Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattle
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/ani11123438 http://hdl.handle.net/11449/222967 |
Resumo: | Knowledge of animal behavior can be indicative of the well-being, health, productivity, and reproduction of animals. The use of accelerometers to classify and predict animal behavior can be a tool for continuous animal monitoring. Therefore, the aim of this study was to provide strategies for predicting more and less frequent beef cattle grazing behaviors. The behavior activities observed were grazing, ruminating, idle, water consumption frequency (WCF), feeding (supplementation) and walking. Three Machine Learning algorithms: Random Forest (RF), Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC) and two resample methods: under and over-sampling, were tested. Overall accuracy was higher for RF models trained with the over-sampled dataset. The greatest sensitivity (0.808) for the less frequent behavior (WCF) was observed in the RF algorithm trained with the under-sampled data. The SVM models only performed efficiently when classifying the most frequent behavior (idle). The greatest predictor in the NBC algorithm was for ruminating behavior, with the over-sampled training dataset. The results showed that the behaviors of the studied animals were classified with high accuracy and specificity when the RF algorithm trained with the resampling methods was used. Resampling training datasets is a strategy to be considered, especially when less frequent behaviors are of interest. |
id |
UNSP_54c6c911e3059634d9321eb602b7a1f5 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/222967 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattleMachine learningNaïve Bayes ClassifierNeloreRandom ForestSupport Vector MachineKnowledge of animal behavior can be indicative of the well-being, health, productivity, and reproduction of animals. The use of accelerometers to classify and predict animal behavior can be a tool for continuous animal monitoring. Therefore, the aim of this study was to provide strategies for predicting more and less frequent beef cattle grazing behaviors. The behavior activities observed were grazing, ruminating, idle, water consumption frequency (WCF), feeding (supplementation) and walking. Three Machine Learning algorithms: Random Forest (RF), Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC) and two resample methods: under and over-sampling, were tested. Overall accuracy was higher for RF models trained with the over-sampled dataset. The greatest sensitivity (0.808) for the less frequent behavior (WCF) was observed in the RF algorithm trained with the under-sampled data. The SVM models only performed efficiently when classifying the most frequent behavior (idle). The greatest predictor in the NBC algorithm was for ruminating behavior, with the over-sampled training dataset. The results showed that the behaviors of the studied animals were classified with high accuracy and specificity when the RF algorithm trained with the resampling methods was used. Resampling training datasets is a strategy to be considered, especially when less frequent behaviors are of interest.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Departamento de Engenharia e Ciências Exatas Universidade Estadual PaulistaDepartamento de Zootecnia e Desenvolvimento Rural Universidade Federal de Santa CatarinaDepartamento de Zootecnia Universidade Estadual PaulistaDepartamento de Engenharia e Ciências Exatas Universidade Estadual PaulistaDepartamento de Zootecnia Universidade Estadual PaulistaCAPES: 001FAPESP: 2015/16631-5FAPESP: 2018/20753-7Universidade Estadual Paulista (UNESP)Universidade Federal de Santa Catarina (UFSC)Watanabe, Rafael N. [UNESP]Bernardes, Priscila A.Romanzini, Eliéder P. [UNESP]Teobaldo, Ronyatta W. [UNESP]Reis, Ricardo A. [UNESP]Munari, Danísio P. [UNESP]Braga, Larissa G. [UNESP]Brito, Thaís R. [UNESP]2022-04-28T19:47:48Z2022-04-28T19:47:48Z2021-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/ani11123438Animals, v. 11, n. 12, 2021.2076-2615http://hdl.handle.net/11449/22296710.3390/ani111234382-s2.0-85120419769Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengAnimalsinfo:eu-repo/semantics/openAccess2022-04-28T19:47:48Zoai:repositorio.unesp.br:11449/222967Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462022-04-28T19:47:48Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattle |
title |
Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattle |
spellingShingle |
Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattle Watanabe, Rafael N. [UNESP] Machine learning Naïve Bayes Classifier Nelore Random Forest Support Vector Machine |
title_short |
Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattle |
title_full |
Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattle |
title_fullStr |
Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattle |
title_full_unstemmed |
Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattle |
title_sort |
Strategy to predict high and low frequency behaviors using triaxial accelerometers in grazing of beef cattle |
author |
Watanabe, Rafael N. [UNESP] |
author_facet |
Watanabe, Rafael N. [UNESP] Bernardes, Priscila A. Romanzini, Eliéder P. [UNESP] Teobaldo, Ronyatta W. [UNESP] Reis, Ricardo A. [UNESP] Munari, Danísio P. [UNESP] Braga, Larissa G. [UNESP] Brito, Thaís R. [UNESP] |
author_role |
author |
author2 |
Bernardes, Priscila A. Romanzini, Eliéder P. [UNESP] Teobaldo, Ronyatta W. [UNESP] Reis, Ricardo A. [UNESP] Munari, Danísio P. [UNESP] Braga, Larissa G. [UNESP] Brito, Thaís R. [UNESP] |
author2_role |
author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Universidade Federal de Santa Catarina (UFSC) |
dc.contributor.author.fl_str_mv |
Watanabe, Rafael N. [UNESP] Bernardes, Priscila A. Romanzini, Eliéder P. [UNESP] Teobaldo, Ronyatta W. [UNESP] Reis, Ricardo A. [UNESP] Munari, Danísio P. [UNESP] Braga, Larissa G. [UNESP] Brito, Thaís R. [UNESP] |
dc.subject.por.fl_str_mv |
Machine learning Naïve Bayes Classifier Nelore Random Forest Support Vector Machine |
topic |
Machine learning Naïve Bayes Classifier Nelore Random Forest Support Vector Machine |
description |
Knowledge of animal behavior can be indicative of the well-being, health, productivity, and reproduction of animals. The use of accelerometers to classify and predict animal behavior can be a tool for continuous animal monitoring. Therefore, the aim of this study was to provide strategies for predicting more and less frequent beef cattle grazing behaviors. The behavior activities observed were grazing, ruminating, idle, water consumption frequency (WCF), feeding (supplementation) and walking. Three Machine Learning algorithms: Random Forest (RF), Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC) and two resample methods: under and over-sampling, were tested. Overall accuracy was higher for RF models trained with the over-sampled dataset. The greatest sensitivity (0.808) for the less frequent behavior (WCF) was observed in the RF algorithm trained with the under-sampled data. The SVM models only performed efficiently when classifying the most frequent behavior (idle). The greatest predictor in the NBC algorithm was for ruminating behavior, with the over-sampled training dataset. The results showed that the behaviors of the studied animals were classified with high accuracy and specificity when the RF algorithm trained with the resampling methods was used. Resampling training datasets is a strategy to be considered, especially when less frequent behaviors are of interest. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-12-01 2022-04-28T19:47:48Z 2022-04-28T19:47:48Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.3390/ani11123438 Animals, v. 11, n. 12, 2021. 2076-2615 http://hdl.handle.net/11449/222967 10.3390/ani11123438 2-s2.0-85120419769 |
url |
http://dx.doi.org/10.3390/ani11123438 http://hdl.handle.net/11449/222967 |
identifier_str_mv |
Animals, v. 11, n. 12, 2021. 2076-2615 10.3390/ani11123438 2-s2.0-85120419769 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Animals |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799965675970625536 |