Devices for assessing the quality of animal environments are important for maintaining production animals, thus improving animal well-being and mitigating pollutant emissions. Therefore, an IoT system was developed and preliminarily assessed across various livestock housing types, including those for pigs, dairy cows, and rabbits. This system measures and transmits key parameters, such as ambient temperature; relative humidity; light intensity; sound pressure; levels of carbon dioxide, ammonia, and hydrogen sulfide; and particulate matter and volatile organic compound concentrations. These data are sent from the sensors to a gateway and then displayed on a dashboard for monitoring. A preliminary evaluation of the system’s performance in controlled conditions revealed that the device’s accuracy and precision were within 2.7% and 3.3% of the measured values, respectively. The system was deployed in three case studies involving rabbit, pig, and dairy cow farms. The results demonstrated its effectiveness in assessing pollutant emissions and identifying critical situations where gas concentrations exceeded threshold levels, thus posing a risk to the animals. By systematically applying this technology on livestock farms to obtain a detailed understanding of the microclimatic and air quality conditions in which the animals live, animal welfare can be significantly improved.
Monitoring dairy cattle behavior can improve the detection of health and welfare issues for early interventions. Often commercial sensors do not provide researchers with sufficient raw and open data; therefore, the aim of this study was to develop an open and customizable system to classify cattle behaviors. A 3D accelerometer device and host-board (i.e., sensor node) were embedded in a case and fixed on a dairy cow collar. It was developed to work in two modes: (1) acquisition mode, where a mobile application supported the raw data collection during observations; and (2) operating mode, where data was processed and sent to a gateway and on the cloud. Accelerations were sampled at 25 Hz and behaviors were classified in 10-min windows. Several algorithms were trained with the 108 h of behavioral data acquired from 32 cows on 3 farms, and after evaluating their computational/memory complexity and accuracy, the Decision Tree algorithm was selected. This model detected standing, lying, eating, and ruminating with an average accuracy of 85.12%. The open nature of this system enables for the addition of other functions (e.g., real-time localization of cows) and the integration with other information sources, e.g., microenvironment and air quality sensors, thereby enhancing data processing potential.
The pursuit of technological sovereignty is a central pillar of the European industrial strategy, driving the critical need for open-source, high-performance computing solutions that reduce reliance on proprietary intellectual property. Supported by the Chips Joint Undertaking within Horizon Europe, the TRISTAN and ISOLDE projects are at the forefront of this mission, synergizing to expand, mature, and industrialize the European RISC-V ecosystem. While TRISTAN aims to strengthen the foundational RISC-V open-source community by focusing on SoC HW and SW building blocks and a comprehensive end-to-end EDA infrastructure, ISOLDE extends this ecosystem across the entire software stack, targeting high-performance, security and safety aspects for key domains such as automotive, aerospace, and IoT. Together, these projects emphasize seamless interoperability and collaboration, sharing a unified virtual repository for IP distribution. This paper details the extensive collaborative developments of the consortium partners, highlighting their specific contributions to high-performance RISC-V architectures.
This study presents a case study of a novel early-warning system for detecting enteric dysbiosis in broiler chickens using Volatile Organic Compounds (VOCs) analysis. The system integrates metal oxide semiconductor (MOS) sensors with PCA-KNN algorithms and was validated in some commercial broiler houses in Northern Italy. The technology identifies metabolic changes associated with enteric diseases, like coccidiosis, by analysing the air within poultry sheds and issuing alerts up to four days before clinical symptoms appear. The prediction was validated using oocyst counts as diagnostic gold standard. Early alerts enabled timely intervention with organic acids rather than antibiotics, reducing mortality, improving feed conversion, and maintaining antibiotic-free certification. The VOC monitoring system is part of a Precision Livestock Farming (PLF) approach and operates in real time, with data processed hourly through a cloud-based platform. Features extracted from VOC signals are normalized and analyzed via PCA, followed by classification using a KNN model and low pass filtered to eliminate spurious alerts and consequently minimize false positives. Results demonstrated over 80% accuracy in early detection. The technology aligns with EU efforts to reduce antimicrobial use in livestock and offers significant economic benefits. Organic acid treatments cost ~ €88 per treatment compared with €180 for antibiotics and preserving antibiotic-free status avoids profit losses of up to 20%. Limitations of the study include reliance on oocyst count alone, and need for IoT connection. Nonetheless, this approach represents a scalable and sustainable alternative to antibiotics in broiler production systems.