Multilabel Acoustic Event Classification Using Real-World Urban Data and Physical Redundancy of Sensors

Many people living in urban environments nowadays are overexposed to noise, which results in adverse effects on their health. Thus, urban sound monitoring has emerged as a powerful tool that might enable public administrations to automatically identify and quantify noise pollution. Therefore, identi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ester Vidaña-Vila, Joan Navarro, Dan Stowell, Rosa Ma Alsina-Pagès
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	acoustic event classification urban sound monitoring multilabel classification deep neural networks physical redundancy distributed computing Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/8eff3f85faf24bcfa251563fc711d75b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8eff3f85faf24bcfa251563fc711d75b
record_format	dspace
spelling	oai:doaj.org-article:8eff3f85faf24bcfa251563fc711d75b2021-11-25T18:56:42ZMultilabel Acoustic Event Classification Using Real-World Urban Data and Physical Redundancy of Sensors10.3390/s212274701424-8220https://doaj.org/article/8eff3f85faf24bcfa251563fc711d75b2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7470https://doaj.org/toc/1424-8220Many people living in urban environments nowadays are overexposed to noise, which results in adverse effects on their health. Thus, urban sound monitoring has emerged as a powerful tool that might enable public administrations to automatically identify and quantify noise pollution. Therefore, identifying multiple and simultaneous acoustic sources in these environments in a reliable and cost-effective way has emerged as a hot research topic. The purpose of this paper is to propose a two-stage classifier able to identify, in real time, a set of up to 21 urban acoustic events that may occur simultaneously (i.e., multilabel), taking advantage of physical redundancy in acoustic sensors from a wireless acoustic sensors network. The first stage of the proposed system consists of a multilabel deep neural network that makes a classification for each 4-s window. The second stage intelligently aggregates the classification results from the first stage of four neighboring nodes to determine the final classification result. Conducted experiments with real-world data and up to three different computing devices show that the system is able to provide classification results in less than 1 s and that it has good performance when classifying the most common events from the dataset. The results of this research may help civic organisations to obtain actionable noise monitoring information from automatic systems.Ester Vidaña-VilaJoan NavarroDan StowellRosa Ma Alsina-PagèsMDPI AGarticleacoustic event classificationurban sound monitoringmultilabel classificationdeep neural networksphysical redundancydistributed computingChemical technologyTP1-1185ENSensors, Vol 21, Iss 7470, p 7470 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	acoustic event classification urban sound monitoring multilabel classification deep neural networks physical redundancy distributed computing Chemical technology TP1-1185
spellingShingle	acoustic event classification urban sound monitoring multilabel classification deep neural networks physical redundancy distributed computing Chemical technology TP1-1185 Ester Vidaña-Vila Joan Navarro Dan Stowell Rosa Ma Alsina-Pagès Multilabel Acoustic Event Classification Using Real-World Urban Data and Physical Redundancy of Sensors
description	Many people living in urban environments nowadays are overexposed to noise, which results in adverse effects on their health. Thus, urban sound monitoring has emerged as a powerful tool that might enable public administrations to automatically identify and quantify noise pollution. Therefore, identifying multiple and simultaneous acoustic sources in these environments in a reliable and cost-effective way has emerged as a hot research topic. The purpose of this paper is to propose a two-stage classifier able to identify, in real time, a set of up to 21 urban acoustic events that may occur simultaneously (i.e., multilabel), taking advantage of physical redundancy in acoustic sensors from a wireless acoustic sensors network. The first stage of the proposed system consists of a multilabel deep neural network that makes a classification for each 4-s window. The second stage intelligently aggregates the classification results from the first stage of four neighboring nodes to determine the final classification result. Conducted experiments with real-world data and up to three different computing devices show that the system is able to provide classification results in less than 1 s and that it has good performance when classifying the most common events from the dataset. The results of this research may help civic organisations to obtain actionable noise monitoring information from automatic systems.
format	article
author	Ester Vidaña-Vila Joan Navarro Dan Stowell Rosa Ma Alsina-Pagès
author_facet	Ester Vidaña-Vila Joan Navarro Dan Stowell Rosa Ma Alsina-Pagès
author_sort	Ester Vidaña-Vila
title	Multilabel Acoustic Event Classification Using Real-World Urban Data and Physical Redundancy of Sensors
title_short	Multilabel Acoustic Event Classification Using Real-World Urban Data and Physical Redundancy of Sensors
title_full	Multilabel Acoustic Event Classification Using Real-World Urban Data and Physical Redundancy of Sensors
title_fullStr	Multilabel Acoustic Event Classification Using Real-World Urban Data and Physical Redundancy of Sensors
title_full_unstemmed	Multilabel Acoustic Event Classification Using Real-World Urban Data and Physical Redundancy of Sensors
title_sort	multilabel acoustic event classification using real-world urban data and physical redundancy of sensors
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8eff3f85faf24bcfa251563fc711d75b
work_keys_str_mv	AT estervidanavila multilabelacousticeventclassificationusingrealworldurbandataandphysicalredundancyofsensors AT joannavarro multilabelacousticeventclassificationusingrealworldurbandataandphysicalredundancyofsensors AT danstowell multilabelacousticeventclassificationusingrealworldurbandataandphysicalredundancyofsensors AT rosamaalsinapages multilabelacousticeventclassificationusingrealworldurbandataandphysicalredundancyofsensors
_version_	1718410539345903616

Multilabel Acoustic Event Classification Using Real-World Urban Data and Physical Redundancy of Sensors

Ejemplares similares