Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning

Deep learning allows us to automatize the acquisition of large amounts of behavioural animal data with applications for fisheries and aquaculture. In this work, we have trained an image-based deep learning algorithm, the Faster R-CNN (Faster region-based convolutional neural network), to automatical...

ver descrição completa

Detalhes bibliográficos
Autores: Signaroli, Marco, Lana, Arancha, Martorell Barceló, Martina, Sanllehi, Javier, Barceló-Serra, Margarida, Aspillaga, Eneko, Mulet, Júlia, Alós, Josep
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/282539
Acesso em linha:http://hdl.handle.net/10261/282539
Access Level:acceso abierto
Palavra-chave:Deep learning
Faster R-CNN
Fish behavioural ecology
Fish tracking
Sparus aurata
id ES_f23d2bcefe831d40f9cd4f76e6777f6c
oai_identifier_str oai:digital.csic.es:10261/282539
network_acronym_str ES
network_name_str España
repository_id_str
spelling Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learningSignaroli, MarcoLana, AranchaMartorell Barceló, MartinaSanllehi, JavierBarceló-Serra, MargaridaAspillaga, EnekoMulet, JúliaAlós, JosepDeep learningFaster R-CNNFish behavioural ecologyFish trackingSparus aurataDeep learning allows us to automatize the acquisition of large amounts of behavioural animal data with applications for fisheries and aquaculture. In this work, we have trained an image-based deep learning algorithm, the Faster R-CNN (Faster region-based convolutional neural network), to automatically detect and track the gilthead seabream, Sparus aurata, to search for individual differences in behaviour. We collected videos using a novel Raspberry Pi high throughput recording system attached to individual experimental behavioural arenas. From the continuous recording during behavioural assays, we acquired and labelled a total of 14,000 images and used them, along with data augmentation techniques, to train the network. Then, we evaluated the performance of our network at different training levels, increasing the number of images and applying data augmentation. For every validation step, we processed more than 52,000 images, with and without the presence of the gilthead seabream, in normal and altered (i.e., after the introduction of a non-familiar object to test for explorative behaviour) behavioural arenas. The final and best version of the neural network, trained with all the images and with data augmentation, reached an accuracy of 92,79% ± 6.78% [89.24–96.34] of correct classification and 10.25 ± 61.59 pixels [6.59-13.91] of fish positioning error. Our recording system based on a Raspberry Pi and a trained convolutional neural network provides a valuable non-invasive tool to automatically track fish movements in experimental arenas and, using the trajectories obtained during behavioural tests, to assay behavioural types.This project was funded by the research project FISHOBES (grant no. CTM2017-91490-EXP) funded by the Spanish Ministry of Science and Innovation (MICINN). Marco Signaroli was suppoerted by a “Ayudas para contratos predoctorales” (grant no. PRE2020-095580) funded by MCIN/AEI /10.13039/501100011033 and the FSE “invierte en tu futuro”. Josep Alós received funding from a Ramon y Cajal Grant (grant no. RYC2018-024488-I), the CLOCKS I+D+I project (grant no. PID2019-104940GA-I00) and JSATS PIE project (grant no. PIE202030E002) funded by MCIN/AEI/10.13039/501100011033 and the FSE “invierte en tu futuro”.PeerJMinisterio de Ciencia e Innovación (España)Agencia Estatal de Investigación (España)Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]2022202220222022info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Publisher's versioninfo:eu-repo/semantics/publishedVersionhttp://hdl.handle.net/10261/282539reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#CTM2017-91490-EXPPRE2020-095580RYC-2018-024488-ISignaroli, Marco; Lana, Arantxa; Martorell Barceló, Martina; Sanllehi, Javier; Barceló-Serra, Margarida; Aspillaga, Eneko; Mulet, Júlia; Alós, Josep; 2022; Supplemental Information of "Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning" [Dataset]; PeerJ; https://doi.org/10.7717/peerj.13396/supp-1http://dx.doi.org/10.7717/peerj.13396Síinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/2825392026-05-22T06:33:51Z
dc.title.none.fl_str_mv Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning
title Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning
spellingShingle Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning
Signaroli, Marco
Deep learning
Faster R-CNN
Fish behavioural ecology
Fish tracking
Sparus aurata
title_short Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning
title_full Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning
title_fullStr Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning
title_full_unstemmed Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning
title_sort Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning
dc.creator.none.fl_str_mv Signaroli, Marco
Lana, Arancha
Martorell Barceló, Martina
Sanllehi, Javier
Barceló-Serra, Margarida
Aspillaga, Eneko
Mulet, Júlia
Alós, Josep
author Signaroli, Marco
author_facet Signaroli, Marco
Lana, Arancha
Martorell Barceló, Martina
Sanllehi, Javier
Barceló-Serra, Margarida
Aspillaga, Eneko
Mulet, Júlia
Alós, Josep
author_role author
author2 Lana, Arancha
Martorell Barceló, Martina
Sanllehi, Javier
Barceló-Serra, Margarida
Aspillaga, Eneko
Mulet, Júlia
Alós, Josep
author2_role author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Ministerio de Ciencia e Innovación (España)
Agencia Estatal de Investigación (España)
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Deep learning
Faster R-CNN
Fish behavioural ecology
Fish tracking
Sparus aurata
topic Deep learning
Faster R-CNN
Fish behavioural ecology
Fish tracking
Sparus aurata
description Deep learning allows us to automatize the acquisition of large amounts of behavioural animal data with applications for fisheries and aquaculture. In this work, we have trained an image-based deep learning algorithm, the Faster R-CNN (Faster region-based convolutional neural network), to automatically detect and track the gilthead seabream, Sparus aurata, to search for individual differences in behaviour. We collected videos using a novel Raspberry Pi high throughput recording system attached to individual experimental behavioural arenas. From the continuous recording during behavioural assays, we acquired and labelled a total of 14,000 images and used them, along with data augmentation techniques, to train the network. Then, we evaluated the performance of our network at different training levels, increasing the number of images and applying data augmentation. For every validation step, we processed more than 52,000 images, with and without the presence of the gilthead seabream, in normal and altered (i.e., after the introduction of a non-familiar object to test for explorative behaviour) behavioural arenas. The final and best version of the neural network, trained with all the images and with data augmentation, reached an accuracy of 92,79% ± 6.78% [89.24–96.34] of correct classification and 10.25 ± 61.59 pixels [6.59-13.91] of fish positioning error. Our recording system based on a Raspberry Pi and a trained convolutional neural network provides a valuable non-invasive tool to automatically track fish movements in experimental arenas and, using the trajectories obtained during behavioural tests, to assay behavioural types.
publishDate 2022
dc.date.none.fl_str_mv 2022
2022
2022
2022
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Publisher's version
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/282539
url http://hdl.handle.net/10261/282539
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv #PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
CTM2017-91490-EXP
PRE2020-095580
RYC-2018-024488-I
Signaroli, Marco; Lana, Arantxa; Martorell Barceló, Martina; Sanllehi, Javier; Barceló-Serra, Margarida; Aspillaga, Eneko; Mulet, Júlia; Alós, Josep; 2022; Supplemental Information of "Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning" [Dataset]; PeerJ; https://doi.org/10.7717/peerj.13396/supp-1
http://dx.doi.org/10.7717/peerj.13396
Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv PeerJ
publisher.none.fl_str_mv PeerJ
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869424260994301952
score 15.811543

Registos relacionados