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.

Gastrointestinal nematode infection affects overall activity in young sheep monitored with tri-axial accelerometers.

Animals suffering from parasitism typically display altered grazing behaviour and a voluntary reduction in feed intake. These changes are potentially important as indicators of disease. Recent advances in sensor technologies provide the opportunity to objectively measure animal activity while on pasture. Tri-axial accelerometers measure body movement in terms of acceleration, which can then be used to estimate physical activity over time. This study investigated if tri-axial measures of overall activity can be used to assess the impact of gastrointestinal nematode (GIN) infection in young sheep. To address this, the overall activity, faecal nematode egg count (FEC) and body weight of two treatment groups of Romney X Suffolk ram lambs were compared. Animals were monitored for four days using tri-axial accelerometer sensors mounted on a ram mating harness after 42-days grazing on contaminated pasture. On Day 0, all lambs were given anthelmintics. Subsequently, a Suppressive Treatment Group (n = 12) was treated with anthelmintics every two weeks. An Untreated Group (n = 12) did not receive further anthelmintics. Overall activity levels were monitored from Day 42 - 46. Activity level was calculated as vectorial dynamic body acceleration (VeDBA). Anthelmintic treatment had a significant effect on FEC but there was no evidence found for a treatment effect on body weight growth over the 42-day period. An effect of treatment and lamb starting weight on overall activity was found (beta = -0.74, 95 % CI -1.17 to -0.30, p =  0.002), identifying a negative impact of parasitism on activity in heavier animals. These results highlight the usefulness of this approach in assessing the effect of GIN parasitism on sheep monitored remotely. If a threshold value of activity could be determined, it could provide a useful tool for farmers and managers that serves as an early indicator of parasitism in sheep.

Abnormal pre-operative tests, pathologic findings of medical history, and their predictive value for perioperative complications.

BACKGROUND: Laboratory tests, electrocardiogram (ECG) and chest X-rays still serve as part of the routine assessment before elective surgery in many institutions, even though there is little evidence of their predictive value relating to perioperative complications. This study investigates the correlation of abnormal findings in pre-operative tests and pathologic findings in the medical history with perioperative complications. METHODS: Patients scheduled for elective surgery in a secondary care hospital were included in this prospective cohort study. Abnormal pre-operative tests, significant findings from the medical history and perioperative complications were recorded. Regression analysis was performed in order to identify the strongest predictors for perioperative complications. RESULTS: A total of 1363 (56.1% female) patients were consecutively included in this study. The percentage of abnormalities in pre-operative tests ranged from 1.6% (electrolytes) and 29.7% (echocardiography). Eighty-six (6.3%) patients had at least one perioperative complication. The most frequent complications were hypo- or hypertension in 55 cases (4.0%), followed by 20 patients (1.5%) who suffered from hemodynamically relevant cardiac dysrhythmias such as supraventricular tachycardia, ventricular tachycardia, bradycardia and ventricular extrasystoles. The binary logistic regression analysis to identify predictors of perioperative complications showed significant results for age, invasiveness of the procedure, history of renal disease or anemia and abnormal ECG. CONCLUSION: Our results indicate that age, type of surgery and medical history are appropriate predictors of perioperative complications, whereas abnormalities in laboratory tests seem to have restricted ability in predicting adverse perioperative outcome.