Optimising Convolutional Neural Network Architectures for Fin Whale Pulse Detection in Spectrograms
Applied Sciences · 28.02.2026 · 16 (5) · 2345
DOI: 10.3390/app16052345 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 28.02.2026. Verfasst von Marta Román-Ruiz und 1 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: HE Framework Programme.
Abstract (Originalsprache)
Deep neural networks are widely used for image classification in different fields, although selecting an appropriate architecture often remains a trial-and-error process. The purpose of this work is to investigate a convolutional neural network architecture used to detect whale pulses in spectrograms in order to better understand the causes of its underperformance. By examining the behaviour of its internal layers, we show that the early convolutional blocks capture the most informative acoustic features, while deeper layers provide limited additional benefit and, under the considered training conditions, may even degrade classification accuracy. Based on these observations, we derive a simplified architecture consisting of only the first two convolutional layers followed by a lightweight classifier. This network achieves near-optimal performance, improving accuracy from 87% to 98%, and exhibits substantially lower variability between repetitions compared to the original model.
Förderung
- HE Framework Programme
Zitieren
APA
Román-Ruiz, M., & Rossi, C. (2026). Optimising Convolutional Neural Network Architectures for Fin Whale Pulse Detection in Spectrograms. Applied Sciences, 16(5), 2345. https://doi.org/10.3390/app16052345
Vancouver
Román-Ruiz M, Rossi C. Optimising Convolutional Neural Network Architectures for Fin Whale Pulse Detection in Spectrograms. Applied Sciences. 2026;16(5):2345. doi:10.3390/app16052345
BibTeX
@article{RomnRuiz2026,
author = {Román-Ruiz, Marta and Rossi, Claudio},
title = {Optimising Convolutional Neural Network Architectures for Fin Whale Pulse Detection in Spectrograms},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {5},
pages = {2345},
doi = {10.3390/app16052345}
}
EUVIMED