Automated Classification of Humpback Whale Calls Using Deep Learning: A Comparative Study of Neural Architectures and Acoustic Feature Representations
Sensors · 2026
DOI: 10.3390/s26020715 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Sensors, 2026. Verfasst von Jack C Johnson und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering, Computing and Mathematical Sciences (EECMS), Curtin University, Kent Street, Bentley, WA 6102, Australia. Hauptthemen laut MEDLINE: Deep Learning, Acoustics, Humpback Whale, Vocalization, Animal. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Passive acoustic monitoring (PAM) using hydrophones enables collecting acoustic data to be collected in large and diverse quantities, necessitating the need for a reliable automated classification system. This paper presents a data-processing pipeline and a set of neural networks designed for a humpback-whale-detection system. A collection of audio segments is compiled using publicly available audio repositories and extensively curated via manual methods, undertaking thorough examination, editing and clipping to produce a dataset minimizing bias or categorization errors. An array of standard data-augmentation techniques are applied to the collected audio, diversifying and expanding the original dataset. Multiple neural networks are designed and trained using TensorFlow 2.20.0 and Keras 3.13.1 frameworks, resulting in a custom curated architecture layout based on research and iterative improvements. The pre-trained model MobileNetV2 is also included for further analysis. Model performance demonstrates a strong dependence on both feature representation and network architecture. Mel spectrogram inputs consistently outperformed MFCC (Mel-Frequency Cepstral Coefficients) features across all model types. The highest performance was achieved by the pretrained MobileNetV2 using mel spectrograms without augmentation, reaching a test accuracy of 99.01% with balanced precision and recall of 99% and a Matthews correlation coefficient of 0.98. The custom CNN with mel spectrograms also achieved strong performance, with 98.92% accuracy and a false negative rate of only 0.75%. In contrast, models trained with MFCC representations exhibited consistently lower robustness and higher false negative rates. These results highlight the comparative strengths of the evaluated feature representations and network architectures for humpback whale detection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical Engineering, Computing and Mathematical Sciences (EECMS), Curtin University, Kent Street, Bentley, WA 6102, Australia.
ORCID-Profile: Jack C Johnson, Yue Rong
Zitieren
APA
Johnson, J. C., & Rong, Y. (2026). Automated Classification of Humpback Whale Calls Using Deep Learning: A Comparative Study of Neural Architectures and Acoustic Feature Representations. Sensors. https://doi.org/10.3390/s26020715
Vancouver
Johnson JC, Rong Y. Automated Classification of Humpback Whale Calls Using Deep Learning: A Comparative Study of Neural Architectures and Acoustic Feature Representations. Sensors. 2026. doi:10.3390/s26020715
BibTeX
@article{Johnson2026,
author = {Johnson, Jack C and Rong, Yue},
title = {Automated Classification of Humpback Whale Calls Using Deep Learning: A Comparative Study of Neural Architectures and Acoustic Feature Representations},
journal = {Sensors},
year = {2026},
doi = {10.3390/s26020715}
}
EUVIMED