Classifying the posture and activity of ewes and lambs using accelerometers and machine learning on a commercial flock

Davis

et al. 2022

Animals

The application of precision livestock farming (PLF) technologies will underpin new strategies to support the control of livestock disease. However, PLF technology is underexploited within the sheep industry compared to other livestock sectors, and research is essential to identify opportunities for PLF applications. These opportunities include the control of endemic sheep disease such as parasitic gastroenteritis, caused by gastrointestinal nematode infections, which is estimated to cost the European sheep industry EUR 120 million annually. In this study, tri-axial accelerometers recorded the behaviour of 54 periparturient Welsh Mule ewes to discover if gastrointestinal nematode (GIN) infection burden, as measured by faecal egg count (FEC), was associated with behavioural variation. Linear mixed models identified that increasing FECs in periparturient ewes were significantly associated with a greater number of lying bouts per day and lower bout durations (p = 0.013 and p = 0.010, respectively). The results demonstrate that FECs of housed periparturient ewes are associated with detectable variations in ewe behaviour, and as such, with further investigation there is potential to develop future targeted selective treatment protocols against GIN in sheep based on behaviour as measured by PLF technologies.

Section: Discussionmentioning

confidence: 99%

Associations between Gastrointestinal Nematode Infection Burden and Lying Behaviour as Measured by Accelerometers in Periparturient Ewes

Davis

et al. 2022

Animals

“…Additionally, there is now considerable use of machine learning to classify postures and other behaviours, particularly among farm animals (e.g. Hansen et al ., 2018; Neethirajan, 2020; Balasso et al ., 2021; Price et al ., 2022).…”

Section: Measuring Positive Affect In Non‐human Animalsmentioning

confidence: 99%

Joyful by nature: approaches to investigate the evolution and function of joy in non‐human animals

Nelson

Taylor

Cartmill³

et al. 2023

Biological Reviews

The nature and evolution of positive emotion is a major question remaining unanswered in science and philosophy. The study of feelings and emotions in humans and animals is dominated by discussion of affective states that have negative valence. Given the clinical and social significance of negative affect, such as depression, it is unsurprising that these emotions have received more attention from scientists. Compared to negative emotions, such as fear that leads to fleeing or avoidance, positive emotions are less likely to result in specific, identifiable, behaviours being expressed by an animal. This makes it particularly challenging to quantify and study positive affect. However, bursts of intense positive emotion (joy) are more likely to be accompanied by externally visible markers, like vocalisations or movement patterns, which make it more amenable to scientific study and more resilient to concerns about anthropomorphism. We define joy as intense, brief, and event‐driven (i.e. a response to something), which permits investigation into how animals react to a variety of situations that would provoke joy in humans. This means that behavioural correlates of joy are measurable, either through newly discovered ‘laughter’ vocalisations, increases in play behaviour, or reactions to cognitive bias tests that can be used across species. There are a range of potential situations that cause joy in humans that have not been studied in other animals, such as whether animals feel joy on sunny days, when they accomplish a difficult feat, or when they are reunited with a familiar companion after a prolonged absence. Observations of species‐specific calls and play behaviour can be combined with biometric markers and reactions to ambiguous stimuli in order to enable comparisons of affect between phylogenetically distant taxonomic groups. Identifying positive affect is also important for animal welfare because knowledge of positive emotional states would allow us to monitor animal well‐being better. Additionally, measuring if phylogenetically and ecologically distant animals play more, laugh more, or act more optimistically after certain kinds of experiences will also provide insight into the mechanisms underlying the evolution of joy and other positive emotions, and potentially even into the evolution of consciousness.

“…The sensors of Actiwatch Mini ® activity monitor attached to the necks of the ewes when used in combination with the activity scores to record behaviors with an overall accuracy of 79.98% and 74.56% for active and inactive, respectively [92]. The accelerometer GENEActiv has a 83.7% average accuracy of standing and lying and a 80.8% average accuracy of grazing, rumination, inactive and walking in ewes, a 85.9% average accuracy of standing and lying and a 85.9% average accuracy of inactive, suckling, walking in lambs by random forest decision tree [102], while the accelerometer ActiGraph can detect the grazing, walking and resting behaviors of lambs on pasture with a classification accuracy of 89.6% [103]. The neck-mounted devices of AXY-3 accelerometer were used along with fractal methods to record temporal sequences of behavioral activity patterns of parasitized sheep which spent 66.03% ± 24.49% of the day and 18.30% ± 8.58% of the night active during the experimental periods, indicating an accurate description of the activity/inactivity patterns of sheep although the activity/inactivity patterns of parasitized sheep rely on long-term activity events and gastrointestinal parasite infection [115].…”

Section: Collar-mounted Accelerometersmentioning

confidence: 99%

Behavioral Fingerprinting: Acceleration Sensors for Identifying Changes in Livestock Health

Fan

Bryant

Greer

2022

During disease or toxin challenges, the behavioral activities of grazing animals alter in response to adverse situations, potentially providing an indicator of their welfare status. Behavioral changes such as feeding behavior, rumination and physical behavior as well as expressive behavior, can serve as indicators of animal health and welfare. Sometimes behavioral changes are subtle and occur gradually, often missed by infrequent visual monitoring until the condition becomes acute. There is growing popularity in the use of sensors for monitoring animal health. Acceleration sensors have been designed to attach to ears, jaws, noses, collars and legs to detect the behavioral changes of cattle and sheep. So far, some automated acceleration sensors with high accuracies have been found to have the capacity to remotely monitor the behavioral patterns of cattle and sheep. These acceleration sensors have the potential to identify behavioral patterns of farm animals for monitoring changes in behavior which can indicate a deterioration in health. Here, we review the current automated accelerometer systems and the evidence they can detect behavioral patterns of animals for the application of potential directions and future solutions for automatically monitoring and the early detection of health concerns in grazing animals.