EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reconstruction Modeling and Validation of Brown Croaker (Miichthys miiuy) Vocalizations Using Wavelet-Based Inversion and Deep Learning

Sunhyo Kim, Jongwook Choi, Bum-Kyu Kim, Hansoo Kim iD, Donhyug Kang iD, Jee Woong Choi, Young Geul Yoon iD, Sungho Cho iD

Sensors · 2025

DOI: 10.3390/s25196178 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Sunhyo Kim und 7 weiteren Autor:innen. Beteiligte Einrichtung: Sea Power Reinforcement Security Research Department, Korea Institute of Ocean Science & Technology (KIOST), Busan 49111, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Vocalization, Animal, Perciformes. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Research Institute for defense Technology planning and advancement.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fish species’ biological vocalizations serve as essential acoustic signatures for passive acoustic monitoring (PAM) and ecological assessments. However, limited availability of high-quality acoustic recordings, particularly for region-specific species like the brown croaker (Miichthys miiuy), hampers data-driven bioacoustic methodology development. In this study, we present a framework for reconstructing brown croaker vocalizations by integrating fk14 wavelet synthesis, PSO-based parameter optimization (with an objective combining correlation and normalized MSE), and deep learning-based validation. Sensitivity analysis using a normalized Bartlett processor identified delay and scale (length) as the most critical parameters, defining valid ranges that maintained waveform similarity above 98%. The reconstructed signals matched measured calls in both time and frequency domains, replicating single-pulse morphology, inter-pulse interval (IPI) distributions, and energy spectral density. Validation with a ResNet-18-based Siamese network produced near-unity cosine similarity (~0.9996) between measured and reconstructed signals. Statistical analyses (95% confidence intervals; residual errors) confirmed faithful preservation of SPL values and minor, biologically plausible IPI variations. Under noisy conditions, similarity decreased as SNR dropped, indicating that environmental noise affects reconstruction fidelity. These results demonstrate that the proposed framework can reliably generate acoustically realistic and morphologically consistent fish vocalizations, even under data-limited scenarios. The methodology holds promise for dataset augmentation, PAM applications, and species-specific call simulation. Future work will extend this framework by using reconstructed signals to train generative models (e.g., GANs, WaveNet), enabling scalable synthesis and supporting real-time adaptive modeling in field monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningVocalization, AnimalPerciformesAnimalsAcousticsWavelet AnalysisSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

bioacoustic signal reconstructionbrown croaker vocalizationpassive acoustic monitoring (PAM)waveform similarity

Autor:innen und Institutionen

  • Sea Power Reinforcement Security Research Department, Korea Institute of Ocean Science & Technology (KIOST), Busan 49111, Republic of Korea.
  • Department of Marine Science and Convergence Engineering, Hanyang University ERICA, Ansan 15588, Republic of Korea.
  • School of Defense Intelligence and Information Convergence Engineering, Hanyang University ERICA, Ansan 15588, Republic of Korea.

ORCID-Profile: Hansoo Kim, Donhyug Kang, Young Geul Yoon, Sungho Cho

Förderung

  • Korea Research Institute for defense Technology planning and advancement

Zitieren

APA

Kim, S., Choi, J., Kim, B. K., Kim, H., Kang, D., Choi, J. W., Yoon, Y. G., & Cho, S. (2025). Reconstruction Modeling and Validation of Brown Croaker (Miichthys miiuy) Vocalizations Using Wavelet-Based Inversion and Deep Learning. Sensors. https://doi.org/10.3390/s25196178

Vancouver

Kim S, Choi J, Kim BK, Kim H, Kang D, Choi JW, et al. Reconstruction Modeling and Validation of Brown Croaker (Miichthys miiuy) Vocalizations Using Wavelet-Based Inversion and Deep Learning. Sensors. 2025. doi:10.3390/s25196178

BibTeX
@article{Kim2025,
  author = {Kim, Sunhyo and Choi, Jongwook and Kim, Bum-Kyu and Kim, Hansoo and Kang, Donhyug and Choi, Jee Woong and Yoon, Young Geul and Cho, Sungho},
  title = {Reconstruction Modeling and Validation of Brown Croaker (Miichthys miiuy) Vocalizations Using Wavelet-Based Inversion and Deep Learning},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25196178}
}
Kostenlos starten →