How Lazy Are Pet Cats Really? Using Machine Learning and Accelerometry to Get a Glimpse into the Behaviour of Privately Owned Cats in Different Households.

Surprisingly little is known about how the home environment influences the behaviour of pet cats. This study aimed to determine how factors in the home environment (e.g., with or without outdoor access, urban vs. rural, presence of a child) and the season influences the daily behaviour of cats. Using accelerometer data and a validated machine learning model, behaviours including being active, eating, grooming, littering, lying, scratching, sitting, and standing were quantified for 28 pet cats. Generalized estimating equation models were used to determine the effects of different environmental conditions. Increasing cat age was negatively correlated with time spent active (p < 0.05). Cats with outdoor access (n = 18) were less active in winter than in summer (p < 0.05), but no differences were observed between seasons for indoor-only (n = 10) cats. Cats living in rural areas (n = 7) spent more time eating than cats in urban areas (n = 21; p < 0.05). Cats living in single-cat households (n = 12) spent more time lying but less time sitting than cats living in multi-cat households (n = 16; p < 0.05). Cats in households with at least one child (n = 20) spent more time standing in winter (p < 0.05), and more time lying but less time sitting in summer compared to cats in households with no children (n = 8; p < 0.05). This study clearly shows that the home environment has a major impact on cat behaviour.

The Use of Triaxial Accelerometers and Machine Learning Algorithms for Behavioural Identification in Domestic Cats (Felis catus): A Validation Study.

Animal behaviour can be an indicator of health and welfare. Monitoring behaviour through visual observation is labour-intensive and there is a risk of missing infrequent behaviours. Twelve healthy domestic shorthair cats were fitted with triaxial accelerometers mounted on a collar and harness. Over seven days, accelerometer and video footage were collected simultaneously. Identifier variables (n = 32) were calculated from the accelerometer data and summarized into 1 s epochs. Twenty-four behaviours were annotated from the video recordings and aligned with the summarised accelerometer data. Models were created using random forest (RF) and supervised self-organizing map (SOM) machine learning techniques for each mounting location. Multiple modelling rounds were run to select and merge behaviours based on performance values. All models were then tested on a validation accelerometer dataset from the same twelve cats to identify behaviours. The frequency of behaviours was calculated and compared using Dirichlet regression. Despite the SOM models having higher Kappa (>95%) and overall accuracy (>95%) compared with the RF models (64-76% and 70-86%, respectively), the RF models predicted behaviours more consistently between mounting locations. These results indicate that triaxial accelerometers can identify cat specific behaviours.

What Are Sheep Doing? Tri-Axial Accelerometer Sensor Data Identify the Diel Activity Pattern of Ewe Lambs on Pasture.

Monitoring activity patterns of animals offers the opportunity to assess individual health and welfare in support of precision livestock farming. The purpose of this study was to use a triaxial accelerometer sensor to determine the diel activity of sheep on pasture. Six Perendale ewe lambs, each fitted with a neck collar mounting a triaxial accelerometer, were filmed during targeted periods of sheep activities: grazing, lying, walking, and standing. The corresponding acceleration data were fitted using a Random Forest algorithm to classify activity (=classifier). This classifier was then applied to accelerometer data from an additional 10 ewe lambs to determine their activity budgets. Each of these was fitted with a neck collar mounting an accelerometer as well as two additional accelerometers placed on a head halter and a body harness over the shoulders of the animal. These were monitored continuously for three days. A classification accuracy of 89.6% was achieved for the grazing, walking and resting activities (i.e., a new class combining lying and standing activity). Triaxial accelerometer data showed that sheep spent 64% (95% CI 55% to 74%) of daylight time grazing, with grazing at night reduced to 14% (95% CI 8% to 20%). Similar activity budgets were achieved from the halter mounted sensors, but not those on a body harness. These results are consistent with previous studies directly observing daily activity of pasture-based sheep and can be applied in a variety of contexts to investigate animal health and welfare metrics e.g., to better understand the impact that young sheep can suffer when carrying even modest burdens of parasitic nematodes.

The effect of nutrition and body condition of triplet-bearing ewes during late pregnancy on the behaviour of ewes and lambs.

OBJECTIVE: Triplet-born lambs are less likely to survive to weaning than twin-born or single-born lambs. Appropriate ewe-lamb bonding behaviours and lamb vigour behaviours are necessary for survival of lambs. The aim of this experiment was to determine whether maternal nutrition during late pregnancy influenced behaviour of the ewe and her lambs soon after birth, and to determine whether mid-pregnancy body condition score (BCS) influenced any behavioural response. METHODS: The experiments included ewes that were in BCS 2.0, 2.5, or 3.0 in mid-pregnancy and were fed either ad libitum or to pregnancy-maintenance requirements in late-pregnancy (day 115 until 136 in experiment one, and day 128 until 141 in experiment two). The time taken for lambs to stand, contact dam, suck from dam and follow dam was recorded three to 18 h after birth. The number of high- and low-pitched bleats emitted by the ewe and lambs was recorded, along with maternal behaviour score (MBS) of the ewe. Lambs in experiment two underwent a maternal-recognition test at 12 or 24 h. RESULTS: There were significant effects of feeding treatment on bleating behaviour of ewes and lambs, but these were inconsistent among BCS groups and between experiments. Lamb vigour behaviours were not affected by feeding treatment. In experiment one, there was no effect of feeding treatment or BCS on MBS, but in experiment two, ewes in BCS3 in mid-pregnancy had greater MBS than ewes in BCS2 in mid-pregnancy (MBS 3.1/5 vs MBS 2.1/5; p<0.05). CONCLUSION: Given there were no repeatable effects on behaviour of ewes and lambs, ad libitum feeding rather than feeding for pregnancy-maintenance requirements cannot be used to improve behaviours soon after birth of triplet-bearing ewes in BCS 2-3 and their lambs in extensive pastoral conditions.

Worms and welfare: Behavioural and physiological changes associated with gastrointestinal nematode parasitism in lambs.

Parasitism with gastrointestinal nematodes (GIN) is a worldwide issue impacting negatively on animal production, health, and welfare. Therefore, early diagnostic signs of parasitism are required to allow for timely interventions. The objective of this study was to evaluate the behavioural and physiological changes in lambs associated with GIN infection. We used 30, 8-month-old Romney-cross wethers, that were administered anthelmintics until faecal egg counts (FEC) were zero and housed in an indoor facility. The study lasted 9 weeks, which comprised a 3-week pre-treatment, and a 6-week treatment phase. Lambs were randomly assigned to one of two treatments (n = 15/treatment) trickle-dosed with: 1) 1500 infective third stage larvae (L3) three days/week for 6 weeks (27,000 total L3; challenged), or 2) water 3 days/week for 6 weeks (control). Within each pen there were 5 pairs of lambs (balanced for liveweight), with each pair comprising a challenged and control lamb. Blood, faecal, and saliva samples were collected 1 week pre-treatment and weekly for 6 weeks of treatment. Behaviour was observed (e.g., feeding, lying, standing) from video-camera recordings using scan sampling every 5 min for 8 h, 1 day pre-treatment and on the day immediately prior to physiological sampling across the 6-week treatment phase (7 days in total). Accelerometers were attached to each lamb to continuously monitor behaviour from 3 weeks pre-treatment and for the remainder of the study. Liveweight, body condition, faecal soiling and faecal consistency scoring were performed weekly as was lipidomic analysis of plasma samples. From week 2 of treatment, challenged lambs spent less time feeding and more time lying than control lambs until week 5 of treatment (P ≤ 0.01). At week 3 of treatment, elevated lipids (mainly triglycerides and phospholipids), loose faeces and faecal soiling around the anus were observed in challenged lambs compared with controls (P ≤ 0.05). From week 4 of treatment, FEC were elevated in the challenged compared to control lambs (P ≤ 0.05). There was also lower liveweight gain at 4 and 5 weeks of treatment in the challenged lambs compared with control lambs (P ≤ 0.05). These results show a clear timeline of changes in behaviour (e.g., feeding and lying), lipids such as triglycerides, and digestive function (e.g., faecal soiling) suggestive of GIN subclinical disease, which show promise for use in future studies on early identification of subclinical GIN parasitism in lambs.

Breeding Ewe Lambs: An Australasian Perspective.

A number of potential advantages have been identified for breeding ewe lambs at 7 to 9 months of age, including increased lifetime productivity and profitability. However, breeding at this young age in extensive pastoral systems, such as in Australasia, can be associated with a number of disadvantages resulting in uptake of this management procedure being relatively low. This review highlights the known differences between ewe lamb and mature ewe reproductive performance, thus differing in their management. The review then summaries the scientific literature of factors that affect ewe lamb reproductive success, with a focus on recent studies conducted under extensive pasture-based conditions in Australasia. In particular, this review outlines the importance of ewe lamb live weight and body condition score on their productivity. The potential long-term consequences of breeding a ewe lamb at a young age in terms of her future success and that of her offspring to weaning are briefly outlined. In addition, the potential impacts of selecting progeny born to ewe lambs as future replacement ewes are discussed. Throughout this review, optimal management guidelines from prior to breeding the ewe lambs until rebreeding at 2 years of age are provided. Lastly, areas requiring future research are identified and discussed.

Factors Associated with Mortality of Lambs Born to Ewe Hoggets.

The reproductive performance of ewe hoggets is poorer than that of mature-age ewes due to production of fewer lambs with poorer survival. Scant data are available on the risk factors for, and causes of, the mortality for lambs born to ewe hoggets, the impact of ewe deaths on lamb loss, and the causes of death for lambs born to ewe hoggets vs. mature-age ewes lambing in the same circumstances. In this study, 297 lambs born to 1142 ewe hoggets were necropsied along with 273 lambs born to 1050 mature-age ewes. Low lamb birthweight, multiple litter size, and increasing ewe hogget average daily gain from breeding to late pregnancy were risk factors for lamb mortality. The most common cause of mortality for lambs born to ewe hoggets was stillbirth and the risk factors for stillbirth were similar to those for lamb mortality generally. Approximately 11% of ewe hoggets' lamb deaths were due to the death of the dam. Causes of mortality differed between lambs born to ewe hoggets vs. those born to mature-age ewes. Management practices to increase ewe hogget lambs' birthweights (particularly those from multiple litters) and supervision of ewe hoggets at lambing time are recommended.

Predicting ewe body condition score using adjusted liveweight for conceptus and fleece weight, height at withers, and previous body condition score record.

The relationship between ewe body condition score (BCS) and liveweight (LW) has been exploited previously to predict the former from LW, LW-change, and previous BCS records. It was hypothesized that if fleece weight and conceptus-free liveweight and LW-change, and in addition, height at withers were used, the accuracy of current approaches to predicting BCS would be enhanced. Ewes born in 2017 (n = 429) were followed from 8 mo to approximately 42 mo of age in New Zealand. Individual ewe data were collected on LW and BCS at different stages of the annual production cycle (i.e., prebreeding, at pregnancy diagnosis, prelambing, and weaning). Additionally, individual lambing dates, ewe fleece weight, and height at withers data were collected. Linear regression models were fitted to predict current BCS at each ewe age and stage of the annual production cycle using two LW-based models, namely, unadjusted for conceptus weight and fleece weight (LW alone1) and adjusted (LW alone2) models. Furthermore, another two models based on a combination of LW, LW-change, previous BCS, and height at withers (combined models), namely, unadjusted (combined1) and adjusted for conceptus and fleece weight (combined2), were fitted. Combined models gave more accurate (with lower root mean square error: RMSE) BCS predictions than models based on LW records alone. However, applying adjusted models did not improve BCS prediction accuracy (or reduce RMSE) or improve model goodness of fit (R 2) (P > 0.05). Furthermore, in all models, both LW-alone and combined models, a great proportion of variability in BCS, could not be accounted for (0.25 ≥ R 2 ≥ 0.83) and there was substantial prediction error (0.33 BCS ≥ RMSE ≥ 0.49 BCS) across age groups and stages of the annual production cycle and over time (years). Therefore, using additional ewe data which allowed for the correction of LW for fleece and conceptus weight and using height at withers as an additional predictor did not improve model accuracy. In fact, the findings suggest that adjusting LW data for conceptus and fleece weight offer no additional value to the BCS prediction models based on LW. Therefore, additional research to identify alternative methodologies to account for individual animal variability is still needed.

Mammary Gland Structures Are Not Affected by an Increased Growth Rate of Yearling Ewes Post-Weaning but Are Associated with Growth Rates of Singletons.

The experiment aimed to examine the impacts of an increased growth rate of ewes between three and seven months of age on udder development using ultrasound and to establish whether ultrasonography could be used to identify ewe mammary structures that may be indirect indicators of singleton growth to weaning. Udder dimensions, depths of gland cistern (GC), parenchyma (PAR) and fat pad (FP) were measured in late pregnancy (P107), early lactation (L29), and at weaning (L100) in 59 single-bearing yearling ewes selected from two treatments. The 'heavy' group (n = 31) was preferentially fed prior to breeding achieving an average breeding live-weight of 47.9 ± 0.38 kg at seven months of age. The 'control' group (n = 28) had an average breeding live-weight of 44.9 ± 0.49 kg. Udder dimensions, GC, PAR and FP did not differ between treatments. Lamb growth to L100 was positively associated (p < 0.05) with PAR at P107 and GC at L29. There was no evidence of negative effects of the live-weight gain treatments on udder development of yearling ewes as measured by ultrasonography. The results suggest that this ultrasound method has the potential to identify pregnant yearling ewes which would wean heavier singletons.

Associations among Mammary Ultrasound Measurements, Milk Yield of Non-Dairy Ewe Lambs and the Growth of Their Single Lambs.

Mammary cistern size was positively correlated with milk yield of mature dairy ewes, but the association in ewe lambs is unknown. This experiment aimed to examine the associations between mammary ultrasound measurements and the milk yield of ewe lambs at one year of age and to determine the accuracy of using maternal mammary ultrasound to predict single lamb growth rates. Single-bearing ewe lambs (n = 45) were randomly selected and 30 were milked once at weeks three (W3), five (W5), and seven (W7) of lactation. Mammary ultrasound scans were performed at day 110 of pregnancy, W3, W5, W7, and weaning (L69). Single lambs (n = 30) were weighed at birth and at each mammary scanning event. Udder measurements explained 26.8%, 21.4%, and 38.4% of the variation in milk yield at W3, W5 and W7, respectively, and 63.5% and 36.4% of the variation in single lamb growth to W3 and to L69. This ultrasound technique was more accurate in predicting single lamb growth to W3 than milk yield and may enable the identification of pregnant ewe lambs whose progeny would have greater growth rates. More research is needed to identify accurate indicators of superior milk yield and determine whether ultrasound could be used to select ewe lambs.

Effect of Breeding Heavier Romney Ewe Lambs at Seven Months of Age on Lamb Production and Efficiency over Their First Three Breeding Seasons.

This experiment examined the effect of breeding heavier ewe lambs on lamb production and their efficiency over their first three breeding seasons. Two groups of ewe lambs were bred at seven months of age at an average pre-breeding live weight of either 47.9 ± 0.36 kg (heavy; n = 135) or 44.9 ± 0.49 kg (control; n = 135). Ewe live weight, number of lambs born and weaned, and lamb live weight were recorded until 39 months of age, and efficiency was calculated for each ewe. Although the number and lamb weaning weight did not differ between treatments over three years, when data were pooled, heavier ewe lambs at breeding weaned a greater number of lambs over the three-year period. The total lamb weaning weight over the three-year period increased by 2% for each additional kilogram at ewe lamb breeding. Breeding heavier ewe lambs had no effect on efficiency. These results suggest that although breeding heavier ewe lambs had a positive effect on lamb production over the three-year period, it had no effect on efficiency. Before final recommendations can be made, lifetime performance and longevity to five years of age of heavier ewe lambs at breeding are required.