EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bee Together: Joining Bee Audio Datasets for Hive Extrapolation in AI-Based Monitoring

Augustin Bricout iD, Philippe Leleux iD, Pascal Acco iD, Christophe Escriba iD, Jean-Yves Fourniols, Georges Soto-Romero iD, Rémi Floquet

Sensors · 19.09.2024 · 24 (18) · 6067

DOI: 10.3390/s24186067 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.09.2024. Verfasst von Augustin Bricout und 6 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory for Analysis and Architecture of Systems (LAAS-CNRS), University of Toulouse, 31077 Toulouse, France. Hauptthemen laut MEDLINE: Artificial Intelligence. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: RF Innovation CIFRE grant, RF Innovation (Toulouse, France).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Beehive health monitoring has gained interest in the study of bees in biology, ecology, and agriculture. As audio sensors are less intrusive, a number of audio datasets (mainly labeled with the presence of a queen in the hive) have appeared in the literature, and interest in their classification has been raised. All studies have exhibited good accuracy, and a few have questioned and revealed that classification cannot be generalized to unseen hives. To increase the number of known hives, a review of open datasets is described, and a merger in the form of the “BeeTogether” dataset on the open Kaggle platform is proposed. This common framework standardizes the data format and features while providing data augmentation techniques and a methodology for measuring hives’ extrapolation properties. A classical classifier is proposed to benchmark the whole dataset, achieving the same good accuracy and poor hive generalization as those found in the literature. Insight into the role of the frequency of the classification of the presence of a queen is provided, and it is shown that this frequency mostly depends on a colony’s belonging. New classifiers inspired by contrastive learning are introduced to circumvent the effect of colony belonging and obtain both good accuracy and hive extrapolation abilities when learning changes in labels. A process for obtaining absolute labels was prototyped on an unsupervised dataset. Solving hive extrapolation with a common open platform and contrastive approach can result in effective applications in agriculture.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceBeesAnimalsAlgorithms

Stichwörter der Autor:innen

bee acousticsbeehive monitoringclassificationcontrastive learninggeneralizationmachine learningqueen presence detection

Autor:innen und Institutionen

  • Laboratory for Analysis and Architecture of Systems (LAAS-CNRS), University of Toulouse, 31077 Toulouse, France.
  • RF Innovation, 20 Avenue Didier Daurat, 31400 Toulouse, France.

ORCID-Profile: Augustin Bricout, Philippe Leleux, Pascal Acco, Christophe Escriba, Georges Soto-Romero

Förderung

  • RF Innovation CIFRE grant
  • RF Innovation (Toulouse, France)

Zitieren

APA

Bricout, A., Leleux, P., Acco, P., Escriba, C., Fourniols, J. Y., Soto-Romero, G., & Floquet, R. (2024). Bee Together: Joining Bee Audio Datasets for Hive Extrapolation in AI-Based Monitoring. Sensors, 24(18), 6067. https://doi.org/10.3390/s24186067

Vancouver

Bricout A, Leleux P, Acco P, Escriba C, Fourniols JY, Soto-Romero G, et al. Bee Together: Joining Bee Audio Datasets for Hive Extrapolation in AI-Based Monitoring. Sensors. 2024;24(18):6067. doi:10.3390/s24186067

BibTeX
@article{Bricout2024,
  author = {Bricout, Augustin and Leleux, Philippe and Acco, Pascal and Escriba, Christophe and Fourniols, Jean-Yves and Soto-Romero, Georges and Floquet, Rémi},
  title = {Bee Together: Joining Bee Audio Datasets for Hive Extrapolation in AI-Based Monitoring},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {18},
  pages = {6067},
  doi = {10.3390/s24186067}
}
Kostenlos starten →