Optimal feature selection and model explanation for reef fish sound classification
Philosophical Transactions of the Royal Society B: Biological Sciences · 2025
DOI: 10.1098/rstb.2024.0055 ↗Kurz gefasst
Fachartikel in der Zeitschrift Philosophical Transactions of the Royal Society B: Biological Sciences, 2025. Verfasst von Viviane R Barroso und 3 weiteren Autor:innen. Beteiligte Einrichtung: Marine Biotechnology Program, Instituto de Estudos do Mar Almirante Paulo Moreira, Arraial do Cabo, Rio de Janeiro 28930-000, Brazil. Hauptthemen laut MEDLINE: Fishes, Coral Reefs, Sound, Vocalization, Animal. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior-Brasil (CAPES), Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brasil.
Abstract (Originalsprache)
Fish produce a wide variety of sounds that contribute to the soundscapes of aquatic environments. In reef systems, these sounds are important acoustic cues for various ecological processes. Artificial intelligence methods to detect, classify and identify fish sounds have become increasingly common. This study proposes the classification of unknown fish sounds recorded in a subtropical rocky reef using different feature sets, data augmentation and explainable artificial intelligence tools. We used different supervised algorithms (naive Bayes, random forest, decision trees and multilayer perceptron) to perform a multiclass classification of four classes of fish pulsed sounds. The proposed models showed excellent performances, achieving 98.1% of correct classification with multilayer perceptron using data augmentation. Explainable artificial intelligence allowed us to identify which features contributed to predict each sound class. Recognizing and characterizing these sounds is key to better understanding diel behaviours and functional roles associated with critical reef ecological processes. This article is part of the theme issue ‘Acoustic monitoring for tropical ecology and conservation’.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Marine Biotechnology Program, Instituto de Estudos do Mar Almirante Paulo Moreira, Arraial do Cabo, Rio de Janeiro 28930-000, Brazil.
- Programa de Pós-Graduação em Ecologia, Universidade Federal do Rio de Janeiro, Rio de Janeiro, RJ 21941-902, Brazil.
- Departamento de Biologia Marinha, Universidade Federal Fluminense, Niterói, Rio de Janeiro 24210-201, Brazil.
ORCID-Profile: Viviane R Barroso
Förderung
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior-Brasil (CAPES)
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brasil
Zitieren
APA
Barroso, V. R., Lessa, A. A., Ferreira, C. E. L., & Xavier, F. C. (2025). Optimal feature selection and model explanation for reef fish sound classification. Philosophical Transactions of the Royal Society B: Biological Sciences. https://doi.org/10.1098/rstb.2024.0055
Vancouver
Barroso VR, Lessa AA, Ferreira CEL, Xavier FC. Optimal feature selection and model explanation for reef fish sound classification. Philosophical Transactions of the Royal Society B: Biological Sciences. 2025. doi:10.1098/rstb.2024.0055
BibTeX
@article{Barroso2025,
author = {Barroso, Viviane R and Lessa, Alexia A and Ferreira, Carlos E L and Xavier, Fabio C},
title = {Optimal feature selection and model explanation for reef fish sound classification},
journal = {Philosophical Transactions of the Royal Society B: Biological Sciences},
year = {2025},
doi = {10.1098/rstb.2024.0055}
}
EUVIMED