EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Pedro Gonçalves iD, Maria do Rosário Marques iD, Ana Teresa Belo iD, António Monteiro iD, João Morais, Ivo Riegel iD, Fernando Braz iD

Animals · 19.03.2024 · 14 (6) · 938

DOI: 10.3390/ani14060938 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 19.03.2024. Verfasst von Pedro Gonçalves und 6 weiteren Autor:innen. Beteiligte Einrichtung: Instituto de Telecomunicações, Escola Superior de Tecnologia e Gestão de Águeda, Universidade de Aveiro, 3830-193 Aveiro, Portugal. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FCT/MCTES.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

concept driftedge computinggoat kidding detectioninertial sensorsprecision livestock farmingstream learning

Autor:innen und Institutionen

  • Instituto de Telecomunicações, Escola Superior de Tecnologia e Gestão de Águeda, Universidade de Aveiro, 3830-193 Aveiro, Portugal.
  • Instituto Nacional de Investigação Agrária e Veterinária I.P. (INIAV), Avenida Professor Vaz Portugal, 2005-424 Vale de Santarém, Portugal.
  • Escola Superior Agrária do Instituto Politécnico de Viseu e CERNAS, Centro de Recursos Naturais, Ambiente e Sociedade, Quinta da Alagoa, Estrada de Nelas, 3500-606 Viseu, Portugal.
  • Instituto de Telecomunicações, Departamento de Eletrónica Telecomunicações e Informática, Universidade de Aveiro, 3830-193 Aveiro, Portugal.
  • Instituto Federal Catarinense, Campus Araquari, Araquari 89245-000, Brazil.

ORCID-Profile: Pedro Gonçalves, Maria do Rosário Marques, Ana Teresa Belo, António Monteiro, Ivo Riegel, Fernando Braz

Förderung

  • FCT/MCTES

Zitieren

APA

Gonçalves, P., Marques, M. D. R., Belo, A. T., Monteiro, A., Morais, J., Riegel, I., & Braz, F. (2024). Exploring the Potential of Machine Learning Algorithms Associated with the Use of Inertial Sensors for Goat Kidding Detection. Animals, 14(6), 938. https://doi.org/10.3390/ani14060938

Vancouver

Gonçalves P, Marques MDR, Belo AT, Monteiro A, Morais J, Riegel I, et al. Exploring the Potential of Machine Learning Algorithms Associated with the Use of Inertial Sensors for Goat Kidding Detection. Animals. 2024;14(6):938. doi:10.3390/ani14060938

BibTeX
@article{Gonalves2024,
  author = {Gonçalves, Pedro and Marques, Maria do Rosário and Belo, Ana Teresa and Monteiro, António and Morais, João and Riegel, Ivo and Braz, Fernando},
  title = {Exploring the Potential of Machine Learning Algorithms Associated with the Use of Inertial Sensors for Goat Kidding Detection},
  journal = {Animals},
  year = {2024},
  volume = {14},
  number = {6},
  pages = {938},
  doi = {10.3390/ani14060938}
}
Kostenlos starten →