EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Markov Chain Wave Generative Adversarial Network for Bee Bioacoustic Signal Synthesis

Kumudu Samarappuli, Iman Ardekani iD, Mahsa Mohaghegh iD, Abdolhossein Sarrafzadeh

Sensors · 2026

DOI: 10.3390/s26020371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Kumudu Samarappuli und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing, Electrical Engineering and Applied Technology, Unitec Institute of Technology, Auckland 1025, New Zealand. Hauptthemen laut MEDLINE: Markov Chains, Signal Processing, Computer-Assisted, Acoustics. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a framework for synthesizing bee bioacoustic signals associated with hive events. While existing approaches like WaveGAN have shown promise in audio generation, they often fail to preserve the subtle temporal and spectral features of bioacoustic signals critical for event-specific classification. The proposed method, MCWaveGAN, extends WaveGAN with a Markov Chain refinement stage, producing synthetic signals that more closely match the distribution of real bioacoustic data. Experimental results show that this method captures signal characteristics more effectively than WaveGAN alone. Furthermore, when integrated into a classifier, synthesized signals improved hive status prediction accuracy. These results highlight the potential of the proposed method to alleviate data scarcity in bioacoustics and support intelligent monitoring in smart beekeeping, with broader applicability to other ecological and agricultural domains.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Markov ChainsSignal Processing, Computer-AssistedAcousticsAnimalsBeesGenerative Adversarial NetworksAlgorithmsGenerative Artificial Intelligence

Stichwörter der Autor:innen

Markov Chainbee bioacousticgenerative adversarial networkssmart beekeepingsynthetic data

Autor:innen und Institutionen

  • School of Computing, Electrical Engineering and Applied Technology, Unitec Institute of Technology, Auckland 1025, New Zealand.
  • School of Arts and Sciences, The University of Notre Dame Australia (Sydney Campus), Darlinghurst, NSW 2007, Australia.
  • School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand.
  • Batten College of Engineering and Technology, Old Dominion University, Norfolk, VA 23529, USA.

ORCID-Profile: Iman Ardekani, Mahsa Mohaghegh

Zitieren

APA

Samarappuli, K., Ardekani, I., Mohaghegh, M., & Sarrafzadeh, A. (2026). Markov Chain Wave Generative Adversarial Network for Bee Bioacoustic Signal Synthesis. Sensors. https://doi.org/10.3390/s26020371

Vancouver

Samarappuli K, Ardekani I, Mohaghegh M, Sarrafzadeh A. Markov Chain Wave Generative Adversarial Network for Bee Bioacoustic Signal Synthesis. Sensors. 2026. doi:10.3390/s26020371

BibTeX
@article{Samarappuli2026,
  author = {Samarappuli, Kumudu and Ardekani, Iman and Mohaghegh, Mahsa and Sarrafzadeh, Abdolhossein},
  title = {Markov Chain Wave Generative Adversarial Network for Bee Bioacoustic Signal Synthesis},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26020371}
}
Kostenlos starten →