An improved ECG-derived respiration method using kernel principal component analysis

Recent studies show that principal component analysis (PCA) of heart beats generates well-performing ECG-derived respiratory signals (EDR). This study aims at improving the performance of EDR signals using kernel PCA (kPCA). Kernel PCA is a generalization of PCA where nonlinearities in the data are...

Full description

Autores:
Tipo de recurso:
Fecha de publicación:
2011
Institución:
Universidad del Rosario
Repositorio:
Repositorio EdocUR - U. Rosario
Idioma:
eng
OAI Identifier:
oai:repository.urosario.edu.co:10336/28434
Acceso en línea:
https://repository.urosario.edu.co/handle/10336/28434
Palabra clave:
Principal component analysis
Kernel
Electrocardiography
Correlation
Coherence
Sensors
Optimization
Rights
License
Restringido (Acceso a grupos específicos)
id EDOCUR2_97d11a7957260fabf94187f13c3cd5a8
oai_identifier_str oai:repository.urosario.edu.co:10336/28434
network_acronym_str EDOCUR2
network_name_str Repositorio EdocUR - U. Rosario
repository_id_str
spelling 1413951260026c827fb-524d-4c98-829a-5c9a9c9c6127600373c77e3-5093-43fd-831b-0db88cefa50d6007f4da012-2e74-4a5d-b3d1-6e03864b76ef6002020-08-28T15:48:11Z2020-08-28T15:48:11Z2011-09-182011Recent studies show that principal component analysis (PCA) of heart beats generates well-performing ECG-derived respiratory signals (EDR). This study aims at improving the performance of EDR signals using kernel PCA (kPCA). Kernel PCA is a generalization of PCA where nonlinearities in the data are taken into account for the decomposition. The performance of PCA and kPCA is evaluated by comparing the EDR signals to the reference respiratory signal. Correlation coefficients of 0.630 ± 0.189 and 0.675 ± 0.163, and magnitude squared coherence coefficients at respiratory frequency of 0.819 ± 0.229 and 0.894 ± 0.139 were obtained for PCA and kPCA respectively. The Wilcoxon signed rank test showed statistically significantly higher coefficients for kPCA than for PCA for both the correlation (p = 0.0257) and coherence (p = 0.0030) coefficients. To conclude, kPCA proves to outperform PCA in the extraction of a respiratory signal from single lead ECGs.application/pdfISSN: 0276-6574EISSN: 2325-8853https://repository.urosario.edu.co/handle/10336/28434engEngineering in Medicine and Biology SocietyComputing in CardiologyComputing in Cardiology,ISSN: 0276-6574; EISSN: 2325-8853 (2011)https://ieeexplore.ieee.org/abstract/document/6164498https://search-ebscohost-com.ez.urosario.edu.co/login.aspx?direct=true&AuthType=ip&db=edseee&AN=edseee.6164498&lang=es&site=eds-live&scope=siteRestringido (Acceso a grupos específicos)http://purl.org/coar/access_right/c_16ecComputing in Cardiologyinstname:Universidad del Rosarioreponame:Repositorio Institucional EdocURPrincipal component analysisKernelElectrocardiographyCorrelationCoherenceSensorsOptimizationAn improved ECG-derived respiration method using kernel principal component analysisUn método mejorado de respiración derivado de ECG que utiliza análisis de componentes principales del núcleoarticleArtículohttp://purl.org/coar/version/c_970fb48d4fbd8a85http://purl.org/coar/resource_type/c_6501Caicedo Dorado, AlexanderVaron, CarolinaVan Huffel, SabineWidjaja, Devy10336/28434oai:repository.urosario.edu.co:10336/284342022-10-06 08:49:21.798https://repository.urosario.edu.coRepositorio institucional EdocURedocur@urosario.edu.co
dc.title.spa.fl_str_mv An improved ECG-derived respiration method using kernel principal component analysis
dc.title.TranslatedTitle.spa.fl_str_mv Un método mejorado de respiración derivado de ECG que utiliza análisis de componentes principales del núcleo
title An improved ECG-derived respiration method using kernel principal component analysis
spellingShingle An improved ECG-derived respiration method using kernel principal component analysis
Principal component analysis
Kernel
Electrocardiography
Correlation
Coherence
Sensors
Optimization
title_short An improved ECG-derived respiration method using kernel principal component analysis
title_full An improved ECG-derived respiration method using kernel principal component analysis
title_fullStr An improved ECG-derived respiration method using kernel principal component analysis
title_full_unstemmed An improved ECG-derived respiration method using kernel principal component analysis
title_sort An improved ECG-derived respiration method using kernel principal component analysis
dc.subject.keyword.spa.fl_str_mv Principal component analysis
Kernel
Electrocardiography
Correlation
Coherence
Sensors
Optimization
topic Principal component analysis
Kernel
Electrocardiography
Correlation
Coherence
Sensors
Optimization
description Recent studies show that principal component analysis (PCA) of heart beats generates well-performing ECG-derived respiratory signals (EDR). This study aims at improving the performance of EDR signals using kernel PCA (kPCA). Kernel PCA is a generalization of PCA where nonlinearities in the data are taken into account for the decomposition. The performance of PCA and kPCA is evaluated by comparing the EDR signals to the reference respiratory signal. Correlation coefficients of 0.630 ± 0.189 and 0.675 ± 0.163, and magnitude squared coherence coefficients at respiratory frequency of 0.819 ± 0.229 and 0.894 ± 0.139 were obtained for PCA and kPCA respectively. The Wilcoxon signed rank test showed statistically significantly higher coefficients for kPCA than for PCA for both the correlation (p = 0.0257) and coherence (p = 0.0030) coefficients. To conclude, kPCA proves to outperform PCA in the extraction of a respiratory signal from single lead ECGs.
publishDate 2011
dc.date.created.spa.fl_str_mv 2011-09-18
dc.date.issued.none.fl_str_mv 2011
dc.date.accessioned.none.fl_str_mv 2020-08-28T15:48:11Z
dc.date.available.none.fl_str_mv 2020-08-28T15:48:11Z
dc.type.eng.fl_str_mv article
dc.type.coarversion.fl_str_mv http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.coar.fl_str_mv http://purl.org/coar/resource_type/c_6501
dc.type.spa.spa.fl_str_mv Artículo
dc.identifier.issn.none.fl_str_mv ISSN: 0276-6574
EISSN: 2325-8853
dc.identifier.uri.none.fl_str_mv https://repository.urosario.edu.co/handle/10336/28434
identifier_str_mv ISSN: 0276-6574
EISSN: 2325-8853
url https://repository.urosario.edu.co/handle/10336/28434
dc.language.iso.spa.fl_str_mv eng
language eng
dc.relation.citationTitle.none.fl_str_mv Computing in Cardiology
dc.relation.ispartof.spa.fl_str_mv Computing in Cardiology,ISSN: 0276-6574; EISSN: 2325-8853 (2011)
dc.relation.uri.spa.fl_str_mv https://ieeexplore.ieee.org/abstract/document/6164498
dc.relation.uri.none.fl_str_mv https://search-ebscohost-com.ez.urosario.edu.co/login.aspx?direct=true&AuthType=ip&db=edseee&AN=edseee.6164498&lang=es&site=eds-live&scope=site
dc.rights.coar.fl_str_mv http://purl.org/coar/access_right/c_16ec
dc.rights.acceso.spa.fl_str_mv Restringido (Acceso a grupos específicos)
rights_invalid_str_mv Restringido (Acceso a grupos específicos)
http://purl.org/coar/access_right/c_16ec
dc.format.mimetype.none.fl_str_mv application/pdf
dc.publisher.spa.fl_str_mv Engineering in Medicine and Biology Society
dc.source.spa.fl_str_mv Computing in Cardiology
institution Universidad del Rosario
dc.source.instname.none.fl_str_mv instname:Universidad del Rosario
dc.source.reponame.none.fl_str_mv reponame:Repositorio Institucional EdocUR
repository.name.fl_str_mv Repositorio institucional EdocUR
repository.mail.fl_str_mv edocur@urosario.edu.co
_version_ 1814167610900611072