Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision tree

Detalhes bibliográficos
Autor(a) principal: Gerhardt, Günther Johannes Lewczuk
Data de Publicação: 2014
Outros Autores: Lemke, Ney [UNESP], Carvalho, Diego Zaquera, Santa-Helena, Emerson Luis de, Schönwald, Suzana Veiga, Dellagustin, Guilherme, Rybarczyk Filho, José Luiz [UNESP]
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.18226/23185279.v2iss1p15
http://hdl.handle.net/11449/140812
Resumo: In this study, Matching Pursuit (MP) procedure is applied to the detection and analysis of EEG sleep spindles in patients evaluated for suspected OSAS. Elements having the frequency of EEG sleep spindles are selected from different dictionary sizes, with and without a frequency modulation function (chirp) for signal description. This procedure was done with high computational cost in order to find best parameters for real EEG data description. At the end we used the atom parameters as input for a decision tree-based classifier, making possible to obtain a classification according to apnea-hypopnea index group and allowing to see how atom parameters such as frequency and amplitude are affected by the presence of sleep apnea.
id UNSP_dbe942ed9b15e4c1ccad21a443e86601
oai_identifier_str oai:repositorio.unesp.br:11449/140812
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision treeEEGSignal analysisMatching pursuitObstructive apneaMachine learningDecision treeIn this study, Matching Pursuit (MP) procedure is applied to the detection and analysis of EEG sleep spindles in patients evaluated for suspected OSAS. Elements having the frequency of EEG sleep spindles are selected from different dictionary sizes, with and without a frequency modulation function (chirp) for signal description. This procedure was done with high computational cost in order to find best parameters for real EEG data description. At the end we used the atom parameters as input for a decision tree-based classifier, making possible to obtain a classification according to apnea-hypopnea index group and allowing to see how atom parameters such as frequency and amplitude are affected by the presence of sleep apnea.Universidade de Caxias do Sul (UCS), Caxias do Sul, RS, BrasilUniversidade Estadual Paulista Júlio de Mesquita Filho (UNESP), Instituto de Biociências (IBB), Departamento de Física e Biofísica, Botucatu, SP, BrasilUniversidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS, BrasilUniversidade Federal de Sergipe (UFS), São Cristóvão, SE, BrasilUniversidade Estadual Paulista Júlio de Mesquita Filho (UNESP), Instituto de Biociências (IBB), Departamento de Física e Biofísica, Botucatu, SP, BrasilUniversidade de Caxias do Sul (UCS)Universidade Estadual Paulista (Unesp)Universidade Federal do Rio Grande do Sul (UFRGS)Universidade Federal de Sergipe (UFS)Gerhardt, Günther Johannes LewczukLemke, Ney [UNESP]Carvalho, Diego ZaqueraSanta-Helena, Emerson Luis deSchönwald, Suzana VeigaDellagustin, GuilhermeRybarczyk Filho, José Luiz [UNESP]2016-07-07T12:35:32Z2016-07-07T12:35:32Z2014info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article15-18application/pdfhttp://dx.doi.org/10.18226/23185279.v2iss1p15Scientia Cum Industria, v. 2, n. 1, p. 15-18, 2014.2318-5279http://hdl.handle.net/11449/14081210.18226/23185279.v2iss1p15ISSN2318-5279-2014-02-01-15-18.pdf7977035910952141Currículo Lattesreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengScientia Cum Industriainfo:eu-repo/semantics/openAccess2023-11-03T06:08:45Zoai:repositorio.unesp.br:11449/140812Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:47:42.691255Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision tree
title Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision tree
spellingShingle Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision tree
Gerhardt, Günther Johannes Lewczuk
EEG
Signal analysis
Matching pursuit
Obstructive apnea
Machine learning
Decision tree
title_short Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision tree
title_full Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision tree
title_fullStr Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision tree
title_full_unstemmed Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision tree
title_sort Analysis of EEG sleep spindle parameters from apnea patients using massive computing and decision tree
author Gerhardt, Günther Johannes Lewczuk
author_facet Gerhardt, Günther Johannes Lewczuk
Lemke, Ney [UNESP]
Carvalho, Diego Zaquera
Santa-Helena, Emerson Luis de
Schönwald, Suzana Veiga
Dellagustin, Guilherme
Rybarczyk Filho, José Luiz [UNESP]
author_role author
author2 Lemke, Ney [UNESP]
Carvalho, Diego Zaquera
Santa-Helena, Emerson Luis de
Schönwald, Suzana Veiga
Dellagustin, Guilherme
Rybarczyk Filho, José Luiz [UNESP]
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade de Caxias do Sul (UCS)
Universidade Estadual Paulista (Unesp)
Universidade Federal do Rio Grande do Sul (UFRGS)
Universidade Federal de Sergipe (UFS)
dc.contributor.author.fl_str_mv Gerhardt, Günther Johannes Lewczuk
Lemke, Ney [UNESP]
Carvalho, Diego Zaquera
Santa-Helena, Emerson Luis de
Schönwald, Suzana Veiga
Dellagustin, Guilherme
Rybarczyk Filho, José Luiz [UNESP]
dc.subject.por.fl_str_mv EEG
Signal analysis
Matching pursuit
Obstructive apnea
Machine learning
Decision tree
topic EEG
Signal analysis
Matching pursuit
Obstructive apnea
Machine learning
Decision tree
description In this study, Matching Pursuit (MP) procedure is applied to the detection and analysis of EEG sleep spindles in patients evaluated for suspected OSAS. Elements having the frequency of EEG sleep spindles are selected from different dictionary sizes, with and without a frequency modulation function (chirp) for signal description. This procedure was done with high computational cost in order to find best parameters for real EEG data description. At the end we used the atom parameters as input for a decision tree-based classifier, making possible to obtain a classification according to apnea-hypopnea index group and allowing to see how atom parameters such as frequency and amplitude are affected by the presence of sleep apnea.
publishDate 2014
dc.date.none.fl_str_mv 2014
2016-07-07T12:35:32Z
2016-07-07T12:35:32Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.18226/23185279.v2iss1p15
Scientia Cum Industria, v. 2, n. 1, p. 15-18, 2014.
2318-5279
http://hdl.handle.net/11449/140812
10.18226/23185279.v2iss1p15
ISSN2318-5279-2014-02-01-15-18.pdf
7977035910952141
url http://dx.doi.org/10.18226/23185279.v2iss1p15
http://hdl.handle.net/11449/140812
identifier_str_mv Scientia Cum Industria, v. 2, n. 1, p. 15-18, 2014.
2318-5279
10.18226/23185279.v2iss1p15
ISSN2318-5279-2014-02-01-15-18.pdf
7977035910952141
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Scientia Cum Industria
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 15-18
application/pdf
dc.source.none.fl_str_mv Currículo Lattes
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808128703064965120

Registros relacionados