EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Based Prediction of Cattle Activity Using Sensor-Based Data

Guillermo Hernández iD, Carlos González-Sánchez iD, Angélica González-Arrieta iD, Guillermo Sánchez-Brizuela iD, Juan-Carlos Fraile iD

Sensors · 2024

DOI: 10.3390/s24103157 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Guillermo Hernández und 4 weiteren Autor:innen. Beteiligte Einrichtung: Grupo de Investigación BISITE, Universidad de Salamanca, 37008 Salamanca, Spain. Hauptthemen laut MEDLINE: Machine Learning, Algorithms. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Centro para el Desarrollo Tecnológico y la Innovación, Centre for the Development of Industrial Technology (CDTI), Spanish companies APLIFISA and COPASA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Livestock monitoring is a task traditionally carried out through direct observation by experienced caretakers. By analyzing its behavior, it is possible to predict to a certain degree events that require human action, such as calving. However, this continuous monitoring is in many cases not feasible. In this work, we propose, develop and evaluate the accuracy of intelligent algorithms that operate on data obtained by low-cost sensors to determine the state of the animal in the terms used by the caregivers (grazing, ruminating, walking, etc.). The best results have been obtained using aggregations and averages of the time series with support vector classifiers and tree-based ensembles, reaching accuracies of 57% for the general behavior problem (4 classes) and 85% for the standing behavior problem (2 classes). This is a preliminary step to the realization of event-specific predictions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningAlgorithmsAnimalsCattleBehavior, AnimalSupport Vector MachineHumansMonitoring, Physiologic

Stichwörter der Autor:innen

cowextensive livestockmachine learningmonitoringsensorized wearable device

Autor:innen und Institutionen

  • Grupo de Investigación BISITE, Universidad de Salamanca, 37008 Salamanca, Spain.
  • ITAP (Instituto de las Tecnologías Avanzadas de la Producción), Universidad de Valladolid, 47011 Valladolid, Spain.

ORCID-Profile: Guillermo Hernández, Carlos González-Sánchez, Angélica González-Arrieta, Guillermo Sánchez-Brizuela, Juan-Carlos Fraile

Förderung

  • Centro para el Desarrollo Tecnológico y la Innovación
  • Centre for the Development of Industrial Technology (CDTI)
  • Spanish companies APLIFISA and COPASA
  • Junta de Castilla y León
  • European Regional Development Fund

Zitieren

APA

Hernández, G., González-Sánchez, C., González-Arrieta, A., Sánchez-Brizuela, G., & Fraile, J. C. (2024). Machine Learning-Based Prediction of Cattle Activity Using Sensor-Based Data. Sensors. https://doi.org/10.3390/s24103157

Vancouver

Hernández G, González-Sánchez C, González-Arrieta A, Sánchez-Brizuela G, Fraile JC. Machine Learning-Based Prediction of Cattle Activity Using Sensor-Based Data. Sensors. 2024. doi:10.3390/s24103157

BibTeX
@article{Hernndez2024,
  author = {Hernández, Guillermo and González-Sánchez, Carlos and González-Arrieta, Angélica and Sánchez-Brizuela, Guillermo and Fraile, Juan-Carlos},
  title = {Machine Learning-Based Prediction of Cattle Activity Using Sensor-Based Data},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24103157}
}
Kostenlos starten →