A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals

Autores
Ferrero, Mariano; Chelotti, Jose Omar; Martínez Rau, Luciano Sebastián; Vignolo, Leandro Daniel; Pires, Martín; Galli, Julio Ricardo; Giovanini, Leonardo Luis; Rufiner, Hugo Leonardo
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Monitoring feeding behaviour is a relevant task for efficient herd management and the effective use of available resources in grazing cattle. The ability to automatically recognise animals’ feeding activities through the identification of specific jaw movements allows for the improvement of diet formulation, as well as early detection of metabolic problems and symptoms of animal discomfort, among other benefits. The use of sensors to obtain signals for such monitoring has become popular in the last two decades. The most frequently employed sensors include accelerometers, microphones, and cameras, each with its own set of advantages and drawbacks. An unexplored aspect is the simultaneous use of multiple sensors with the aim of combining signals in order to enhance the precision of the estimations. In this direction, this work introduces a deep neural network based on the fusion of acoustic and inertial signals, composed of convolutional, recurrent, and dense layers. The main advantage of this model is the combination of signals through the automatic extraction of features independently from each of them. The model has emerged from an exploration and comparison of different neural network architectures proposed in this work, which carry out information fusion at different levels. Feature-level fusion has outperformed data and decision-level fusion by at least a 0.14 based on the F1-score metric. Moreover, a comparison with state-of-the-art machine learning methods is presented, including traditional and deep learning approaches. The proposed model yielded an F1-score value of 0.802, representing a 14% increase compared to previous methods. Finally, results from an ablation study and post-training quantisation evaluation are also reported.
Fil: Ferrero, Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Chelotti, Jose Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Martínez Rau, Luciano Sebastián. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Vignolo, Leandro Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Pires, Martín. Universidad Nacional de Rosario; Argentina
Fil: Galli, Julio Ricardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Investigaciones en Ciencias Agrarias de Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Agrarias. Instituto de Investigaciones en Ciencias Agrarias de Rosario; Argentina
Fil: Giovanini, Leonardo Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Rufiner, Hugo Leonardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Materia
Deep learning
Information fusion
Convolutional neural networks
Recurrent neural networks
Precision livestock farming
Ruminant foraging behaviour
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/282030
Acceder
id CONICETDig_459a4859771676f122424f85a96afd19
oai_identifier_str oai:ri.conicet.gov.ar:11336/282030
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signalsFerrero, MarianoChelotti, Jose OmarMartínez Rau, Luciano SebastiánVignolo, Leandro DanielPires, MartínGalli, Julio RicardoGiovanini, Leonardo LuisRufiner, Hugo LeonardoDeep learningInformation fusionConvolutional neural networksRecurrent neural networksPrecision livestock farmingRuminant foraging behaviourhttps://purl.org/becyt/ford/2.2https://purl.org/becyt/ford/2Monitoring feeding behaviour is a relevant task for efficient herd management and the effective use of available resources in grazing cattle. The ability to automatically recognise animals’ feeding activities through the identification of specific jaw movements allows for the improvement of diet formulation, as well as early detection of metabolic problems and symptoms of animal discomfort, among other benefits. The use of sensors to obtain signals for such monitoring has become popular in the last two decades. The most frequently employed sensors include accelerometers, microphones, and cameras, each with its own set of advantages and drawbacks. An unexplored aspect is the simultaneous use of multiple sensors with the aim of combining signals in order to enhance the precision of the estimations. In this direction, this work introduces a deep neural network based on the fusion of acoustic and inertial signals, composed of convolutional, recurrent, and dense layers. The main advantage of this model is the combination of signals through the automatic extraction of features independently from each of them. The model has emerged from an exploration and comparison of different neural network architectures proposed in this work, which carry out information fusion at different levels. Feature-level fusion has outperformed data and decision-level fusion by at least a 0.14 based on the F1-score metric. Moreover, a comparison with state-of-the-art machine learning methods is presented, including traditional and deep learning approaches. The proposed model yielded an F1-score value of 0.802, representing a 14% increase compared to previous methods. Finally, results from an ablation study and post-training quantisation evaluation are also reported.Fil: Ferrero, Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaFil: Chelotti, Jose Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaFil: Martínez Rau, Luciano Sebastián. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaFil: Vignolo, Leandro Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaFil: Pires, Martín. Universidad Nacional de Rosario; ArgentinaFil: Galli, Julio Ricardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Investigaciones en Ciencias Agrarias de Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Agrarias. Instituto de Investigaciones en Ciencias Agrarias de Rosario; ArgentinaFil: Giovanini, Leonardo Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaFil: Rufiner, Hugo Leonardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaPergamon-Elsevier Science Ltd2025-10info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/282030Ferrero, Mariano; Chelotti, Jose Omar; Martínez Rau, Luciano Sebastián; Vignolo, Leandro Daniel; Pires, Martín; et al.; A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals; Pergamon-Elsevier Science Ltd; Engineering Applications Of Artificial Intelligence; 157; 10-2025; 1-160952-1976CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S0952197625013740info:eu-repo/semantics/altIdentifier/doi/10.1016/j.engappai.2025.111372info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-03-11T12:17:14Zoai:ri.conicet.gov.ar:11336/282030instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982026-03-11 12:17:14.294CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
title A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
spellingShingle A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
Ferrero, Mariano
Deep learning
Information fusion
Convolutional neural networks
Recurrent neural networks
Precision livestock farming
Ruminant foraging behaviour
title_short A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
title_full A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
title_fullStr A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
title_full_unstemmed A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
title_sort A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals
dc.creator.none.fl_str_mv Ferrero, Mariano
Chelotti, Jose Omar
Martínez Rau, Luciano Sebastián
Vignolo, Leandro Daniel
Pires, Martín
Galli, Julio Ricardo
Giovanini, Leonardo Luis
Rufiner, Hugo Leonardo
author Ferrero, Mariano
author_facet Ferrero, Mariano
Chelotti, Jose Omar
Martínez Rau, Luciano Sebastián
Vignolo, Leandro Daniel
Pires, Martín
Galli, Julio Ricardo
Giovanini, Leonardo Luis
Rufiner, Hugo Leonardo
author_role author
author2 Chelotti, Jose Omar
Martínez Rau, Luciano Sebastián
Vignolo, Leandro Daniel
Pires, Martín
Galli, Julio Ricardo
Giovanini, Leonardo Luis
Rufiner, Hugo Leonardo
author2_role author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Deep learning
Information fusion
Convolutional neural networks
Recurrent neural networks
Precision livestock farming
Ruminant foraging behaviour
topic Deep learning
Information fusion
Convolutional neural networks
Recurrent neural networks
Precision livestock farming
Ruminant foraging behaviour
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.2
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv Monitoring feeding behaviour is a relevant task for efficient herd management and the effective use of available resources in grazing cattle. The ability to automatically recognise animals’ feeding activities through the identification of specific jaw movements allows for the improvement of diet formulation, as well as early detection of metabolic problems and symptoms of animal discomfort, among other benefits. The use of sensors to obtain signals for such monitoring has become popular in the last two decades. The most frequently employed sensors include accelerometers, microphones, and cameras, each with its own set of advantages and drawbacks. An unexplored aspect is the simultaneous use of multiple sensors with the aim of combining signals in order to enhance the precision of the estimations. In this direction, this work introduces a deep neural network based on the fusion of acoustic and inertial signals, composed of convolutional, recurrent, and dense layers. The main advantage of this model is the combination of signals through the automatic extraction of features independently from each of them. The model has emerged from an exploration and comparison of different neural network architectures proposed in this work, which carry out information fusion at different levels. Feature-level fusion has outperformed data and decision-level fusion by at least a 0.14 based on the F1-score metric. Moreover, a comparison with state-of-the-art machine learning methods is presented, including traditional and deep learning approaches. The proposed model yielded an F1-score value of 0.802, representing a 14% increase compared to previous methods. Finally, results from an ablation study and post-training quantisation evaluation are also reported.
Fil: Ferrero, Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Chelotti, Jose Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Martínez Rau, Luciano Sebastián. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Vignolo, Leandro Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Pires, Martín. Universidad Nacional de Rosario; Argentina
Fil: Galli, Julio Ricardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Investigaciones en Ciencias Agrarias de Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Agrarias. Instituto de Investigaciones en Ciencias Agrarias de Rosario; Argentina
Fil: Giovanini, Leonardo Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Rufiner, Hugo Leonardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
description Monitoring feeding behaviour is a relevant task for efficient herd management and the effective use of available resources in grazing cattle. The ability to automatically recognise animals’ feeding activities through the identification of specific jaw movements allows for the improvement of diet formulation, as well as early detection of metabolic problems and symptoms of animal discomfort, among other benefits. The use of sensors to obtain signals for such monitoring has become popular in the last two decades. The most frequently employed sensors include accelerometers, microphones, and cameras, each with its own set of advantages and drawbacks. An unexplored aspect is the simultaneous use of multiple sensors with the aim of combining signals in order to enhance the precision of the estimations. In this direction, this work introduces a deep neural network based on the fusion of acoustic and inertial signals, composed of convolutional, recurrent, and dense layers. The main advantage of this model is the combination of signals through the automatic extraction of features independently from each of them. The model has emerged from an exploration and comparison of different neural network architectures proposed in this work, which carry out information fusion at different levels. Feature-level fusion has outperformed data and decision-level fusion by at least a 0.14 based on the F1-score metric. Moreover, a comparison with state-of-the-art machine learning methods is presented, including traditional and deep learning approaches. The proposed model yielded an F1-score value of 0.802, representing a 14% increase compared to previous methods. Finally, results from an ablation study and post-training quantisation evaluation are also reported.
publishDate 2025
dc.date.none.fl_str_mv 2025-10
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/282030
Ferrero, Mariano; Chelotti, Jose Omar; Martínez Rau, Luciano Sebastián; Vignolo, Leandro Daniel; Pires, Martín; et al.; A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals; Pergamon-Elsevier Science Ltd; Engineering Applications Of Artificial Intelligence; 157; 10-2025; 1-16
0952-1976
CONICET Digital
CONICET
url http://hdl.handle.net/11336/282030
identifier_str_mv Ferrero, Mariano; Chelotti, Jose Omar; Martínez Rau, Luciano Sebastián; Vignolo, Leandro Daniel; Pires, Martín; et al.; A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals; Pergamon-Elsevier Science Ltd; Engineering Applications Of Artificial Intelligence; 157; 10-2025; 1-16
0952-1976
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S0952197625013740
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.engappai.2025.111372
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Pergamon-Elsevier Science Ltd
publisher.none.fl_str_mv Pergamon-Elsevier Science Ltd
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1859460253127540736
score 12.977003

Publicaciones similares