Cattle behavior recognition from accelerometer data: Leveraging in-situ cross-device model learning
Computers and Electronics in Agriculture · 2024-12 · 227 · 109546
DOI: 10.1016/j.compag.2024.109546 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers and Electronics in Agriculture, 2024-12. Verfasst von Reza Arablouei und 3 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Automating livestock behavior recognition using wearable sensors offers significant benefits for monitoring animal health, ensuring welfare, and enhancing farm productivity. While collar-mounted accelerometers provide useful data leading to accurate behavior recognition models, ear-tags offer greater practicality and scalability. However, ear-tag data is affected by independent ear movements (e.g., for flicking flies), necessitating extensive labeled data for accurate recognition, which is time-consuming and costly to obtain. To address this challenge, we propose a pioneering cross-device learning approach. By leveraging a pre-trained behavior recognition model from collar data to guide ear-tag model training, we significantly reduce the need for manual labeling of ear-tag data. This facilitates the development of efficient and scalable behavior recognition models suitable for wider deployment. Additionally, we introduce a novel deep neural network architecture that integrates linearly-constrained convolutional layers specifically designed to counteract gravity’s impact on accelerometer data, along with a confidence penalty term to combat overfitting when training on limited labeled data. Evaluation on real-world cattle data demonstrates that our approach yields ear-tag model performance nearly on par with collar models. This breakthrough paves the way for personalized behavior recognition models using ear-tags, requiring only brief periods of collar-based labeling per animal. • Collar accelerometers give accurate behavior models but ear-tags are more practical. • Ear-tag data needs extensive and costly labeling due to independent ear movements. • Cross-device learning reduces manual labeling by leveraging collar model predictions. • New model architecture uses constrained convolutions to counter effects of gravity. • Proposed approach yields ear-tag model performance nearly matching collar model.
Zitieren
APA
Arablouei, R., Bishop-Hurley, G. J., Bagnall, N., & Ingham, A. (2024). Cattle behavior recognition from accelerometer data: Leveraging in-situ cross-device model learning. Computers and Electronics in Agriculture, 227, 109546. https://doi.org/10.1016/j.compag.2024.109546
Vancouver
Arablouei R, Bishop-Hurley GJ, Bagnall N, Ingham A. Cattle behavior recognition from accelerometer data: Leveraging in-situ cross-device model learning. Computers and Electronics in Agriculture. 2024;227:109546. doi:10.1016/j.compag.2024.109546
BibTeX
@article{Arablouei2024,
author = {Arablouei, Reza and Bishop-Hurley, Greg J. and Bagnall, Neil and Ingham, Aaron},
title = {Cattle behavior recognition from accelerometer data: Leveraging in-situ cross-device model learning},
journal = {Computers and Electronics in Agriculture},
year = {2024},
volume = {227},
pages = {109546},
doi = {10.1016/j.compag.2024.109546}
}
EUVIMED