Early detection of bovine respiratory disease in pre-weaned dairy calves using sensor based feeding, movement, and social behavioural data.

Previous research shows that feeding and activity behaviours in combination with machine learning algorithms has the potential to predict the onset of bovine respiratory disease (BRD). This study used 229 novel and previously researched feeding, movement, and social behavioural features with machine learning classification algorithms to predict BRD events in pre-weaned calves. Data for 172 group housed calves were collected using automatic milk feeding machines and ultrawideband location sensors. Health assessments were carried out twice weekly using a modified Wisconsin scoring system and calves were classified as sick if they had a Wisconsin score of five or above and/or a rectal temperature of 39.5 °C or higher. A gradient boosting machine classification algorithm produced moderate to high performance: accuracy (0.773), precision (0.776), sensitivity (0.625), specificity (0.872), and F1-score (0.689). The most important 30 features were 40% feeding, 50% movement, and 10% social behavioural features. Movement behaviours, specifically the distance walked per day, were most important for model prediction, whereas feeding and social features aided in the model's prediction minimally. These results highlighting the predictive potential in this area but the need for further improvement before behavioural changes can be used to reliably predict the onset of BRD in pre-weaned calves.

Bunching behavior in housed dairy cows at higher ambient temperatures.

Bunching behavior in cattle may occur for several reasons including enabling social interactions, a response to stress or danger, or due to shared interest in resources such as feeding or watering areas. There is evidence in pasture grazed cattle that bunching may occur more frequently at higher ambient temperatures, possibly due to sharing of fly-load or to seek shade from the direct sun under heat stress conditions. Here we demonstrate how bunching behavior is associated with higher ambient temperatures in a barn-housed UK dairy herd. A real-time local positioning system was used, as part of a precision livestock farming (PLF) approach, to track the spatial position and activity of a commercial dairy herd (∼100 cows) in a freestall barn continuously at high temporal resolution for 4 mo between August and November 2014. Bunching was determined using 4 different spatial measures determined on an hourly basis: herd full and core range size, mean herd intercow distance (ICD), and mean herd nearest-neighbor distance (NND). For hourly mean ambient temperatures above 20°C, the herd showed higher bunching behavior with increasing ambient temperature (i.e., reduced full and core range size, ICD, and NND). Aggregated space-use intensity was found to positively correlate with localized variations in temperature across the barn (as measured by animal-mounted sensors), but the level of correlation decreased at higher ambient barn temperatures. Bunching behavior may increase localized temperatures experienced by individuals and hence may be a maladaptive behavioral response in housed dairy cattle, which are known to suffer heat stress at higher temperatures. Our study is the first to use high-resolution positional data to provide evidence of associations between bunching behavior and higher ambient temperatures for a barn-housed dairy herd in a temperate region (UK). Further studies are needed to explore the exact mechanisms for this response to inform both welfare and production management.

Evidence of personality-dependent plasticity in dairy calf movement behaviours derived from automated data collection.

Individual consistency in behaviour, known as animal personality, and behavioural plasticity in response to environmental changes are important factors shaping individual behaviour. Correlations between them, called personality-dependent plasticity, indicate that personality can affect individual reactions to the environment. In farm animals this could impact the response to management changes or stressors but has not yet been investigated. Here we use ultra-wideband location sensors to measure personality and plasticity in the movement of 90 dairy calves for up to 56 days starting in small pair-housing enclosures, and subsequently moved to larger social housings. For the first time calves were shown to differ in personality and plasticity of movement when changing housing. There were significant correlations between personality and plasticity for distance travelled (0.57), meaning that individuals that travelled the furthest in the pair housing increased their movement more in the social groups, and for residence time (- 0.65) as those that stayed in the same area more decreased more with the change in housing, demonstrating personality-dependent plasticity. Additionally, calves conformed to their pen-mate's behaviour in pairs, but this did not continue in the groups. Therefore, personality, plasticity and social effects impact how farm animals respond to changes and can inform management decisions.

Accurate prediction of calving in dairy cows by applying feature engineering and machine learning.

Prediction of calving is key to dairy cow management. Current trends of increasing herd sizes globally can directly impact the time that farmers spend monitoring individual animals. Automated monitoring on behavioural and physiological changes prior to parturition can be used to develop machine learning solutions for calving prediction. In this study, we developed a machine learning algorithm for the prediction of calving in dairy cows. We demonstrated that temperature and activity index information retrieved from a commercial reticuloruminal bolus sensor can accurately predict calving from 1-day to 5-days in advance. The best prediction solution using data from 82 dairy cows, achieved up to 87.81 % in accuracy, 92.99 % in specificity, 75.84 % in sensitivity, 82.99 % in positive predictive value (PPV), 78.85 % in F-score, and 90.02 % in negative predictive value (NPV) on the test dataset when using information from 2-days in advance and all the subsets of feature characteristics (temperature + drinking + activity). The performance only decreased by 2.45 % points in accuracy, 0.74 % points in specificity, 6.41 % points in sensitivity, 2.45 % points in positive predictive value, 4.91 % points in F-score, and 2.44 % points in negative predictive value on the test dataset when using all feature characteristics and 5-days in advance information compared to using all features and information from 2-days in advance. Full evaluation of the performance of the prediction showed an improvement when using all the different subsets of feature characteristics together (temperature, activity, and drinking) compared to using temperature features only. When adding activity and drinking to the subset of temperature features, an average increase of 2.70, 1.52, 5.40, 4.39, 5.02, 2.13 % points in accuracy, specificity, sensitivity, PPV, F-score, and NPV, respectively, was obtained. Notably, evaluation of feature importance (i.e., relative weight of any given feature in relation to model prediction) showed that 3-5 (depending on the selected days in advance model) of the top ten features were derived from drinking behaviour, showing the relevance that this behaviour can have in the prediction of calving. This algorithm can provide a useful tool for automated calving prediction in dairy cows which has potential for improvement of health, welfare, and productivity in the dairy industry.

Familiarity, age, weaning and health status impact social proximity networks in dairy calves.

Social network analysis in dairy calves has not been widely studied, with previous studies limited by the short study duration, and low number of animals and replicates. In this study, we investigated social proximity interactions of 79 Holstein-Friesian calves from 5 cohorts for up to 76 days. Networks were computed using 4-day aggregated associations obtained from ultrawideband location sensor technology, at 1 Hz sampling rate. The effect of age, familiarity, health, and weaning status on the social proximity networks of dairy calves was assessed. Networks were poorly correlated (non-stable) between the different 4-day periods, in the majority of them calves associated heterogeneously, and individuals assorted based on previous familiarity for the whole duration of the study. Age significantly increased association strength, social time and eigenvector centrality and significantly decreased closeness and coefficient of variation in association (CV). Sick calves had a significantly lower strength, social time, centrality and CV, and significantly higher closeness compared to the healthy calves. During and after weaning, calves had significantly lower closeness and CV, and significantly higher association strength, social time, and eigenvector centrality. These results indicate that age, familiarity, weaning, and sickness have a significant impact on the variation of social proximity interaction of calves.

Indication of a personality trait in dairy calves and its link to weight gain through automatically collected feeding behaviours.

Farm animal personality traits are of interest since they can help predict individual variation in behaviour and productivity. However, personality traits are currently inferred using behavioural tests which are impractical outside of research settings. To meet the definition of a personality trait, between-individual differences in related behaviours must be temporally as well as contextually stable. In this study, we used data collected by computerised milk feeders from 76 calves over two contexts, pair housing and group housing, to test if between-individual differences in feeding rate and meal frequency meet the definition for a personality trait. Results show that between-individual differences in feeding rate and meal frequency were related, and, for each behaviour, between-individual differences were positively and significantly correlated across contexts. In addition, feeding rate and meal frequency were positively and significantly associated with weight gain. Together, these results indicate the existence of a personality trait which positions high meal frequency, fast drinking, fast growing calves at one end and low meal frequency, slow drinking, and slow growing calves at the other. Our results suggest that data already available on commercial farms could be harnessed to establish a personality trait.

Personality and predictability in farmed calves using movement and space-use behaviours quantified by ultra-wideband sensors.

Individuals within a population often show consistent between individual differences in their average behavioural expression (personality), and consistent differences in their within individual variability of behaviour around the mean (predictability). Where correlations between different personality traits and/or the predictability of traits exist, these represent behavioural or predictability syndromes. In wild populations, behavioural syndromes have consequences for individuals' survival and reproduction and affect the structure and functioning of groups and populations. The consequences of behavioural syndromes for farm animals are less well explored, partly due to the challenges in quantifying behaviour of many individuals across time and context in a farm setting. Here, we use ultra-wideband location sensors to provide precise measures of movement and space use for 60 calves over 40-48 days. We are the first livestock study to demonstrate consistent within and between individual variation in movement and space use with repeatability values of up to 0.80 and CVp values up to 0.49. Our results show correlations in personality and predictability, indicating the existence of 'exploratory' and 'active' personality traits in farmed calves. We consider the consequences of such individual variability for cattle behaviour and welfare and how such data may be used to inform management decisions in farm animals.

Repeatability and Predictability of Calf Feeding Behaviors-Quantifying Between- and Within-Individual Variation for Precision Livestock Farming.

Individual calves show substantial between- and within-individual variation in their feeding behavior, the existence and extent of which are not fully researched. In this study, 57,196 feeding records, collected by a computerized milk feeder from 48 pre-weaned calves over 5 weeks, were collated and analyzed for individual differences in three different feeding behaviors using a multi-level modeling approach. For each feeding behavior, we quantified behavioral variation by calculating repeatability and the coefficient of variation in predictability. Our results indicate that calves differed from each other in their average behavioral expression (behavioral type) and in their residual, within individual variation around their behavioral type (predictability). Feeding rate and total meals had the highest repeatability (>0.4) indicating that substantial, temporally stable between-individual differences exist for these behaviors. Additionally, for some behaviors (e.g., feeding rate) calves varied from more to less predictable whereas for other behaviors (e.g., meal size) calves were more homogenous in their within-individual variation around their behavioral type. Finally, we show that for individual calves, behavioral types for feeding rate and total meals were positively correlated which may suggest the existence of an underlying factor responsible for driving the (co)expression of these two behaviors. Our results highlight how the application of methods from the behavioral ecology literature can assist in improving our understanding of individual differences in calf feeding behavior. Furthermore, by uncovering consistencies between individual behavioral differences in calves, our results indicate that animal personality may play a role in driving variability in calf feeding behavior.

Machine Learning Algorithms to Classify and Quantify Multiple Behaviours in Dairy Calves Using a Sensor: Moving beyond Classification in Precision Livestock.

Previous research has shown that sensors monitoring lying behaviours and feeding can detect early signs of ill health in calves. There is evidence to suggest that monitoring change in a single behaviour might not be enough for disease prediction. In calves, multiple behaviours such as locomotor play, self-grooming, feeding and activity whilst lying are likely to be informative. However, these behaviours can occur rarely in the real world, which means simply counting behaviours based on the prediction of a classifier can lead to overestimation. Here, we equipped thirteen pre-weaned dairy calves with collar-mounted sensors and monitored their behaviour with video cameras. Behavioural observations were recorded and merged with sensor signals. Features were calculated for 1-10-s windows and an AdaBoost ensemble learning algorithm implemented to classify behaviours. Finally, we developed an adjusted count quantification algorithm to predict the prevalence of locomotor play behaviour on a test dataset with low true prevalence (0.27%). Our algorithm identified locomotor play (99.73% accuracy), self-grooming (98.18% accuracy), ruminating (94.47% accuracy), non-nutritive suckling (94.96% accuracy), nutritive suckling (96.44% accuracy), active lying (90.38% accuracy) and non-active lying (90.38% accuracy). Our results detail recommended sampling frequencies, feature selection and window size. The quantification estimates of locomotor play behaviour were highly correlated with the true prevalence (0.97; p < 0.001) with a total overestimation of 18.97%. This study is the first to implement machine learning approaches for multi-class behaviour identification as well as behaviour quantification in calves. This has potential to contribute towards new insights to evaluate the health and welfare in calves by use of wearable sensors.

Proximity Interactions in a Permanently Housed Dairy Herd: Network Structure, Consistency, and Individual Differences.

Understanding the herd structure of housed dairy cows has the potential to reveal preferential interactions, detect changes in behavior indicative of illness, and optimize farm management regimes. This study investigated the structure and consistency of the proximity interaction network of a permanently housed commercial dairy herd throughout October 2014, using data collected from a wireless local positioning system. Herd-level networks were determined from sustained proximity interactions (pairs of cows continuously within three meters for 60 s or longer), and assessed for social differentiation, temporal stability, and the influence of individual-level characteristics such as lameness, parity, and days in milk. We determined the level of inter-individual variation in proximity interactions across the full barn housing, and for specific functional zones within it (feeding, non-feeding). The observed networks were highly connected and temporally varied, with significant preferential assortment, and inter-individual variation in daily interactions in the non-feeding zone. We found no clear social assortment by lameness, parity, or days in milk. Our study demonstrates the potential benefits of automated tracking technology to monitor the proximity interactions of individual animals within large, commercially relevant groups of livestock.

Automated detection of lameness in sheep using machine learning approaches: novel insights into behavioural differences among lame and non-lame sheep.

Lameness in sheep is the biggest cause of concern regarding poor health and welfare among sheep-producing countries. Best practice for lameness relies on rapid treatment, yet there are no objective measures of lameness detection. Accelerometers and gyroscopes have been widely used in human activity studies and their use is becoming increasingly common in livestock. In this study, we used 23 datasets (10 non-lame and 13 lame sheep) from an accelerometer- and gyroscope-based ear sensor with a sampling frequency of 16 Hz to develop and compare algorithms that can differentiate lameness within three different activities (walking, standing and lying). We show for the first time that features extracted from accelerometer and gyroscope signals can differentiate between lame and non-lame sheep while standing, walking and lying. The random forest algorithm performed best for classifying lameness with an accuracy of 84.91% within lying, 81.15% within standing and 76.83% within walking and overall correctly classified over 80% sheep within activities. Both accelerometer- and gyroscope-based features ranked among the top 10 features for classification. Our results suggest that novel behavioural differences between lame and non-lame sheep across all three activities could be used to develop an automated system for lameness detection.

A Combined Offline and Online Algorithm for Real-Time and Long-Term Classification of Sheep Behaviour: Novel Approach for Precision Livestock Farming.

Real-time and long-term behavioural monitoring systems in precision livestock farming have huge potential to improve welfare and productivity for the better health of farm animals. However, some of the biggest challenges for long-term monitoring systems relate to "concept drift", which occurs when systems are presented with challenging new or changing conditions, and/or in scenarios where training data is not accurately reflective of live sensed data. This study presents a combined offline algorithm and online learning algorithm which deals with concept drift and is deemed by the authors as a useful mechanism for long-term in-the-field monitoring systems. The proposed algorithm classifies three relevant sheep behaviours using information from an embedded edge device that includes tri-axial accelerometer and tri-axial gyroscope sensors. The proposed approach is for the first time reported in precision livestock behavior monitoring and demonstrates improvement in classifying relevant behaviour in sheep, in real-time, under dynamically changing conditions.

Space-use patterns highlight behavioural differences linked to lameness, parity, and days in milk in barn-housed dairy cows.

Lameness is a key health and welfare issue affecting commercial herds of dairy cattle, with potentially significant economic impacts due to the expense of treatment and lost milk production. Existing lameness detection methods can be time-intensive, and under-detection remains a significant problem leading to delayed or missed treatment. Hence, there is a need for automated monitoring systems that can quickly and accurately detect lameness in individual cows within commercial dairy herds. Recent advances in sensor tracking technology have made it possible to observe the movement, behaviour and space-use of a range of animal species over extended time-scales. However, little is known about how observed movement behaviour and space-use patterns in individual dairy cattle relate to lameness, or to other possible confounding factors such as parity or number of days in milk. In this cross-sectional study, ten lame and ten non-lame barn-housed dairy cows were classified through mobility scoring and subsequently tracked using a wireless local positioning system. Nearly 900,000 spatial locations were recorded in total, allowing a range of movement and space-use measures to be determined for each individual cow. Using linear models, we highlight where lameness, parity, and the number of days in milk have a significant effect on the observed space-use patterns. Non-lame cows spent more time, and had higher site fidelity (on a day-to-day basis they were more likely to revisit areas they had visited previously), in the feeding area. Non-lame cows also had a larger full range size within the barn. In contrast, lame cows spent more time, and had a higher site-fidelity, in the cubicle (resting) areas of the barn than non-lame cows. Higher parity cows were found to spend more time in the right-hand-side area of the barn, closer to the passageway to the milking parlour. The number of days in milk was found to positively affect the core range size, but with a negative interaction effect with lameness. Using a simple predictive model, we demonstrate how it is possible to accurately determine the lameness status of all individual cows within the study using only two observed space-use measures, the proportion of time spent in the feeding area and the full range size. Our findings suggest that differences in individual movement and space-use behaviour could be used as indicators of health status for automated monitoring within a Precision Livestock Farming approach, potentially leading to faster diagnosis and treatment, and improved animal welfare for dairy cattle and other managed animal species.

The Status of Pet Rabbit Breeding and Online Sales in the UK: A Glimpse into an Otherwise Elusive Industry.

Conditions of pet rabbit breeding colonies and breeder practices are undocumented and very little is known about the pet rabbit sales market. Here, multiple methods were employed to investigate this sector of the UK pet industry. A freedom of information request sent to 10% of councils revealed confusion and inconsistency in licensing conditions. Data from 1-month of online sale adverts (3446) identified 646 self-declared breeders, of which 1.08% were licensed. Further, despite veterinary advice to vaccinate rabbits from five weeks, only 16.7% rabbits were vaccinated and 9.2% of adult rabbits were neutered. Thirty-three breeders completed a questionnaire of which 51.5% provided smaller housing than recommended, the majority housed rabbits singly and bucks were identified as most at risk of compromised welfare. However, most breeders provided enrichment and gave a diet compliant with recommended guidelines. Mini-lops and Netherland dwarfs were the most commonly sold breeds, both of which are brachycephalic, which can compromise their health and wellbeing. From sales data extrapolation, we estimate that 254,804 rabbits are purposefully bred for the UK online pet sales market each year. This data is the first of its kind and highlights welfare concerns within the pet rabbit breeding sector, which is unregulated and difficult to access.

Evaluation of sampling frequency, window size and sensor position for classification of sheep behaviour.

Automated behavioural classification and identification through sensors has the potential to improve health and welfare of the animals. Position of a sensor, sampling frequency and window size of segmented signal data has a major impact on classification accuracy in activity recognition and energy needs for the sensor, yet, there are no studies in precision livestock farming that have evaluated the effect of all these factors simultaneously. The aim of this study was to evaluate the effects of position (ear and collar), sampling frequency (8, 16 and 32 Hz) of a triaxial accelerometer and gyroscope sensor and window size (3, 5 and 7 s) on the classification of important behaviours in sheep such as lying, standing and walking. Behaviours were classified using a random forest approach with 44 feature characteristics. The best performance for walking, standing and lying classification in sheep (accuracy 95%, F-score 91%-97%) was obtained using combination of 32 Hz, 7 s and 32 Hz, 5 s for both ear and collar sensors, although, results obtained with 16 Hz and 7 s window were comparable with accuracy of 91%-93% and F-score 88%-95%. Energy efficiency was best at a 7 s window. This suggests that sampling at 16 Hz with 7 s window will offer benefits in a real-time behavioural monitoring system for sheep due to reduced energy needs.