Blind Source Separation by Multiresolution Analysis using AMUSE Algorithm

Detalhes bibliográficos
Autor(a) principal: de Oliveira, Bruno Rodrigues
Data de Publicação: 2018
Outros Autores: Duarte, Marco Aparecido Queiroz, Vieira Filho, Jozué
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Multi-Science Journal
Texto Completo: https://periodicos.ifgoiano.edu.br/multiscience/article/view/106
Resumo: Algorithms for blind source separation have been extensively studied in the last years. This paper proposes the use of multiresolution analysis in three decomposition levels of the wavelet transform, such as a preprocessing step, and the AMUSE algorithm to separate the source signals in distinct levels of resolution. The results show that there is an improvement in the estimation of the signals and the of mixing matrix even in noisy environment if compared to the use of AMUSE only.
id IFGO-1_dc929f2e632d539881b6c8cb751a70c7
oai_identifier_str oai:ojs.emnuvens.com.br:article/106
network_acronym_str IFGO-1
network_name_str Multi-Science Journal
repository_id_str
spelling Blind Source Separation by Multiresolution Analysis using AMUSE AlgorithmAlgorithms for blind source separation have been extensively studied in the last years. This paper proposes the use of multiresolution analysis in three decomposition levels of the wavelet transform, such as a preprocessing step, and the AMUSE algorithm to separate the source signals in distinct levels of resolution. The results show that there is an improvement in the estimation of the signals and the of mixing matrix even in noisy environment if compared to the use of AMUSE only.Instituto Federal Goiano - Câmpus Urutaí2018-03-18info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.ifgoiano.edu.br/multiscience/article/view/10610.33837/msj.v1i3.106Multi-Science Journal; Vol. 1 No. 3 (2015); 40-45Multi-Science Journal; v. 1 n. 3 (2015); 40-452359-69022359-6902reponame:Multi-Science Journalinstname:Instituto Federal de Educação, Ciência e Tecnologia Goiano (IF Goiano)instacron:IFGOenghttps://periodicos.ifgoiano.edu.br/multiscience/article/view/106/84Copyright (c) 2017 Bruno Rodrigues de Oliveira, Marco Aparecido Queiroz Duarte, Jozué Vieira Filhoinfo:eu-repo/semantics/openAccessde Oliveira, Bruno RodriguesDuarte, Marco Aparecido QueirozVieira Filho, Jozué2018-03-18T10:17:38Zoai:ojs.emnuvens.com.br:article/106Revistahttps://periodicos.ifgoiano.edu.br/index.php/multisciencePUBhttps://periodicos.ifgoiano.edu.br/index.php/multiscience/oaiguilhermeifgoiano@gmail.com || multiscience@ifgoiano.edu.br || wesley.andrade@ifgoiano.edu.br2359-69022359-6902opendoar:2018-03-18T10:17:38Multi-Science Journal - Instituto Federal de Educação, Ciência e Tecnologia Goiano (IF Goiano)false
dc.title.none.fl_str_mv Blind Source Separation by Multiresolution Analysis using AMUSE Algorithm
title Blind Source Separation by Multiresolution Analysis using AMUSE Algorithm
spellingShingle Blind Source Separation by Multiresolution Analysis using AMUSE Algorithm
de Oliveira, Bruno Rodrigues
title_short Blind Source Separation by Multiresolution Analysis using AMUSE Algorithm
title_full Blind Source Separation by Multiresolution Analysis using AMUSE Algorithm
title_fullStr Blind Source Separation by Multiresolution Analysis using AMUSE Algorithm
title_full_unstemmed Blind Source Separation by Multiresolution Analysis using AMUSE Algorithm
title_sort Blind Source Separation by Multiresolution Analysis using AMUSE Algorithm
author de Oliveira, Bruno Rodrigues
author_facet de Oliveira, Bruno Rodrigues
Duarte, Marco Aparecido Queiroz
Vieira Filho, Jozué
author_role author
author2 Duarte, Marco Aparecido Queiroz
Vieira Filho, Jozué
author2_role author
author
dc.contributor.author.fl_str_mv de Oliveira, Bruno Rodrigues
Duarte, Marco Aparecido Queiroz
Vieira Filho, Jozué
description Algorithms for blind source separation have been extensively studied in the last years. This paper proposes the use of multiresolution analysis in three decomposition levels of the wavelet transform, such as a preprocessing step, and the AMUSE algorithm to separate the source signals in distinct levels of resolution. The results show that there is an improvement in the estimation of the signals and the of mixing matrix even in noisy environment if compared to the use of AMUSE only.
publishDate 2018
dc.date.none.fl_str_mv 2018-03-18
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://periodicos.ifgoiano.edu.br/multiscience/article/view/106
10.33837/msj.v1i3.106
url https://periodicos.ifgoiano.edu.br/multiscience/article/view/106
identifier_str_mv 10.33837/msj.v1i3.106
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://periodicos.ifgoiano.edu.br/multiscience/article/view/106/84
dc.rights.driver.fl_str_mv Copyright (c) 2017 Bruno Rodrigues de Oliveira, Marco Aparecido Queiroz Duarte, Jozué Vieira Filho
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2017 Bruno Rodrigues de Oliveira, Marco Aparecido Queiroz Duarte, Jozué Vieira Filho
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Instituto Federal Goiano - Câmpus Urutaí
publisher.none.fl_str_mv Instituto Federal Goiano - Câmpus Urutaí
dc.source.none.fl_str_mv Multi-Science Journal; Vol. 1 No. 3 (2015); 40-45
Multi-Science Journal; v. 1 n. 3 (2015); 40-45
2359-6902
2359-6902
reponame:Multi-Science Journal
instname:Instituto Federal de Educação, Ciência e Tecnologia Goiano (IF Goiano)
instacron:IFGO
instname_str Instituto Federal de Educação, Ciência e Tecnologia Goiano (IF Goiano)
instacron_str IFGO
institution IFGO
reponame_str Multi-Science Journal
collection Multi-Science Journal
repository.name.fl_str_mv Multi-Science Journal - Instituto Federal de Educação, Ciência e Tecnologia Goiano (IF Goiano)
repository.mail.fl_str_mv guilhermeifgoiano@gmail.com || multiscience@ifgoiano.edu.br || wesley.andrade@ifgoiano.edu.br
_version_ 1798325175278632960

Registros relacionados