Background: Advances in bio-telemetry technology have made it possible to automatically monitor and classify behavioural activities in many animals, including domesticated species such as dairy cows. Automated behavioural classification has the potential to improve health and welfare monitoring processes as part of a Precision Livestock Farming approach. Recent studies have used accelerometers and pedometers to classify behavioural activities in dairy cows, but such approaches often cannot discriminate accurately between biologically important behaviours such as feeding, lying and standing or transition events between lying and standing. In this study we develop a decision-tree algorithm that uses tri-axial accelerometer data from a neck-mounted sensor to both classify biologically important behaviour in dairy cows and to detect transition events between lying and standing. Results: Data were collected from six dairy cows that were monitored continuously for 36 h. Direct visual observations of each cow were used to validate the algorithm. Results show that the decision-tree algorithm is able to accurately classify three types of biologically relevant behaviours: lying (77.42 % sensitivity, 98.63 % precision), standing (88.00 % sensitivity, 55.00 % precision), and feeding (98.78 % sensitivity, 93.10 % precision). Transitions between standing and lying were also detected accurately with an average sensitivity of 96.45 % and an average precision of 87.50 %. The sensitivity and precision of the decision-tree algorithm matches the performance of more computationally intensive algorithms such as hidden Markov models and support vector machines.

No abstract

Spatial scan analyses can complement descriptive statistics, but results must be interpreted with consideration of factors that affect the ability to detect meaningful differences such as the number of events observed, accuracy in geocoding rural versus urban addresses, and the difficulty of adjusting for covariates.

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.

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.