EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spectral Components of Honey Bee Sound Signals Recorded Inside and Outside the Beehive: An Explainable Machine Learning Approach to Diurnal Pattern Recognition

Piotr Książek iD, Urszula Libal iD, Aleksandra Król-Nowak iD

Sensors · 16.07.2025 · 25 (14) · 4424

DOI: 10.3390/s25144424 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 16.07.2025. Verfasst von Piotr Książek und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Acoustics, Multimedia and Signal Processing, Wroclaw University of Science and Technology, 50-370 Wroclaw, Poland. Hauptthemen laut MEDLINE: Machine Learning, Circadian Rhythm, Sound, Pattern Recognition, Automated. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates the impact of microphone placement on honey bee audio monitoring for time-of-day classification, a key step toward automated activity monitoring and anomaly detection. Recognizing the time-dependent nature of bee behavior, we aimed to establish a baseline diurnal pattern recognition method. A custom apparatus enabled simultaneous audio acquisition from internal (brood frame, protected from propolization) and external hive locations. Sound signals were preprocessed using Power Spectral Density (PSD). Extra Trees and Convolutional Neural Network (CNN) classifiers were trained to identify diurnal activity patterns. Analysis focused on feature importance, particularly spectral characteristics. Interestingly, Extra Trees performance varied significantly. While achieving near-perfect accuracy (98–99%) with internal recordings, its accuracy was considerably lower (61–72%) with external recordings, even lower than CNNs trained on the same data (76–87%). Further investigation using Extra Trees and feature selection methods using Mean Decrease Impurity (MDI) and Recursive Feature Elimination with Cross-Validation (RFECV) revealed the importance of the 100–600 Hz band, with peaks around 100 Hz and 300 Hz. These findings inform future monitoring setups, suggesting potential for reduced sampling frequencies and underlining the need for monitoring of sound inside the beehive in order to validate methods being tested.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningCircadian RhythmSoundPattern Recognition, AutomatedAnimalsBeesNeural Networks, ComputerSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

acoustic sensingbeehive acoustic monitoringhoney bee soundmachine learningprecision apiculturespectral analysis

Autor:innen und Institutionen

  • Department of Acoustics, Multimedia and Signal Processing, Wroclaw University of Science and Technology, 50-370 Wroclaw, Poland.
  • Department of Mechanics and Vibroacoustics, AGH University of Krakow, 30-059 Krakow, Poland.

ORCID-Profile: Piotr Książek, Urszula Libal, Aleksandra Król-Nowak

Zitieren

APA

Książek, P., Libal, U., & Król-Nowak, A. (2025). Spectral Components of Honey Bee Sound Signals Recorded Inside and Outside the Beehive: An Explainable Machine Learning Approach to Diurnal Pattern Recognition. Sensors, 25(14), 4424. https://doi.org/10.3390/s25144424

Vancouver

Książek P, Libal U, Król-Nowak A. Spectral Components of Honey Bee Sound Signals Recorded Inside and Outside the Beehive: An Explainable Machine Learning Approach to Diurnal Pattern Recognition. Sensors. 2025;25(14):4424. doi:10.3390/s25144424

BibTeX
@article{Ksiek2025,
  author = {Książek, Piotr and Libal, Urszula and Król-Nowak, Aleksandra},
  title = {Spectral Components of Honey Bee Sound Signals Recorded Inside and Outside the Beehive: An Explainable Machine Learning Approach to Diurnal Pattern Recognition},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {14},
  pages = {4424},
  doi = {10.3390/s25144424}
}
Kostenlos starten →