2026/07/10 by A. Matthews, Lindsay R. Matthews, Bart R. H. Geurten · 1 voice
Environmental Science · Veterinary · Psychology · #Wildlife Ecology and Conservation #Animal Behavior and Welfare Studies #Primate Behavior and Ecology
paper · doi:10.1016/j.compag.2026.112122
openalex publication_date 2026/07/10 · openalex created_date 2026/07/11 · openalex updated_date 2026/07/11
Monitoring deer behaviour continuously and objectively is essential for accurate welfare assessment in pastoral farming, yet conventional observation methods are labour-intensive and prone to subjective bias. We present an unsupervised machine-learning pipeline for classifying farmed red deer ( Cervus elaphus ) behaviour from wearable accelerometer data. Tri-axial accelerometers mounted on the head and ear of stags recorded movement at 50 Hz over 48 h. k -means clustering of the normalised signals yielded eight prototypical movements spanning three behavioural categories: inactive states (lying, resting with or without rumination/panting), grazing (stationary and walking), and rapid ear flicks. A first-order Markov chain then linked these prototypes into higher-order sequences we call ”super-prototypes”. These compound behaviours included ear-flick bouts and alternating grazing-stepping cycles. Within the single 24-h window, activity varied with time of day, ear flicks being markedly more frequent by day. Against independent video annotation, the eight categories agreed with the observer’s labelling at a mean of 0.96 across prototypes. Because classification reduces to a nearest-centroid operation, the algorithm runs on a 16 MHz microcontroller at over 4 × 1 0 8 classifications per second, four orders of magnitude faster than the sensor sampling rate. The pipeline requires no hand-labelled training data and runs in real time on the animal, a feasible basis for welfare monitoring in extensive deer farming systems once validated under field conditions.