EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial Intelligence and Circadian Thresholds for Stress Detection in Dairy Cattle

Samuel Lascano Rivera iD, Luis Rivera iD, Hernán Benavides iD, Yasmany Fernández iD

Sensors · 2025

DOI: 10.3390/s25216544 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Samuel Lascano Rivera und 3 weiteren Autor:innen. Beteiligte Einrichtung: Research Department, State Polytechnic University of Carchi, Tulcán 040101, Ecuador. Hauptthemen laut MEDLINE: Circadian Rhythm, Artificial Intelligence, Stress, Physiological. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Research Directorate of the State Polytechnic University of Carchi.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates stress detection in dairy cattle by integrating circadian rhythm analysis and deep learning. Behavioral biomarkers, including feeding, resting, and rumination, were continuously monitored using Nedap CowControl sensors over a 12-month period to capture seasonal variability. Circadian features were extracted using the Fast Fourier Transform (FFT), and deviations from expected 24 h patterns were quantified using Euclidean distance. These features were used to train a Long Short-Term Memory (LSTM) neural network to classify stress into three levels: normal, mild, and high. Expert veterinary observations of anomalous behaviors and environmental records were used to validate stress labeling. We continuously monitored 10 lactating Holstein cows for 365 days, yielding 87,600 raw hours and 3650 cow-days (one day per cow as the analytical unit). The Short-Time Fourier Transform (STFT, 36 h window, 1 h step) was used solely to derive daily circadian characteristics (amplitude, phase, coherence); STFT windows are not statistical samples. A 60 min window prior to stress onset was incorporated to anticipate stress conditions triggered by management practices and environmental stressors, such as vaccination, animal handling, and cold stress. The proposed LSTM model achieved an accuracy of 82.3% and an AUC of 0.847, outperforming a benchmark logistic regression model (65% accuracy). This predictive capability, with a one-hour lead time, provides a critical window for preventive interventions and represents a practical tool for precision livestock farming and animal welfare monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Circadian RhythmArtificial IntelligenceStress, PhysiologicalAnimalsCattleFemaleNeural Networks, ComputerDairyingFourier AnalysisDeep LearningMonitoring, Physiologic

Stichwörter der Autor:innen

Fast Fourier TransformLSTMactivity levelbovine stresscircadian rhythmmachine learning

Autor:innen und Institutionen

  • Research Department, State Polytechnic University of Carchi, Tulcán 040101, Ecuador.
  • Postgraduate Program, Faculty of Systems and Informatics Engineering, National University of San Marcos, Lima 15081, Peru.
  • Mathematical Sciences Laboratory, State University of Norte Fluminense, Rio de Janeiro 28013-602, Brazil.

ORCID-Profile: Samuel Lascano Rivera, Luis Rivera, Hernán Benavides, Yasmany Fernández

Förderung

  • the Research Directorate of the State Polytechnic University of Carchi

Zitieren

APA

Rivera, S. L., Rivera, L., Benavides, H., & Fernández, Y. (2025). Artificial Intelligence and Circadian Thresholds for Stress Detection in Dairy Cattle. Sensors. https://doi.org/10.3390/s25216544

Vancouver

Rivera SL, Rivera L, Benavides H, Fernández Y. Artificial Intelligence and Circadian Thresholds for Stress Detection in Dairy Cattle. Sensors. 2025. doi:10.3390/s25216544

BibTeX
@article{Rivera2025,
  author = {Rivera, Samuel Lascano and Rivera, Luis and Benavides, Hernán and Fernández, Yasmany},
  title = {Artificial Intelligence and Circadian Thresholds for Stress Detection in Dairy Cattle},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25216544}
}
Kostenlos starten →