IoT-enabled individual poultry monitoring with lightweight step-counting for health assessment
Year: 2026
Type: article
Abstract: To address the challenges of quantifying individual physical activity, delayed detection of health anomalies in high-density environments, and the lack of objective data supporting welfare-oriented farming in large-scale floor-rearing poultry farms, this paper proposes and implements an Internet of Things-based system for individual poultry behavior monitoring and digital management. The system consists of three core components: an energy-efficient smart anklet, a solar-powered multi-modal communication base station, and a cloud management platform. At the edge node, the smart anklet utilizes a CH582M microcontroller and an ADXL362 three-axis accelerometer to achieve precise acquisition of poultry gait signals. The base station integrates Bluetooth Low Energy and an ML307A LTE Cat.1 cellular module, featuring a custom SL3795-based solar power management circuit to overcome the challenges of device power supply and data relay transmission in expansive rearing facilities. Algorithmically, a lightweight step-counting algorithm based on the signal amplitude features and an adaptive dynamic threshold is proposed to minimize computation overhead. Furthermore, integrated with cloud-based time-series logic, multi-dimensional strategies are developed for daily activity evaluation, abnormal resting early warning, and out-of-bounds anti-loss alarming. Field tests indicate that the proposed algorithm achieves a high average step-counting accuracy of 97.19% under complex activity states, and the multi-dimensional state warning model reaches an overall accuracy of 96.33%. This solution provides objective and reliable data support for the digital logging of high-quality poultry behaviors and the advancement of animal-centric precision livestock farming.
Source: Scientific Reports
Authors: Xinran Sun, Wenyi Zeng, Bingqi Shi, Xiao Liang
Institution: Minzu University of China
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
Open Access status: gold
Estimated APC paid: $2,690
OpenAlex ID: W7223381610