Identifying Sheep Activity from Tri-Axial Acceleration Signals Using a Moving Window Classification Model

Abstract

Behaviour is a useful indicator of an individual animal’s overall wellbeing. There is widespread agreement that measuring and monitoring individual behaviour autonomously can provide valuable opportunities to trigger and refine on-farm management decisions. Conventionally, this has required visual observation of animals across a set time period. Technological advancements, such as animal-borne accelerometers, are offering 24/7 monitoring capability. Accelerometers have been used in research to quantify animal behaviours for a number of years. Now, technology and software developers, and more recently decision support platform providers, are integrating to offer commercial solutions for the extensive livestock industries. For these systems to function commercially, data must be captured, processed and analysed in sync with data acquisition. Practically, this requires a continuous stream of data or a duty cycled data segment and, from an analytics perspective, the application of moving window algorithms to derive the required classification. The aim of this study was to evaluate the application of a ‘clean state’ moving window behaviour state classification algorithm applied to 3, 5 and 10 second duration segments of data (including behaviour transitions), to categorise data emanating from collar, leg and ear mounted accelerometers on five Merino ewes. The model was successful at categorising grazing, standing, walking and lying behaviour classes with varying sensitivity, and no significant difference in model accuracy was observed between the three moving window lengths. The accuracy in identifying behaviour classes was highest for the ear-mounted sensor (86%–95%), followed by the collar-mounted sensor (67%–88%) and leg-mounted sensor (48%–94%). Between-sheep variations in classification accuracy confirm the sensor orientation is an important source of variation in all deployment modes. This research suggests a moving window classifier is capable of segregating continuous accelerometer signals into exclusive behaviour classes and may provide an appropriate data processing framework for commercial deployments.

Effect of De-noising by Wavelet Filtering and Data Augmentation by Borderline SMOTE on the Classification of Imbalanced Datasets of Pig Behavior

“…The problem of imbalanced data is, of course, not unique to the behavior of pigs, but is also seen in the behavior of cows (Homburger et al, 2014), calves (Abell et al, 2017), sheep (Fogarty et al, 2020), and goats (Sakai et al, 2019). Barwick (2020) used an imbalanced dataset directly as the training set to identify sheep activity from triaxial acceleration signals. Their results showed that lying behavior was predicted very poorly from the collar data with a sensitivity of 6%, since limited lying behavior was observed.…”

“…Under-sampling has the drawback that when observations are removed from the majority class, potentially useful information is lost. The drawback of the commonly used simple over-sampling is that a large number of identical samples will be generated, which will cause the model to over-fit to those repeated observations (Barwick, 2020). In the field of livestock science, most researchers who address the problem of imbalanced data sets do so by applying the under-sampling solution (e.g., Smith et al, 2016;Abell et al, 2017;Sakai et al, 2019;Fogarty et al, 2020).…”

“…In the field of livestock science, most researchers who address the problem of imbalanced data sets do so by applying the under-sampling solution (e.g., Smith et al, 2016;Abell et al, 2017;Sakai et al, 2019;Fogarty et al, 2020). Many researchers in this field, however, do not address this issue at all (e.g., Barwick, 2020), which suggests that this is an issue in need of more attention within the animal science community.…”

A Pilot Study Using Accelerometers to Characterise the Licking Behaviour of Penned Cattle at a Mineral Block Supplement

“…Discrete events of individual behaviours were annotated to reflect the mutually exclusive behaviours of licking, eating, standing and lying ( Table 1 ). The software time-stamped the beginning and the end of each event over a particular time regardless the type animals [ 6 , 10 , 31 ]. Each event was processed only if the cattle performed an observed behaviour for a minimum duration of 10 s to avoid multiple events merged in one epoch.…”

“…Wireless technology using animal-borne sensors allows individual animals to be physically monitored in real-time without interfering in their natural behaviour [ 6 , 7 ]. Tri-axial accelerometers have been routinely deployed to automatically record and classify behaviours of domesticated animals based on the acceleration movements over the three perpendicular axes [ 8 , 9 , 10 , 11 ]. Recent investigations have reported that tri-axial accelerometers were capable of categorising oral and intake behaviours of ruminants such as suckling [ 12 ], ruminating, eating [ 13 ], grazing [ 14 ], chewing, biting [ 11 ], and drinking [ 15 ].…”