EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Convolutional Neural Networks for Real Time Classification of Beehive Acoustic Patterns on Constrained Devices

Antonio Robles-Guerrero iD, Salvador Gómez-Jiménez iD, Tonatiuh Saucedo-Anaya, Daniela López-Betancur iD, David Navarro-Solís iD, Carlos Guerrero-Méndez iD

Sensors · 2024

DOI: 10.3390/s24196384 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Antonio Robles-Guerrero und 5 weiteren Autor:innen. Beteiligte Einrichtung: Unidad Académica de Ingeniería, Universidad Autónoma de Zacatecas, Zacatecas 98000, Mexico. Hauptthemen laut MEDLINE: Neural Networks, Computer, Acoustics. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent research has demonstrated the effectiveness of convolutional neural networks (CNN) in assessing the health status of bee colonies by classifying acoustic patterns. However, developing a monitoring system using CNNs compared to conventional machine learning models can result in higher computation costs, greater energy demand, and longer inference times. This study examines the potential of CNN architectures in developing a monitoring system based on constrained hardware. The experimentation involved testing ten CNN architectures from the PyTorch and Torchvision libraries on single-board computers: an Nvidia Jetson Nano (NJN), a Raspberry Pi 5 (RPi5), and an Orange Pi 5 (OPi5). The CNN architectures were trained using four datasets containing spectrograms of acoustic samples of different durations (30, 10, 5, or 1 s) to analyze their impact on performance. The hyperparameter search was conducted using the Optuna framework, and the CNN models were validated using k-fold cross-validation. The inference time and power consumption were measured to compare the performance of the CNN models and the SBCs. The aim is to provide a basis for developing a monitoring system for precision applications in apiculture based on constrained devices and CNNs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerAcousticsAnimalsBeesMachine LearningAlgorithms

Stichwörter der Autor:innen

beehive acoustic classificationbeehive monitoringconvolutional neural networksprecision apicultureprecision beekeeping

Autor:innen und Institutionen

  • Unidad Académica de Ingeniería, Universidad Autónoma de Zacatecas, Zacatecas 98000, Mexico.
  • Unidad Académica de Ciencia y Tecnología de la Luz y la Materia, Universidad Autónoma de Zacatecas, Campus es Parque de Ciencia y Tecnología QUANTUM Cto., Zacatecas 98160, Mexico.

ORCID-Profile: Antonio Robles-Guerrero, Salvador Gómez-Jiménez, Daniela López-Betancur, David Navarro-Solís, Carlos Guerrero-Méndez

Zitieren

APA

Robles-Guerrero, A., Gómez-Jiménez, S., Saucedo-Anaya, T., López-Betancur, D., Navarro-Solís, D., & Guerrero-Méndez, C. (2024). Convolutional Neural Networks for Real Time Classification of Beehive Acoustic Patterns on Constrained Devices. Sensors. https://doi.org/10.3390/s24196384

Vancouver

Robles-Guerrero A, Gómez-Jiménez S, Saucedo-Anaya T, López-Betancur D, Navarro-Solís D, Guerrero-Méndez C. Convolutional Neural Networks for Real Time Classification of Beehive Acoustic Patterns on Constrained Devices. Sensors. 2024. doi:10.3390/s24196384

BibTeX
@article{RoblesGuerrero2024,
  author = {Robles-Guerrero, Antonio and Gómez-Jiménez, Salvador and Saucedo-Anaya, Tonatiuh and López-Betancur, Daniela and Navarro-Solís, David and Guerrero-Méndez, Carlos},
  title = {Convolutional Neural Networks for Real Time Classification of Beehive Acoustic Patterns on Constrained Devices},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24196384}
}
Kostenlos starten →