An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment

Artificial Intelligence of Things (AIoT) is an emerging area of interest, and this can be used to obtain knowledge and take better decisions in the same Internet of Things (IoT) devices. IoT data are prone to anomalies due to various factors such as malfunctioning of sensors, low-cost devices, etc....

Descripción completa

Detalles Bibliográficos
Autores: Hammad, Sahibzada Saadoon, Iskandaryan, Ditsuhi, Trilles, Sergio
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:España
Institución:Universidad de Barcelona
Repositorio:Dipòsit Digital de la UB
OAI Identifier:oai:diposit.ub.edu:2445/202605
Acceso en línea:https://hdl.handle.net/2445/202605
Access Level:acceso abierto
Palabra clave:Contaminació acústica
Ciutats intel·ligents
Noise pollution
Smart cities
id ES_722b20e93f70686c124f31e5ef13dcfa
oai_identifier_str oai:diposit.ub.edu:2445/202605
network_acronym_str ES
network_name_str España
repository_id_str
spelling An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environmentHammad, Sahibzada SaadoonIskandaryan, DitsuhiTrilles, SergioContaminació acústicaCiutats intel·ligentsNoise pollutionSmart citiesArtificial Intelligence of Things (AIoT) is an emerging area of interest, and this can be used to obtain knowledge and take better decisions in the same Internet of Things (IoT) devices. IoT data are prone to anomalies due to various factors such as malfunctioning of sensors, low-cost devices, etc. Following the AIoT paradigm, this work explores anomaly detection in IoT urban noise sensor networks using a Long Short-Term Memory Autoencoder. Two autoencoder models are trained using normal data from two different sensors in the sensor network and tested for the detection of two different types of anomalies, i.e. point anomalies and collective anomalies. The results in terms of accuracy of the two models are 99.99% and 99.34%. The trained model is quantised, converted to TensorFlow Lite format and deployed on the ESP32 microcontroller (MCU). The inference time on the microcontroller is 4 ms for both models, and the power consumption of the MCU is 0.2693 W & PLUSMN; 0.039 and 0.3268 W & PLUSMN; 0.015. Heap memory consumption during the execution of the program for sensors TA120-T246187 and TA120-T246189 is 528 bytes and 744 bytes respectively.Elsevier BV2023info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://hdl.handle.net/2445/202605Articles publicats en revistes (Institut d'lnvestigació Biomèdica de Bellvitge (IDIBELL))reponame:Dipòsit Digital de la UBinstname:Universidad de BarcelonaInglésReproducció del document publicat a: https://doi.org/10.1016/j.iot.2023.100848Internet of Things, 2023, vol. 23, p. 100848https://doi.org/10.1016/j.iot.2023.100848cc by (c) Hammad, Sahibzada Saadoon et al., 2023http://creativecommons.org/licenses/by/3.0/es/info:eu-repo/semantics/openAccessoai:diposit.ub.edu:2445/2026052026-05-27T06:46:51Z
dc.title.none.fl_str_mv An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment
title An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment
spellingShingle An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment
Hammad, Sahibzada Saadoon
Contaminació acústica
Ciutats intel·ligents
Noise pollution
Smart cities
title_short An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment
title_full An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment
title_fullStr An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment
title_full_unstemmed An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment
title_sort An unsupervised TinyML approach applied to the detection of urban noise anomalies under the smart cities environment
dc.creator.none.fl_str_mv Hammad, Sahibzada Saadoon
Iskandaryan, Ditsuhi
Trilles, Sergio
author Hammad, Sahibzada Saadoon
author_facet Hammad, Sahibzada Saadoon
Iskandaryan, Ditsuhi
Trilles, Sergio
author_role author
author2 Iskandaryan, Ditsuhi
Trilles, Sergio
author2_role author
author
dc.subject.none.fl_str_mv Contaminació acústica
Ciutats intel·ligents
Noise pollution
Smart cities
topic Contaminació acústica
Ciutats intel·ligents
Noise pollution
Smart cities
description Artificial Intelligence of Things (AIoT) is an emerging area of interest, and this can be used to obtain knowledge and take better decisions in the same Internet of Things (IoT) devices. IoT data are prone to anomalies due to various factors such as malfunctioning of sensors, low-cost devices, etc. Following the AIoT paradigm, this work explores anomaly detection in IoT urban noise sensor networks using a Long Short-Term Memory Autoencoder. Two autoencoder models are trained using normal data from two different sensors in the sensor network and tested for the detection of two different types of anomalies, i.e. point anomalies and collective anomalies. The results in terms of accuracy of the two models are 99.99% and 99.34%. The trained model is quantised, converted to TensorFlow Lite format and deployed on the ESP32 microcontroller (MCU). The inference time on the microcontroller is 4 ms for both models, and the power consumption of the MCU is 0.2693 W & PLUSMN; 0.039 and 0.3268 W & PLUSMN; 0.015. Heap memory consumption during the execution of the program for sensors TA120-T246187 and TA120-T246189 is 528 bytes and 744 bytes respectively.
publishDate 2023
dc.date.none.fl_str_mv 2023
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/2445/202605
url https://hdl.handle.net/2445/202605
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Reproducció del document publicat a: https://doi.org/10.1016/j.iot.2023.100848
Internet of Things, 2023, vol. 23, p. 100848
https://doi.org/10.1016/j.iot.2023.100848
dc.rights.none.fl_str_mv cc by (c) Hammad, Sahibzada Saadoon et al., 2023
http://creativecommons.org/licenses/by/3.0/es/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv cc by (c) Hammad, Sahibzada Saadoon et al., 2023
http://creativecommons.org/licenses/by/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier BV
publisher.none.fl_str_mv Elsevier BV
dc.source.none.fl_str_mv Articles publicats en revistes (Institut d'lnvestigació Biomèdica de Bellvitge (IDIBELL))
reponame:Dipòsit Digital de la UB
instname:Universidad de Barcelona
instname_str Universidad de Barcelona
reponame_str Dipòsit Digital de la UB
collection Dipòsit Digital de la UB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869410704748969984
score 15,301603

Similares en LA Referencia