Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/40327
DC FieldValueLanguage
dc.contributor.authorShanawaz Mostafa, Sheikhen_US
dc.contributor.authorMendonça, Fabioen_US
dc.contributor.authorMorgado-Dias, F.en_US
dc.contributor.authorRavelo García, Antonioen_US
dc.date.accessioned2018-06-13T10:36:38Z-
dc.date.available2018-06-13T10:36:38Z-
dc.date.issued2017en_US
dc.identifier.isbn9781479976775
dc.identifier.issn1562-5850en_US
dc.identifier.urihttp://hdl.handle.net/10553/40327-
dc.description.abstractIn a classical classification process, automatic sleep apnea detection involves creating and selecting the features, using prior knowledge, and apply them to a classifier. A different approach is applied in this paper, where a Deep Belief Network is used for feature extraction, without using domain-specific knowledge, and then the same network is used for classification of sleep apnea. The Deep Belief Network was created by stacking Restricted Boltzmann Machines. The first two layers are autoencoder type and the last layer is of soft-max type. The initial weights are calculated using unsupervised learning and, at the end, a supervised fine-tuning of the weights is performed. Two public databases, one with 8 subjects and other with 25 subjects, are tested using tenfold cross validation. The optimum number of hidden neurons of this problem is found using a search technique. The accuracy achieved from UCD database is 85.26\% and Apnea-ECG database is 97.64\%.en_US
dc.languageengen_US
dc.relation.ispartofProceedings - INESen_US
dc.sourceProceedings - INES [ISSN 1562-5850], 21st International Conference on Intelligent Engineering Systems (Larnaca, Cyprus), p. 000091-000096en_US
dc.subject33 Ciencias tecnológicasen_US
dc.subject.otherDeep belief netsen_US
dc.subject.otherDeep learningen_US
dc.subject.otherRestricted boltzmann machinesen_US
dc.subject.otherSleep apnea,en_US
dc.subject.otherUnsuperviseden_US
dc.subject.otherFeature learningen_US
dc.titleSpO2 based sleep apnea detection using deep learningen_US
dc.typeinfo:eu-repo/semantics/conferenceObjecten_US
dc.typeConferenceObjectes
dc.relation.conference21st IEEE International Conference on Intelligent Engineering Systems (INES)
dc.relation.conference21st IEEE International Conference on Intelligent Engineering Systems, INES 2017
dc.identifier.doi10.1109/INES.2017.8118534
dc.identifier.scopus85043512764
dc.identifier.isi000418333800015
dc.contributor.authorscopusid55489640900
dc.contributor.authorscopusid57195946416
dc.contributor.authorscopusid57200602527
dc.contributor.authorscopusid9634135600
dc.description.lastpage96-
dc.description.firstpage91-
dc.investigacionIngeniería y Arquitecturaen_US
dc.type2Actas de congresosen_US
dc.contributor.daisngid4069296
dc.contributor.daisngid6442981
dc.contributor.daisngid1189663
dc.contributor.daisngid1986395
dc.contributor.wosstandardWOS:Mostafa, SS
dc.contributor.wosstandardWOS:Mendonca, F
dc.contributor.wosstandardWOS:Morgado-Dias, F
dc.contributor.wosstandardWOS:Ravelo-Garcia, A
dc.date.coverdateNoviembre 2017
dc.identifier.conferenceidevents121074
dc.identifier.ulpgces
item.fulltextSin texto completo-
item.grantfulltextnone-
crisitem.author.deptGIR IDeTIC: División de Procesado Digital de Señales-
crisitem.author.deptIU para el Desarrollo Tecnológico y la Innovación-
crisitem.author.deptDepartamento de Señales y Comunicaciones-
crisitem.author.orcid0000-0002-8512-965X-
crisitem.author.parentorgIU para el Desarrollo Tecnológico y la Innovación-
crisitem.author.fullNameRavelo García, Antonio Gabriel-
crisitem.event.eventsstartdate20-10-2017-
crisitem.event.eventsstartdate20-10-2017-
crisitem.event.eventsenddate23-10-2017-
crisitem.event.eventsenddate23-10-2017-
Appears in Collections:Actas de congresos
Show simple item record

SCOPUSTM   
Citations

33
checked on Jun 26, 2022

WEB OF SCIENCETM
Citations

13
checked on Apr 25, 2021

Page view(s)

28
checked on Nov 27, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.