Power Up: Combining Behavior Monitoring Software with Business Intelligence Tools to Enhance Proactive Animal Welfare Reporting

Cinereous Vulture (Aegypius monachus) Welfare Monitoring in a Breeding Center during the Breeding Season

One of the conservation measures of the globally near-threatened cinereous vulture is restoring populations via translocations, with some vultures originating from breeding centers. These centers need to have reproductive success, and securing good welfare levels should be a priority due to the negative implications a compromised welfare has on reproduction. Thus, assessing welfare in breeding centers is essential. Remote methods should be preferred, such as behavior analysis and use of space using camera systems. The study's first objective was to develop an activity budget that could be used as a baseline for detecting behavior irregularities. The second was to determine if behavior analysis and use of space could detect potential welfare issues in a breeding center. The study developed an activity budget that could be used as a standard for behavior analysis for the captive population. Behavior irregularities were detected, and the potential need to improve the enclosure and its surroundings were noticed. Altogether, the proposed methodology and results will contribute to the detection of possible welfare issues in breeding centers and, consequently, improve reproductive success and species' conservation.

A novel protocol for three-dimensional mapping of sand tiger shark (Carcharias taurus) enclosure use in aquaria: Implications for management

This study investigated sand tiger shark (STS; Carcharias taurus) spatial use and exclusion in public aquarium enclosures using a novel protocol for three-dimensional mapping. Fifty-one STS were observed in 14 enclosures, and swimming pattern, depth, and location were recorded in ZooMonitor. Data were converted into quantitative, three-dimensional representations using ArcGIS® Pro v. 2.9. All observed STS except one swam in circular patterns, and 80% (n = 41) showed a directional swimming bias. Most STS (80%; n = 41) predominantly utilized the top two-thirds of the enclosures, though 83% (n = 34) of those had swimming obstructions in the bottom of the enclosure. Avoidance of obstructed areas, sections <7 m wide, as well as behavioral spatial separation, resulted in utilization of between 27% and 66% of available enclosure space. STS underutilized corners, pinch-points, and obstructed areas requiring abrupt directional changes and instead exhibited continual, unimpeded swimming patterns. In addition, this study found no relationship between directional swimming bias or use of smaller enclosure volumes and spinal deformity, a health issue affecting 26% of STS 10 years ago but now with an incidence of 6%. Using novel protocols for three-dimensional mapping and volume estimation, this study demonstrated that enclosures facilitating unimpeded, continuous swimming are most usable for STS and provides important information that will be useful for future enclosure design.

Cloud Data-Driven Intelligent Monitoring System for Interactive Smart Farming

Smart farms, as a part of high-tech agriculture, collect a huge amount of data from IoT devices about the conditions of animals, plants, and the environment. These data are most often stored locally and are not used in intelligent monitoring systems to provide opportunities for extracting meaningful knowledge for the farmers. This often leads to a sense of missed transparency, fairness, and accountability, and a lack of motivation for the majority of farmers to invest in sensor-based intelligent systems to support and improve the technological development of their farm and the decision-making process. In this paper, a data-driven intelligent monitoring system in a cloud environment is proposed. The designed architecture enables a comprehensive solution for interaction between data extraction from IoT devices, preprocessing, storage, feature engineering, modelling, and visualization. Streaming data from IoT devices to interactive live reports along with built machine learning (ML) models are included. As a result of the proposed intelligent monitoring system, the collected data and ML modelling outcomes are visualized using a powerful dynamic dashboard. The dashboard allows users to monitor various parameters across the farm and provides an accessible way to view trends, deviations, and patterns in the data. ML models are trained on the collected data and are updated periodically. The data-driven visualization enables farmers to examine, organize, and represent collected farm's data with the goal of better serving their needs. Performance and durability tests of the system are provided. The proposed solution is a technological bridge with which farmers can easily, affordably, and understandably monitor and track the progress of their farms with easy integration into an existing IoT system.