Cargando…
Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls
Despite the accumulation of data and studies, deciphering animal vocal communication remains challenging. In most cases, researchers must deal with the sparse recordings composing Small, Unbalanced, Noisy, but Genuine (SUNG) datasets. SUNG datasets are characterized by a limited number of recordings...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10129004/ https://www.ncbi.nlm.nih.gov/pubmed/37053268 http://dx.doi.org/10.1371/journal.pcbi.1010325 |
_version_ | 1785030636779601920 |
---|---|
author | Arnaud, Vincent Pellegrino, François Keenan, Sumir St-Gelais, Xavier Mathevon, Nicolas Levréro, Florence Coupé, Christophe |
author_facet | Arnaud, Vincent Pellegrino, François Keenan, Sumir St-Gelais, Xavier Mathevon, Nicolas Levréro, Florence Coupé, Christophe |
author_sort | Arnaud, Vincent |
collection | PubMed |
description | Despite the accumulation of data and studies, deciphering animal vocal communication remains challenging. In most cases, researchers must deal with the sparse recordings composing Small, Unbalanced, Noisy, but Genuine (SUNG) datasets. SUNG datasets are characterized by a limited number of recordings, most often noisy, and unbalanced in number between the individuals or categories of vocalizations. SUNG datasets therefore offer a valuable but inevitably distorted vision of communication systems. Adopting the best practices in their analysis is essential to effectively extract the available information and draw reliable conclusions. Here we show that the most recent advances in machine learning applied to a SUNG dataset succeed in unraveling the complex vocal repertoire of the bonobo, and we propose a workflow that can be effective with other animal species. We implement acoustic parameterization in three feature spaces and run a Supervised Uniform Manifold Approximation and Projection (S-UMAP) to evaluate how call types and individual signatures cluster in the bonobo acoustic space. We then implement three classification algorithms (Support Vector Machine, xgboost, neural networks) and their combination to explore the structure and variability of bonobo calls, as well as the robustness of the individual signature they encode. We underscore how classification performance is affected by the feature set and identify the most informative features. In addition, we highlight the need to address data leakage in the evaluation of classification performance to avoid misleading interpretations. Our results lead to identifying several practical approaches that are generalizable to any other animal communication system. To improve the reliability and replicability of vocal communication studies with SUNG datasets, we thus recommend: i) comparing several acoustic parameterizations; ii) visualizing the dataset with supervised UMAP to examine the species acoustic space; iii) adopting Support Vector Machines as the baseline classification approach; iv) explicitly evaluating data leakage and possibly implementing a mitigation strategy. |
format | Online Article Text |
id | pubmed-10129004 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-101290042023-04-26 Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls Arnaud, Vincent Pellegrino, François Keenan, Sumir St-Gelais, Xavier Mathevon, Nicolas Levréro, Florence Coupé, Christophe PLoS Comput Biol Research Article Despite the accumulation of data and studies, deciphering animal vocal communication remains challenging. In most cases, researchers must deal with the sparse recordings composing Small, Unbalanced, Noisy, but Genuine (SUNG) datasets. SUNG datasets are characterized by a limited number of recordings, most often noisy, and unbalanced in number between the individuals or categories of vocalizations. SUNG datasets therefore offer a valuable but inevitably distorted vision of communication systems. Adopting the best practices in their analysis is essential to effectively extract the available information and draw reliable conclusions. Here we show that the most recent advances in machine learning applied to a SUNG dataset succeed in unraveling the complex vocal repertoire of the bonobo, and we propose a workflow that can be effective with other animal species. We implement acoustic parameterization in three feature spaces and run a Supervised Uniform Manifold Approximation and Projection (S-UMAP) to evaluate how call types and individual signatures cluster in the bonobo acoustic space. We then implement three classification algorithms (Support Vector Machine, xgboost, neural networks) and their combination to explore the structure and variability of bonobo calls, as well as the robustness of the individual signature they encode. We underscore how classification performance is affected by the feature set and identify the most informative features. In addition, we highlight the need to address data leakage in the evaluation of classification performance to avoid misleading interpretations. Our results lead to identifying several practical approaches that are generalizable to any other animal communication system. To improve the reliability and replicability of vocal communication studies with SUNG datasets, we thus recommend: i) comparing several acoustic parameterizations; ii) visualizing the dataset with supervised UMAP to examine the species acoustic space; iii) adopting Support Vector Machines as the baseline classification approach; iv) explicitly evaluating data leakage and possibly implementing a mitigation strategy. Public Library of Science 2023-04-13 /pmc/articles/PMC10129004/ /pubmed/37053268 http://dx.doi.org/10.1371/journal.pcbi.1010325 Text en © 2023 Arnaud et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Arnaud, Vincent Pellegrino, François Keenan, Sumir St-Gelais, Xavier Mathevon, Nicolas Levréro, Florence Coupé, Christophe Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls |
title | Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls |
title_full | Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls |
title_fullStr | Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls |
title_full_unstemmed | Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls |
title_short | Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls |
title_sort | improving the workflow to crack small, unbalanced, noisy, but genuine (sung) datasets in bioacoustics: the case of bonobo calls |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10129004/ https://www.ncbi.nlm.nih.gov/pubmed/37053268 http://dx.doi.org/10.1371/journal.pcbi.1010325 |
work_keys_str_mv | AT arnaudvincent improvingtheworkflowtocracksmallunbalancednoisybutgenuinesungdatasetsinbioacousticsthecaseofbonobocalls AT pellegrinofrancois improvingtheworkflowtocracksmallunbalancednoisybutgenuinesungdatasetsinbioacousticsthecaseofbonobocalls AT keenansumir improvingtheworkflowtocracksmallunbalancednoisybutgenuinesungdatasetsinbioacousticsthecaseofbonobocalls AT stgelaisxavier improvingtheworkflowtocracksmallunbalancednoisybutgenuinesungdatasetsinbioacousticsthecaseofbonobocalls AT mathevonnicolas improvingtheworkflowtocracksmallunbalancednoisybutgenuinesungdatasetsinbioacousticsthecaseofbonobocalls AT levreroflorence improvingtheworkflowtocracksmallunbalancednoisybutgenuinesungdatasetsinbioacousticsthecaseofbonobocalls AT coupechristophe improvingtheworkflowtocracksmallunbalancednoisybutgenuinesungdatasetsinbioacousticsthecaseofbonobocalls |