Cyber-physical system for environmental monitoring based on deep learning

Cyber-physical systems (CPS) constitute a promising paradigm that could fit various applications. Monitoring based on the Internet of Things (IoT) has become a research area with new challenges in which to extract valuable information. This paper proposes a deep learning classification sound system...

ver descrição completa

Detalhes bibliográficos
Autores: Monedero Goicoechea, Iñigo Luis, Barbancho Concejero, Julio, Márquez, Rafael, Beltrán Gala, Juan Francisco
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Recursos:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/111399
Acesso em linha:https://hdl.handle.net/11441/111399
https://doi.org/10.3390/s21113655
Access Level:acceso abierto
Palavra-chave:Convolutional neural network
Cyber-physical systems
Deep learning
Internet of Things
Machine learning
Passive active monitoring
id ES_4e37bba91d12ba024ca938144fbd27c3
oai_identifier_str oai:idus.us.es:11441/111399
network_acronym_str ES
network_name_str España
repository_id_str
spelling Cyber-physical system for environmental monitoring based on deep learningMonedero Goicoechea, Iñigo LuisBarbancho Concejero, JulioMárquez, RafaelBeltrán Gala, Juan FranciscoConvolutional neural networkCyber-physical systemsDeep learningInternet of ThingsMachine learningPassive active monitoringCyber-physical systems (CPS) constitute a promising paradigm that could fit various applications. Monitoring based on the Internet of Things (IoT) has become a research area with new challenges in which to extract valuable information. This paper proposes a deep learning classification sound system for execution over CPS. This system is based on convolutional neural networks (CNNs) and is focused on the different types of vocalization of two species of anurans. CNNs, in conjunction with the use of mel-spectrograms for sounds, are shown to be an adequate tool for the classification of environmental sounds. The classification results obtained are excellent (97.53% overall accuracy) and can be considered a very promising use of the system for classifying other biological acoustic targets as well as analyzing biodiversity indices in the natural environment. The paper concludes by observing that the execution of this type of CNN, involving low-cost and reduced computing resources, are feasible for monitoring extensive natural areas. The use of CPS enables flexible and dynamic configuration and deployment of new CNN updates over remote IoT nodes.Multidisciplinary Digital Publishing Institute (MDPI)ZoologíaTecnología Electrónica2021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/111399https://doi.org/10.3390/s21113655reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésSensors, 21 (11), 3655.https://doi.org/10.3390/s21113655info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1113992026-06-17T12:51:07Z
dc.title.none.fl_str_mv Cyber-physical system for environmental monitoring based on deep learning
title Cyber-physical system for environmental monitoring based on deep learning
spellingShingle Cyber-physical system for environmental monitoring based on deep learning
Monedero Goicoechea, Iñigo Luis
Convolutional neural network
Cyber-physical systems
Deep learning
Internet of Things
Machine learning
Passive active monitoring
title_short Cyber-physical system for environmental monitoring based on deep learning
title_full Cyber-physical system for environmental monitoring based on deep learning
title_fullStr Cyber-physical system for environmental monitoring based on deep learning
title_full_unstemmed Cyber-physical system for environmental monitoring based on deep learning
title_sort Cyber-physical system for environmental monitoring based on deep learning
dc.creator.none.fl_str_mv Monedero Goicoechea, Iñigo Luis
Barbancho Concejero, Julio
Márquez, Rafael
Beltrán Gala, Juan Francisco
author Monedero Goicoechea, Iñigo Luis
author_facet Monedero Goicoechea, Iñigo Luis
Barbancho Concejero, Julio
Márquez, Rafael
Beltrán Gala, Juan Francisco
author_role author
author2 Barbancho Concejero, Julio
Márquez, Rafael
Beltrán Gala, Juan Francisco
author2_role author
author
author
dc.contributor.none.fl_str_mv Zoología
Tecnología Electrónica
dc.subject.none.fl_str_mv Convolutional neural network
Cyber-physical systems
Deep learning
Internet of Things
Machine learning
Passive active monitoring
topic Convolutional neural network
Cyber-physical systems
Deep learning
Internet of Things
Machine learning
Passive active monitoring
description Cyber-physical systems (CPS) constitute a promising paradigm that could fit various applications. Monitoring based on the Internet of Things (IoT) has become a research area with new challenges in which to extract valuable information. This paper proposes a deep learning classification sound system for execution over CPS. This system is based on convolutional neural networks (CNNs) and is focused on the different types of vocalization of two species of anurans. CNNs, in conjunction with the use of mel-spectrograms for sounds, are shown to be an adequate tool for the classification of environmental sounds. The classification results obtained are excellent (97.53% overall accuracy) and can be considered a very promising use of the system for classifying other biological acoustic targets as well as analyzing biodiversity indices in the natural environment. The paper concludes by observing that the execution of this type of CNN, involving low-cost and reduced computing resources, are feasible for monitoring extensive natural areas. The use of CPS enables flexible and dynamic configuration and deployment of new CNN updates over remote IoT nodes.
publishDate 2021
dc.date.none.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/111399
https://doi.org/10.3390/s21113655
url https://hdl.handle.net/11441/111399
https://doi.org/10.3390/s21113655
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Sensors, 21 (11), 3655.
https://doi.org/10.3390/s21113655
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407741770989568
score 15.301629

Registos relacionados