A novel wheezing detection approach based on constrained non-negative matrix factorization

The early wheezing detection is still a challenging task in biomedical signal processing because the presence of wheeze sounds often indicate respiratory diseases from airway obstructions. Currently, most of the first clinical examinations to detect any airway obstructions are carried out using ausc...

Descripción completa

Detalles Bibliográficos
Autores: Torre-Cruz, Juan, Cañadas-Quesada, Francisco Jesús, Carabias-Orti, Julio José, Vera-Candeas, Pedro, Ruiz-Reyes, Nicolás
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2019
País:España
Institución:Universidad de Jaén
Repositorio:RUJA. Repositorio Institucional de la Producción Científica de la Universidad de Jaén
OAI Identifier:oai:ruja.ujaen.es:10953/2189
Acceso en línea:https://hdl.handle.net/10953/2189
Access Level:acceso abierto
Palabra clave:Detection
on-negative matrix factorization (NMF)
Divergence
Wheezing
621.39
id ES_37a9a02e9cf6c211eb7e7b02bdc832cd
oai_identifier_str oai:ruja.ujaen.es:10953/2189
network_acronym_str ES
network_name_str España
repository_id_str
spelling A novel wheezing detection approach based on constrained non-negative matrix factorizationTorre-Cruz, JuanCañadas-Quesada, Francisco JesúsCarabias-Orti, Julio JoséVera-Candeas, PedroRuiz-Reyes, NicolásDetectionon-negative matrix factorization (NMF)DivergenceWheezing621.39The early wheezing detection is still a challenging task in biomedical signal processing because the presence of wheeze sounds often indicate respiratory diseases from airway obstructions. Currently, most of the first clinical examinations to detect any airway obstructions are carried out using auscultation. However, a high percentage of diagnoses are misdiagnosed since they are highly dependent on the physician’s training in the wheezing detection, especially in noisy environments in which weak wheeze sounds can be masked by louder respiratory sounds. In this work, we propose a novel wheezing detection approach, based on Constrained Non-negative Matrix Factorization, that uses two-stage cascade: separation and detection. The novelty of the separation stage is to model wheeze and respiratory sounds as reliably as possible that they can be observed in the nature incorporating constraints (sparseness and smoothness) into the NMF factorization. Once the estimated wheezing and respiratory signal are obtained from the separation stage, the detection contribution is based on the use of the Kullback-Leibler divergence to discriminate between wheezing and respiratory areas. The experiments have been conducted using three different datasets composed of healthy or unhealthy patients. First, an optimization process is applied to obtain the optimal parameters of the separation stage. Finally, the performance of the wheezing detection of the proposed method is evaluated taking into account other state-of-the-art methods. Experimental results report that i) the proposed method outperforms recent state-of-the-art wheezing detection approaches showing a robust wheezing detection performance even evaluating noisy environments and ii) the ability of the proposal to reliably detect healthy patients.This work was supported by the Spanish Ministry of Economy and Competitiveness under Project TEC2015-67387-C4-2-R.Elsevier202420242019info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://hdl.handle.net/10953/2189reponame:RUJA. Repositorio Institucional de la Producción Científica de la Universidad de Jaéninstname:Universidad de JaénInglésApplied Acoustics, Volume 148, 2019, Pages 276-288CC0 1.0 Universalhttp://creativecommons.org/publicdomain/zero/1.0/info:eu-repo/semantics/openAccessoai:ruja.ujaen.es:10953/21892026-06-24T12:41:07Z
dc.title.none.fl_str_mv A novel wheezing detection approach based on constrained non-negative matrix factorization
title A novel wheezing detection approach based on constrained non-negative matrix factorization
spellingShingle A novel wheezing detection approach based on constrained non-negative matrix factorization
Torre-Cruz, Juan
Detection
on-negative matrix factorization (NMF)
Divergence
Wheezing
621.39
title_short A novel wheezing detection approach based on constrained non-negative matrix factorization
title_full A novel wheezing detection approach based on constrained non-negative matrix factorization
title_fullStr A novel wheezing detection approach based on constrained non-negative matrix factorization
title_full_unstemmed A novel wheezing detection approach based on constrained non-negative matrix factorization
title_sort A novel wheezing detection approach based on constrained non-negative matrix factorization
dc.creator.none.fl_str_mv Torre-Cruz, Juan
Cañadas-Quesada, Francisco Jesús
Carabias-Orti, Julio José
Vera-Candeas, Pedro
Ruiz-Reyes, Nicolás
author Torre-Cruz, Juan
author_facet Torre-Cruz, Juan
Cañadas-Quesada, Francisco Jesús
Carabias-Orti, Julio José
Vera-Candeas, Pedro
Ruiz-Reyes, Nicolás
author_role author
author2 Cañadas-Quesada, Francisco Jesús
Carabias-Orti, Julio José
Vera-Candeas, Pedro
Ruiz-Reyes, Nicolás
author2_role author
author
author
author
dc.subject.none.fl_str_mv Detection
on-negative matrix factorization (NMF)
Divergence
Wheezing
621.39
topic Detection
on-negative matrix factorization (NMF)
Divergence
Wheezing
621.39
description The early wheezing detection is still a challenging task in biomedical signal processing because the presence of wheeze sounds often indicate respiratory diseases from airway obstructions. Currently, most of the first clinical examinations to detect any airway obstructions are carried out using auscultation. However, a high percentage of diagnoses are misdiagnosed since they are highly dependent on the physician’s training in the wheezing detection, especially in noisy environments in which weak wheeze sounds can be masked by louder respiratory sounds. In this work, we propose a novel wheezing detection approach, based on Constrained Non-negative Matrix Factorization, that uses two-stage cascade: separation and detection. The novelty of the separation stage is to model wheeze and respiratory sounds as reliably as possible that they can be observed in the nature incorporating constraints (sparseness and smoothness) into the NMF factorization. Once the estimated wheezing and respiratory signal are obtained from the separation stage, the detection contribution is based on the use of the Kullback-Leibler divergence to discriminate between wheezing and respiratory areas. The experiments have been conducted using three different datasets composed of healthy or unhealthy patients. First, an optimization process is applied to obtain the optimal parameters of the separation stage. Finally, the performance of the wheezing detection of the proposed method is evaluated taking into account other state-of-the-art methods. Experimental results report that i) the proposed method outperforms recent state-of-the-art wheezing detection approaches showing a robust wheezing detection performance even evaluating noisy environments and ii) the ability of the proposal to reliably detect healthy patients.
publishDate 2019
dc.date.none.fl_str_mv 2019
2024
2024
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/10953/2189
url https://hdl.handle.net/10953/2189
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Applied Acoustics, Volume 148, 2019, Pages 276-288
dc.rights.none.fl_str_mv CC0 1.0 Universal
http://creativecommons.org/publicdomain/zero/1.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv CC0 1.0 Universal
http://creativecommons.org/publicdomain/zero/1.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:RUJA. Repositorio Institucional de la Producción Científica de la Universidad de Jaén
instname:Universidad de Jaén
instname_str Universidad de Jaén
reponame_str RUJA. Repositorio Institucional de la Producción Científica de la Universidad de Jaén
collection RUJA. Repositorio Institucional de la Producción Científica de la Universidad de Jaén
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869406051504226304
score 15,81155

Similares en LA Referencia