluated by comparing its estimates with those generated by the original model. For 11 individuals out of 130, the DLM did not fit the observed data well in a specific period, resulting in an increase in the sum of standardized forecast errors and in the number of time steps that the model needed to adapt to the new patterns. This poor fit can be identified by the increase in the CUMSUM with a consequent alarm generated. The results of this study show that the updated model made it possible to reduce intra-individual variation for the estimated lysine requirements in comparison with the original model, especially for individuals with atypical feeding patterns. In conclusion, the DLM in conjunction with CUMSUM could be used as a tool for the online monitoring of DFI for growing-finishing pigs. Moreover, the proposed general approach allows the estimation of real-time amino acid requirements and accounts for the reduced feed intake and growth potential of pigs with atypical feeding patterns.

Quantification of the sensitivity of early detection surveillance

Early detection surveillance is used for various purposes, including the early detection of non‐communicable diseases (e.g. cancer screening), of unusual increases of disease frequency (e.g. influenza or pertussis outbreaks), and the first occurrence of a disease in a previously free population. This latter purpose is particularly important due to the high consequences and cost of delayed detection of a disease moving to a new population. Quantifying the sensitivity of early detection surveillance allows important aspects of the performance of different systems, approaches and authorities to be evaluated, compared and improved. While quantitative evaluation of the sensitivity of other branches of surveillance has been available for many years, development has lagged in the area of early detection, arguably one of the most important purposes of surveillance. This paper, using mostly animal health examples, develops a simple approach to quantifying the sensitivity of early detection surveillance, in terms of population coverage, temporal coverage and detection sensitivity. This approach is extended to quantify the benefits of risk‐based approaches to early detection surveillance. Population‐based clinical surveillance (based on either farmers and their veterinarians, or patients and their local health services) provides the best combination of sensitivity, practicality and cost‐effectiveness. These systems can be significantly enhanced by removing disincentives to reporting, for instance by implementing effective strategies to improve farmer awareness and engagement with health services and addressing the challenges of well‐intentioned disease notification policies that inadvertently impose barriers to reporting.

EmbeddedPigDet—Fast and Accurate Pig Detection for Embedded Board Implementations

Automated pig monitoring is an important issue in the surveillance environment of a pig farm. For a large-scale pig farm in particular, practical issues such as monitoring cost should be considered but such consideration based on low-cost embedded boards has not yet been reported. Since low-cost embedded boards have more limited computing power than typical PCs and have tradeoffs between execution speed and accuracy, achieving fast and accurate detection of individual pigs for “on-device” pig monitoring applications is very challenging. Therefore, in this paper, we propose a method for the fast detection of individual pigs by reducing the computational workload of 3 × 3 convolution in widely-used, deep learning-based object detectors. Then, in order to recover the accuracy of the “light-weight” deep learning-based object detector, we generate a three-channel composite image as its input image, through “simple” image preprocessing techniques. Our experimental results on an NVIDIA Jetson Nano embedded board show that the proposed method can improve the integrated performance of both execution speed and accuracy of widely-used, deep learning-based object detectors, by a factor of up to 8.7.

Automated Video Behavior Recognition of Pigs Using Two-Stream Convolutional Networks

The detection of pig behavior helps detect abnormal conditions such as diseases and dangerous movements in a timely and effective manner, which plays an important role in ensuring the health and well-being of pigs. Monitoring pig behavior by staff is time consuming, subjective, and impractical. Therefore, there is an urgent need to implement methods for identifying pig behavior automatically. In recent years, deep learning has been gradually applied to the study of pig behavior recognition. Existing studies judge the behavior of the pig only based on the posture of the pig in a still image frame, without considering the motion information of the behavior. However, optical flow can well reflect the motion information. Thus, this study took image frames and optical flow from videos as two-stream input objects to fully extract the temporal and spatial behavioral characteristics. Two-stream convolutional network models based on deep learning were proposed, including inflated 3D convnet (I3D) and temporal segment networks (TSN) whose feature extraction network is Residual Network (ResNet) or the Inception architecture (e.g., Inception with Batch Normalization (BN-Inception), InceptionV3, InceptionV4, or InceptionResNetV2) to achieve pig behavior recognition. A standard pig video behavior dataset that included 1000 videos of feeding, lying, walking, scratching and mounting from five kinds of different behavioral actions of pigs under natural conditions was created. The dataset was used to train and test the proposed models, and a series of comparative experiments were conducted. The experimental results showed that the TSN model whose feature extraction network was ResNet101 was able to recognize pig feeding, lying, walking, scratching, and mounting behaviors with a higher average of 98.99%, and the average recognition time of each video was 0.3163 s. The TSN model (ResNet101) is superior to the other models in solving the task of pig behavior recognition.

Only When It Feels Good: Specific Cat Vocalizations Other Than Meowing

Our objective was to identify and characterize the types of vocalization other than meowing (VOM) in two contexts, a pleasant and an aversive situation, and to study the effect of the sex of the animal. A total of 74 cats (32 tom cats and 42 queens) living in the city of Curitiba, Brazil, participated in the study; in total, 68 (29 tom cats and 39 queens) were divided into two groups according to the stimulus they were exposed to: either a pleasant situation (PS), when they were offered a snack, or an aversive situation (AS), with the simulation of a car transport event. The other six animals (three tom cats and three queens) participated in both situations. Only the PS group presented VOM; of the 40 PS animals, 14 presented VOM, mostly acknowledgment or trill and squeak. No correlation was observed between vocalization and cat sex (p = 0.08; Pearson's Chi-Square). Results show that VOM is exclusively associated with positive situations, suggesting that these vocalizations may be relevant for understanding the valence of cat emotional state. Further studies are warranted to advance knowledge on other VOMs and on the generalization of our findings to other situations.

Deep Learning and Machine Vision Approaches for Posture Detection of Individual Pigs

Posture detection targeted towards providing assessments for the monitoring of health and welfare of pigs has been of great interest to researchers from different disciplines. Existing studies applying machine vision techniques are mostly based on methods using three-dimensional imaging systems, or two-dimensional systems with the limitation of monitoring under controlled conditions. Thus, the main goal of this study was to determine whether a two-dimensional imaging system, along with deep learning approaches, could be utilized to detect the standing and lying (belly and side) postures of pigs under commercial farm conditions. Three deep learning-based detector methods, including faster regions with convolutional neural network features (Faster R-CNN), single shot multibox detector (SSD) and region-based fully convolutional network (R-FCN), combined with Inception V2, Residual Network (ResNet) and Inception ResNet V2 feature extractions of RGB images were proposed. Data from different commercial farms were used for training and validation of the proposed models. The experimental results demonstrated that the R-FCN ResNet101 method was able to detect lying and standing postures with higher average precision (AP) of 0.93, 0.95 and 0.92 for standing, lying on side and lying on belly postures, respectively and mean average precision (mAP) of more than 0.93.

How many pigs within a group need to be sick to lead to a diagnostic change in the group's behavior?1

Disease is a leading cause of diminished welfare and productivity in pig systems, but its spread among pigs within commercial herds can be limited through early detection. Identifying specific behavioral changes at the onset of disease can have a substantial diagnostic value by improving treatment success through timely intervention. Our study aimed to identify key behaviors that visibly change at the group level when only a few individuals are acutely sick. First, we quantified the behavioral changes seen during an acute health challenge in groups of pigs, using total pen vaccination as an artificial sickness model. Then we investigated the minimum proportion of sick pigs needed to detect group level behavioral changes using three treatments: a control (Con; 0% pigs), low (±20% pigs), or a high (±50% pigs) number of pigs vaccinated in the pens. Total pen vaccination in Trial 1 produced group level behavioral changes, including reduced feeding (P < 0.001), non-nutritive visits to the feeder (P < 0.01), drinking (P < 0.001), standing (P < 0.001), and interaction with pen enrichment (P < 0.001), accompanied by increased lying rates (P < 0.01) and elevated body temperatures (P < 0.001), confirming that vaccination is an appropriate model to study effects of acute sickness. In Trial 2, group level declines in interaction with the enrichment device (P < 0.001) and standing rates (P = 0.064), along with an increase in pen lying rates (P < 0.001), were apparent in the Low treatment when compared to the Con rates, which suggests these key behaviors could serve an important diagnostic value for early disease detection in groups. These changes lasted for up to 3 h post vaccination. In contrast, feeding rates (treatment × time of day: P < 0.01) only showed a decrease from the Con in the High treatment after vaccination, with pen drinking showing a similar trend (treatment: P = 0.07), suggesting that these behaviors would be more appropriate for confirming the spread of disease within a herd. Identifying key behaviors that alert to the presence of disease is critical to further refine automated early warning systems using pen level sensors for commercial pig operations.

Automated bioacoustics: methods in ecology and conservation and their potential for animal welfare monitoring

Vocalizations carry emotional, physiological and individual information. This suggests that they may serve as potentially useful indicators for inferring animal welfare. At the same time, automated methods for analysing and classifying sound have developed rapidly, particularly in the fields of ecology, conservation and sound scene classification. These methods are already used to automatically classify animal vocalizations, for example, in identifying animal species and estimating numbers of individuals. Despite this potential, they have not yet found widespread application in animal welfare monitoring. In this review, we first discuss current trends in sound analysis for ecology, conservation and sound classification. Following this, we detail the vocalizations produced by three of the most important farm livestock species: chickens ( Gallus gallus domesticus), pigs ( Sus scrofa domesticus) and cattle ( Bos taurus). Finally, we describe how these methods can be applied to monitor animal welfare with new potential for developing automated methods for large-scale farming.

Remote Identification of Sheep with Flystrike Using Behavioural Observations

Simple Summary

Flystrike in sheep is a common condition in Australia where parasitic flies lay eggs on soiled wool or open wounds; and the resulting maggots feed off the flesh. Identification of ‘flystruck’ individuals is crucial for treatment; but requires labour-intensive physical examination of every animal. The aim of this study was to investigate the behaviour of sheep; while they remained in the paddock; to try and visually distinguish those suffering from flystrike. Observers who were blinded to the flystrike status of the sheep were asked to score the animal’s body language from video footage. These scores were then compared with the condition of the wool and whether the sheep were flystruck. The observers found that the flystruck sheep exhibited behavioural characteristics that corresponded to the flystrike severity and the condition of the wool around the tail (breech) of the sheep. We therefore conclude that behavioural monitoring of sheep in the paddock could be used to identify animals that had flystrike.

Abstract

Flystrike is a major problem affecting sheep in Australia. Identification of ‘flystruck’ individuals is crucial for treatment; but requires labour-intensive physical examination. As the industry moves toward more low-input systems; there is a need for remote methods to identify flystruck individuals. The aim of this study was to investigate the behaviour of sheep with breech flystrike within a paddock setting. Video footage of sixteen Merino sheep; eight later confirmed with flystrike and eight without; was collected as they moved freely within the paddock with conspecifics. Quantitative behavioural measurements and a qualitative behavioural assessment (QBA) were conducted and compared to their breech conditions (i.e., faecal/urine staining; flystrike severity). Both qualitative and quantitative assessments indicated behavioural differences between flystruck and non-flystruck animals. Flystruck sheep had a behavioural profile characterised by restless behaviour; abnormal postures and reduced grazing time (p < 0.05). Furthermore; flystruck sheep were scored to have a more ‘exhausted/irritated’ demeanour using QBA (p < 0.05). The behavioural responses also corresponded to the flystrike severity scores and condition of the breech area. We conclude that remotely assessed behaviour of flystruck sheep diverges markedly from non-flystruck sheep; and thus could be a low-input method for identifying and treating affected animals.

Use of non-steroidal anti-inflammatory drugs in porcine health management

OBJECTIVE

Treatment of inflammation and pain management is an important topic in the welfare of pigs. It is very difficult for veterinary practitioners to choose the most appropriate product for a certain problem. This review aims to summarise and discuss the characteristics of different non-steroidal anti-inflammatory drugs (NSAIDs), as well as paracetamol and metamizole, available for pigs in the European Union.

METHODS

The databases Pubmed, Google Scholar, CliniPharm CliniTox and European Medicines Agency were searched. Relevant terms (eg,'meloxicam', 'fever', 'swine', 'pig', 'inflammation', 'castration', 'pain') were used to search for original articles, reviews and books. Only peer-reviewed articles were used. References from studies were also analysed in order to find additional relevant studies.

CONCLUSION

Studies which have investigated the efficacy of NSAIDs for different conditions, using different treatment regimens, are scarce. Most studies focused on the efficacy of NSAID-related pain alleviation in piglet castration, as well as the anti-inflammatory potential of NSAIDs in experimental inflammation models. Little research has been carried out on the use of metamizole, tolfenamic acid, paracetamol and sodium salicylate and their effect in pigs.

Development of an Automated Pain Facial Expression Detection System for Sheep (Ovis Aries)

The use of technology to optimize the production and management of each individual animal is becoming key to good farming. There is a need for the real-time systematic detection and control of disease in animals in order to limit the impact on animal welfare and food supply. Diseases such as footrot and mastitis cause significant pain in sheep, and so early detection is vital to ensuring effective treatment and preventing the spread across the flock. Facial expression scoring to assess pain in humans and non-humans is now well utilized, and the Sheep Pain Facial Expression Scale (SPFES) is a tool that can reliably detect pain in this species. The SPFES currently requires manual scoring, leaving it open to observer bias, and it is also time-consuming. The ability of a computer to automatically detect and direct a producer as to where assessment and treatment are needed would increase the chances of controlling the spread of disease. It would also aid in the prevention of resistance across the individual, farm, and landscape at both national and international levels. In this paper, we present our framework for an integrated novel system based on techniques originally applied for human facial expression recognition that could be implemented at the farm level. To the authors' knowledge, this is the first time that this technology has been applied to sheep to assess pain.

Fast Pig Detection with a Top-View Camera under Various Illumination Conditions

The fast detection of pigs is a crucial aspect for a surveillance environment intended for the ultimate purpose of the 24 h tracking of individual pigs. Particularly, in a realistic pig farm environment, one should consider various illumination conditions such as sunlight, but such consideration has not been reported yet. We propose a fast method to detect pigs under various illumination conditions by exploiting the complementary information from depth and infrared images. By applying spatiotemporal interpolation, we first remove the noises caused by sunlight. Then, we carefully analyze the characteristics of both the depth and infrared information and detect pigs using only simple image processing techniques. Rather than exploiting highly time-consuming techniques, such as frequency-, optimization-, or deep learning-based detections, our image processing-based method can guarantee a fast execution time for the final goal, i.e., intelligent pig monitoring applications. In the experimental results, pigs could be detected effectively through the proposed method for both accuracy (i.e., 0.79) and execution time (i.e., 8.71 ms), even with various illumination conditions.

Multi-Pig Part Detection and Association with a Fully-Convolutional Network

Computer vision systems have the potential to provide automated, non-invasive monitoring of livestock animals, however, the lack of public datasets with well-defined targets and evaluation metrics presents a significant challenge for researchers. Consequently, existing solutions often focus on achieving task-specific objectives using relatively small, private datasets. This work introduces a new dataset and method for instance-level detection of multiple pigs in group-housed environments. The method uses a single fully-convolutional neural network to detect the location and orientation of each animal, where both body part locations and pairwise associations are represented in the image space. Accompanying this method is a new dataset containing 2000 annotated images with 24,842 individually annotated pigs from 17 different locations. The proposed method achieves over 99% precision and over 96% recall when detecting pigs in environments previously seen by the network during training. To evaluate the robustness of the trained network, it is also tested on environments and lighting conditions unseen in the training set, where it achieves 91% precision and 67% recall. The dataset is publicly available for download.

Review: Environmental impact of livestock farming and Precision Livestock Farming as a mitigation strategy

This paper reviews the environmental impact of current livestock practices and discusses the advantages offered by Precision Livestock Farming (PLF), as a potential strategy to mitigate environmental risks. PLF is defined as: "the application of process engineering principles and techniques to livestock farming to automatically monitor, model and manage animal production". The primary goal of PLF is to make livestock farming more economically, socially and environmentally sustainable and this can be obtained through the observation, interpretation of behaviours and, if possible, individual control of animals. Furthermore, adopting PLF to support management strategies, may lead to the reduction of the environmental impact of farms. Currently, few studies reported PLF efficacy in reducing the environmental impact, however further studies are necessary to better analyze the actual potential of PLF as a mitigation strategy. Literature shows the potentiality of the application of PLF, as the introduction of PLF in farms can lead to a reduction of Greenhouse gases (GHG) and ammonia (NH3) emission in air, nitrates and antibiotics pollution in water bodies, phosphorus, antibiotics and heavy metals in the soil.

Activity Behaviour of Minipigs Transgenic for the Huntington Gene

BACKGROUND

To increase the reliability of translating preclinical findings to humans, large animal models, such as the transgenic (tg) Libechov minipig, were established. As minipigs possess high genetic homology with humans and have similarities in anatomy, physiology and metabolism to humans, they are considered for studying neurodegenerative diseases longitudinally. Recently, sleep abnormalities and changes in circadian rhythm in Huntington's disease (HD) patients were acknowledged to present one of the early symptoms in HD.

OBJECTIVE

The aim of the present study was to explore the activity behaviour of Libechov minipigs and to investigate whether tgHD and wildtype (wt) minipigs exhibit differences in activity behaviour. Furthermore, it was investigated whether activity assessments may serve as reliable endpoints for phenotyping minipigs transgenic for the Huntington gene.

METHODS

Activity behaviour of minipigs was studied by video recording the stables twice a week over a total study period of five weeks for a cohort of five tgHD minipigs and five wt minipigs. Statistical analysis was performed using the linear mixed model. Once a week, the distances covered by two minipigs in focus (tgHD, wt) were measured using the VideoMotionTracker® software.

RESULTS

Libechov minipigs showed a biphasic pattern of activity, spending most of the time inactive or grubbing in litter. Differences in activity behaviour (rooting, resting and standing) were detected between wt and tgHD minipigs. The influence of the genotype on behavioural patterns was observed during circadian monitoring. TgHD minipigs covered longer distances on average and during every 24 h observation period than wt minipigs.

CONCLUSION

Activity behaviour may be a viable marker for phenotyping minipigs transgenic for the Huntington gene. Video recordings of behavioural patterns provide a non-invasive opportunity to capture potential disease signs. Phenotypic progression including the age of disease manifestation may be explored by documentation of circadian characteristics.

Antimicrobial Stewardship in Veterinary Medicine

While antimicrobial resistance is already a public health crisis in human medicine, therapeutic failure in veterinary medicine due to antimicrobial resistance remains relatively uncommon. However, there are many pathways by which antimicrobial resistance determinants can travel between animals and humans: by close contact, through the food chain, or indirectly via the environment. Antimicrobial stewardship describes measures that can help mitigate the public health crisis and preserve the effectiveness of available antimicrobial agents. Antimicrobial stewardship programs have been principally developed, implemented, and studied in human hospitals but are beginning to be adapted for other applications in human medicine. Key learning from the experiences of antimicrobial stewardship programs in human medicine are summarized in this article-guiding the development of a stewardship framework suitable for adaptation and use in both companion animal and livestock practice. The antimicrobial stewardship program for veterinary use integrates infection prevention and control together with approaches emphasizing avoidance of antimicrobial agents. The 5R framework of continuous improvement that is described recognizes the importance of executive support; highly motivated organizations and teams (responsibility); the need to review the starting position, set objectives, and determine means of measuring progress and success; and a critical focus on reducing, replacing, and refining the use of antimicrobial agents. Significant issues that are currently the focus of intensive research include improved detection and diagnosis of infections, refined dosing regimens that are simultaneously effective while not selecting resistance, searches for alternatives to antimicrobial agents, and development of improved vaccines to enhance immunity and reduce disease.

A systematic literature mapping and meta-analysis of animal-based traits as indicators of production diseases in pigs

The choice of animal-based traits to identify and deal with production diseases is often a challenge for pig farmers, researchers and other related professionals. This systematic review focused on production diseases, that is, the diseases that arise from management practices, affecting the digestive, locomotory and respiratory system of pigs. The aim was to classify all traits that have been measured and conduct a meta-analysis to quantify the impact of diseases on these traits so that these can be used as indicators for intervention. Data were extracted from 67 peer-reviewed publications selected from 2339 records. Traits were classified as productive (performance and carcass composition), behavioural, biochemical and molecular traits. A meta-analysis based on mixed models was performed on traits assessed more than five times across studies, using the package metafor of the R software. A total of 524 unique traits were recorded 1 to 31 times in a variety of sample material including blood, muscle, articular cartilage, bone or at the level of whole animal. No behavioural traits were recorded from the included experiments. Only 14 traits were measured on more than five occasions across studies. Traits within the biochemical, molecular and productive trait groups were reported most frequently in the published literature and were most affected by production diseases; among these were some cytokines (interleukin (IL) 1-β, IL6, IL8 and tumour necrosis factor-α), acute phase proteins (haptoglobin) and daily weight gain. Quantification of the influence of factors relating to animal characteristics or husbandry practices was not possible, due to the low frequency of reporting throughout the literature. To conclude, this study has permitted a holistic assessment of traits measured in the published literature to study production diseases occurring in various stages of the production cycle of pigs. It shows the lack of consensus and common measurements of traits to characterise production diseases within the scientific literature. Specific traits, most of them relating to performance characteristics or immunological response of pigs, are proposed for further study as potential tools for the prognosis and study of production diseases.

A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors

We designed and evaluated an assumption-free, deep learning-based methodology for animal health monitoring, specifically for the early detection of respiratory disease in growing pigs based on environmental sensor data. Two recurrent neural networks (RNNs), each comprising gated recurrent units (GRUs), were used to create an autoencoder (GRU-AE) into which environmental data, collected from a variety of sensors, was processed to detect anomalies. An autoencoder is a type of network trained to reconstruct the patterns it is fed as input. By training the GRU-AE using environmental data that did not lead to an occurrence of respiratory disease, data that did not fit the pattern of "healthy environmental data" had a greater reconstruction error. All reconstruction errors were labelled as either normal or anomalous using threshold-based anomaly detection optimised with particle swarm optimisation (PSO), from which alerts are raised. The results from the GRU-AE method outperformed state-of-the-art techniques, raising alerts when such predictions deviated from the actual observations. The results show that a change in the environment can result in occurrences of pigs showing symptoms of respiratory disease within 1⁻7 days, meaning that there is a period of time during which their keepers can act to mitigate the negative effect of respiratory diseases, such as porcine reproductive and respiratory syndrome (PRRS), a common and destructive disease endemic in pigs.

A Kinect-Based Segmentation of Touching-Pigs for Real-Time Monitoring

Segmenting touching-pigs in real-time is an important issue for surveillance cameras intended for the 24-h tracking of individual pigs. However, methods to do so have not yet been reported. We particularly focus on the segmentation of touching-pigs in a crowded pig room with low-contrast images obtained using a Kinect depth sensor. We reduce the execution time by combining object detection techniques based on a convolutional neural network (CNN) with image processing techniques instead of applying time-consuming operations, such as optimization-based segmentation. We first apply the fastest CNN-based object detection technique (i.e., You Only Look Once, YOLO) to solve the separation problem for touching-pigs. If the quality of the YOLO output is not satisfied, then we try to find the possible boundary line between the touching-pigs by analyzing the shape. Our experimental results show that this method is effective to separate touching-pigs in terms of both accuracy (i.e., 91.96%) and execution time (i.e., real-time execution), even with low-contrast images obtained using a Kinect depth sensor.

Unravelling variation in feeding, social interaction and growth patterns among pigs using an agent-based model

Domesticated pigs, Sus scrofa, vary considerably in feeding, social interaction and growth patterns. This variation originates partly from genetic variation that affects physiological factors and partly from behavioural strategies (avoid or approach) in competitive food resource situations. Currently, it is unknown how variation in physiological factors and in behavioural strategies among animals contributes to variation in feeding, social interaction and growth patterns in animals. The aim of this study was to unravel causation of variation in these patterns among pigs. We used an agent-based model to explore the effects of physiological factors and behavioural strategies in pigs on variation in feeding, social interaction and growth patterns. Model results show that variation in feeding, social interaction and growth patterns are caused partly by chance, such as time effects and coincidence of conflicts. Furthermore, results show that seemingly contradictory empirical findings in literature can be explained by variation in pig characteristics (i.e. growth potential, positive feedback, dominance, and coping style). Growth potential mainly affected feeding and growth patterns, whereas positive feedback, dominance and coping style affected feeding patterns, social interaction patterns, as well as growth patterns. Variation in behavioural strategies among pigs can reduce aggression at group level, but also make some pigs more susceptible to social constraints inhibiting them from feeding when they want to, especially low-ranking pigs and pigs with a passive coping style. Variation in feeding patterns, such as feeding rate or meal frequency, can indicate social constraints. Feeding patterns, however, can say something different about social constraints at group versus individual level. A combination of feeding patterns, such as a decreased feed intake, an increased feeding rate, and an increased meal frequency might, therefore, be needed to measure social constraints at individual level.

Automatic early warning of tail biting in pigs: 3D cameras can detect lowered tail posture before an outbreak

Tail biting is a major welfare and economic problem for indoor pig producers worldwide. Low tail posture is an early warning sign which could reduce tail biting unpredictability. Taking a precision livestock farming approach, we used Time-of-flight 3D cameras, processing data with machine vision algorithms, to automate the measurement of pig tail posture. Validation of the 3D algorithm found an accuracy of 73.9% at detecting low vs. not low tails (Sensitivity 88.4%, Specificity 66.8%). Twenty-three groups of 29 pigs per group were reared with intact (not docked) tails under typical commercial conditions over 8 batches. 15 groups had tail biting outbreaks, following which enrichment was added to pens and biters and/or victims were removed and treated. 3D data from outbreak groups showed the proportion of low tail detections increased pre-outbreak and declined post-outbreak. Pre-outbreak, the increase in low tails occurred at an increasing rate over time, and the proportion of low tails was higher one week pre-outbreak (-1) than 2 weeks pre-outbreak (-2). Within each batch, an outbreak and a non-outbreak control group were identified. Outbreak groups had more 3D low tail detections in weeks -1, +1 and +2 than their matched controls. Comparing 3D tail posture and tail injury scoring data, a greater proportion of low tails was associated with more injured pigs. Low tails might indicate more than just tail biting as tail posture varied between groups and over time and the proportion of low tails increased when pigs were moved to a new pen. Our findings demonstrate the potential for a 3D machine vision system to automate tail posture detection and provide early warning of tail biting on farm.

Real Time Analysis of Bioanalytes in Healthcare, Food, Zoology and Botany

The growing demand for real time analysis of bioanalytes has spurred development in the field of wearable technology to offer non-invasive data collection at a low cost. The manufacturing processes for creating these sensing systems vary significantly by the material used, the type of sensors needed and the subject of study as well. The methods predominantly involve stretchable electronic sensors to monitor targets and transmit data mainly through flexible wires or short-range wireless communication devices. Capable of conformal contact, the application of wearable technology goes beyond the healthcare to fields of food, zoology and botany. With a brief review of wearable technology and its applications to various fields, we believe this mini review would be of interest to the reader in broad fields of materials, sensor development and areas where wearable sensors can provide data that are not available elsewhere.

Automated tracking to measure behavioural changes in pigs for health and welfare monitoring

Since animals express their internal state through behaviour, changes in said behaviour may be used to detect early signs of problems, such as in animal health. Continuous observation of livestock by farm staff is impractical in a commercial setting to the degree required to detect behavioural changes relevant for early intervention. An automated monitoring system is developed; it automatically tracks pig movement with depth video cameras, and automatically measures standing, feeding, drinking, and locomotor activities from 3D trajectories. Predictions of standing, feeding, and drinking were validated, but not locomotor activities. An artificial, disruptive challenge; i.e., introduction of a novel object, is used to cause reproducible behavioural changes to enable development of a system to detect the changes automatically. Validation of the automated monitoring system with the controlled challenge study provides a reproducible framework for further development of robust early warning systems for pigs. The automated system is practical in commercial settings because it provides continuous monitoring of multiple behaviours, with metrics of behaviours that may be considered more intuitive and have diagnostic validity. The method has the potential to transform how livestock are monitored, directly impact their health and welfare, and address issues in livestock farming, such as antimicrobial use.

Depth-Based Detection of Standing-Pigs in Moving Noise Environments

In a surveillance camera environment, the detection of standing-pigs in real-time is an important issue towards the final goal of 24-h tracking of individual pigs. In this study, we focus on depth-based detection of standing-pigs with “moving noises”, which appear every night in a commercial pig farm, but have not been reported yet. We first apply a spatiotemporal interpolation technique to remove the moving noises occurring in the depth images. Then, we detect the standing-pigs by utilizing the undefined depth values around them. Our experimental results show that this method is effective for detecting standing-pigs at night, in terms of both cost-effectiveness (using a low-cost Kinect depth sensor) and accuracy (i.e., 94.47%), even with severe moving noises occluding up to half of an input depth image. Furthermore, without any time-consuming technique, the proposed method can be executed in real-time.

Motion-based video monitoring for early detection of livestock diseases: The case of African swine fever

Early detection of infectious diseases can substantially reduce the health and economic impacts on livestock production. Here we describe a system for monitoring animal activity based on video and data processing techniques, in order to detect slowdown and weakening due to infection with African swine fever (ASF), one of the most significant threats to the pig industry. The system classifies and quantifies motion-based animal behaviour and daily activity in video sequences, allowing automated and non-intrusive surveillance in real-time. The aim of this system is to evaluate significant changes in animals’ motion after being experimentally infected with ASF virus. Indeed, pig mobility declined progressively and fell significantly below pre-infection levels starting at four days after infection at a confidence level of 95%. Furthermore, daily motion decreased in infected animals by approximately 10% before the detection of the disease by clinical signs. These results show the promise of video processing techniques for real-time early detection of livestock infectious diseases.

Technical note: Use of an automated grooming brush by heifers and potential for radiofrequency identification-based measurements of this behavior

Healthy cattle readily use grooming brushes but this behavior subsides when animals become ill. Tracking use of a brush may provide an opportunity for health monitoring, especially if the process could be automated. We assessed how healthy heifers groom themselves on a brush and hypothesized that radiofrequency identification (RFID) could be used to accurately and automatically record this behavior. Angus and Hereford heifers (n = 16) were fitted with 2 ultra-high-frequency RFID ear tags and monitored in groups of 8 while housed in a pen with an electronic brush, video cameras, and 4 RFID antennas. Each heifer was observed for a 6-h period using continuous video recordings, and brush contact was characterized in terms of anatomic region involved (head/neck, trunk, or posterior) and when not touching the brush but within 1 body length of it. The RFID data were collected for the same period and then processed such that intervals of up to 16 s with no detections but contained between 2 recordings were also considered positive (animal in brush proximity). Brush proximity (RFID) was regressed against brush contact duration (video) and the sensitivity and specificity for each individual heifer calculated. Across heifers, the majority of brush use involved the head/neck, although a few heifers demonstrated relatively large amounts of posterior contact, which contributed to false-negative readings when antennas failed to read the ear tags. Furthermore, for the majority of time that animals were near the brush, they were not in contact with it but rather standing or lying nearby, resulting in false-positive readings. It follows that the ability of the RFID system to accurately detect brush contact varied widely across individual heifers (sensitivity 0.54-1.0; specificity 0.59-0.98), with RFID generally overestimating the duration of brush proximity relative to actual time spent in brush contact. The implication is that RFID-based ear tag recording of brush proximity relative to continuous video observations of contact does not yield accurate results in certain heifers and therefore, as currently configured, is not a reliable representation of this type of grooming behavior.