SpaceSheep: Satellite Communications for Ovine Smart Grazing

Gonçalves, Pedro; Corujo, Daniel

doi:10.3390/vetsci10050340

Cited by 1 publication

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With this effect, the fluctuation of the context on A, distance, and the pitch and roll angles of each collar was carefully examined. The goal was to verify if it is possible to identify To take advantage of the sensing platform [63], the instantiation of the edge solution was performed in a previously developed gateway [65] used in a data-gathering trial [38], and it was implemented by a Raspberry PI 3 Model B Plus Rev 1.3. The integration of the edge equipment with the cloud component was carried out using a message broker that communicates via Message Queuing Telemetry Transport (MQTT) [66].…”

Section: Edge-located Drift Detectormentioning

confidence: 99%

“…The data structure includes a timestamp, accelerometer (D x , D y , and D z ) data, pitch and roll angles, the distance between the collar and the ground as measured by ultrasound, and behavior classification as performed by the collar (i.e., standing, eating, moving, running). The data were periodically sampled at intervals of 10 s and reported from the collars to a central gateway that stored the data [65]. In order to study animal activity using collar sensors, activity indicators (A) based on accelerometer intensity, also known as Dynamic Body Acceleration [67], were defined, and accordingly to [67], the Vectorial sum of Dynamic Body Acceleration (VeDBAtwo), which is best suited for animal movement analysis, was used and defined as shown in Equation (1).…”

Section: The Flock and Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Exploring the Potential of Machine Learning Algorithms Associated with the Use of Inertial Sensors for Goat Kidding Detection

Gonçalves,

Marques,

Belo

et al. 2024

Animals

View full text Add to dashboard Cite

The autonomous identification of animal births has a significant added value, since it enables for a prompt timely human intervention in the process, protecting the young and the mothers’ health, without requiring continuous human surveillance. Wearable inertial sensors have been employed for a variety of animal monitoring applications, thanks to their low cost and the fact that they allow less invasive monitoring process. Alarms triggered by the occurrence of events must be generated close to the events to avoid delays caused by communication latency, which is why this type of mechanism is typically implemented at the network’s edge and integrated with existing auxiliary mechanisms on the Internet. Although the detection of births in cattle has been carried out commercially for some years, there is no solution for small ruminants, especially goats, where the literature does not even report any attempts. The current work consisted of a first attempt at developing an automatic birth monitor using inertial sensing, as well as detection techniques based on Machine Learning, implemented in a network edge device to assure real-time alarm triggering. Thus, two concept drift detection techniques and seven kidding detection mechanisms were developed using data classification models. The work also includes the testing and comparison of learning results, both in terms of accuracy and of computational costs of the detection module, for algorithms implemented. The results revealed that, despite their simplicity, concept drift algorithms do not allow kidding detection, whereas classification-algorithm-based static learning models do, despite the unbalanced character of the dataset and its reduced size. The learning findings are quite promising in terms of computational cost and its suitability for deployment on edge devices. The algorithm demonstrates behavior changes four hours before kidding and allows for the identification of the kidding hour with an accuracy of 61%, as well as the capacity to improve the overall learning process with a larger dataset.

show abstract

Section: Edge-located Drift Detectormentioning

confidence: 99%