Application of a Lightweight, Open-Hardware Wearable System for Robust Behaviour Monitoring in Precision Livestock Farming

Precision livestock farming (PLF) is hindered by high costs, infrastructure demands, and complex deployment. To address these barriers, we developed CABRA, an open-hardware wearable system for real-time behaviour monitoring in pasture-based livestock. The collar-mounted device integrates a 6-axis IMU, a GPS, and a low-power ESP32 microcontroller within a modular architecture, using the routerless ESP-NOW protocol to transmit data directly to a base station—eliminating reliance on network infrastructure or cloud connectivity. The system supports both synchronised data logging for video annotation and real-time embedded behaviour classification via an optimized decision-tree pipeline deployed directly on the microcontroller. Field trials with dairy goats confirmed robust hardware performance, minimal animal disturbance, and reliable communication over 100 m. A two-stage evaluation revealed that while the extracted IMU features are highly discriminative (achieving F1 > 0.99 under window-level validation), cross-animal generalization remains challenging (macro F1 = 0.31 under rigorous animal-level partitioning), primarily due to the “sensor placement effect” and domain shift between individuals. These results honestly quantify the current limitations of uncalibrated wearable livestock sensing while validating the functional feasibility of edge-based inference. All design assets—CAD files, schematics, firmware, and data pipelines—are openly released to ensure full reproducibility and community-driven adaptation for diverse PLF applications.