Quantifying Sheep Behaviour Using a 3D Accelerometer: A Proof-of-Concept for Objective Stress Assessment

TL;DR

A 3D accelerometer system was developed to detect sheep behavior, showing that changes in rumination and resting/idling can indicate stress when animals are moved to unfamiliar environments.

Contribution

A novel miniaturized 3D accelerometer system with a microcontroller for automated sheep behavior detection and stress assessment was developed and validated.

Findings

The system achieved high accuracy in detecting rumination (0.87), resting/idling (0.90), and eating (0.86) behaviors.

Relocation caused a significant decrease in rumination and increase in resting/idling, suggesting these behaviors can indicate stress.

Deviations from baseline behavior durations may serve as ethological parameters for automated stress alerts in sheep.

Abstract

What are the main findings?
A novel, miniaturised three-dimensional accelerometer system incorporating a nRF52832 microcontroller was developed with a primary focus on rumination detection. In addition to this core function, the system enables classification of resting/idling behaviour and shows potential for detecting eating behaviour following further technical refinement.The duration of rumination and resting/idling changed significantly when sheep were separated from their familiar group and relocated to an unfamiliar environment in pairs, which was defined as a “potential stressor.”

A novel, miniaturised three-dimensional accelerometer system incorporating a nRF52832 microcontroller was developed with a primary focus on rumination detection. In addition to this core function, the system enables classification of resting/idling behaviour and shows potential for detecting eating behaviour following further technical refinement.

The duration of rumination and resting/idling changed significantly when sheep were separated from their familiar group and relocated to an unfamiliar environment in pairs, which was defined as a “potential stressor.”

What are the implications of the main findings?
Deviations in rumination and resting/idling from individual baseline behaviour may be suitable for triggering automated alerts, as such deviations may indicate stress-related responses. However, validation in larger cohorts of sheep is required to confirm this applicability.Automatic behaviour detection represents a promising approach for early stress identification and reliable welfare assessment in both laboratory animal and livestock settings.

Deviations in rumination and resting/idling from individual baseline behaviour may be suitable for triggering automated alerts, as such deviations may indicate stress-related responses. However, validation in larger cohorts of sheep is required to confirm this applicability.

Automatic behaviour detection represents a promising approach for early stress identification and reliable welfare assessment in both laboratory animal and livestock settings.

Continuous digital monitoring of sheep behaviour shows potential for early stress detection. In Part 1 of this study, a novel accelerometer-based behaviour-recognition system using a nRF52832 microcontroller with Bluetooth wireless data transfer was developed and validated. A dedicated algorithm was developed to focus on the automatic detection of rumination, which also enables the classification of resting/idling and eating. The system achieved accuracies of 0.87 (rumination), 0.90 (resting/idling), and 0.86 (eating). Specificities were 0.87, 0.95, and 0.94; sensitivities 0.89, 0.80, and 0.60; and precisions 0.79, 0.88, and 0.73, respectively. In Part 2, four sheep were continuously monitored for 24 h to establish baseline behavioural durations. Animals were then relocated in pairs to an unfamiliar enclosure for a further 24 h observation period. Relocation resulted in a significant reduction in rumination time (−45.6%, p < 0.05) and a significant increase in resting/idling (+47.9%, p < 0.05), while time spent eating decreased but did not reach statistical significance (−36.2%). These findings indicate that detecting deviations from baseline rumination and resting/idling durations may serve as suitable ethological parameters for automated, sensor-based stress alerts. With further technical refinement and validation, the developed system shows strong potential as a reliable, non-invasive tool for monitoring key sheep stress indicators.

Figures