Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/77400
Campo DC Valoridioma
dc.contributor.authorMostafa, Sheikh Shanawazen_US
dc.contributor.authorMendonca, Fabioen_US
dc.contributor.authorRavelo García, Antonio Gabrielen_US
dc.contributor.authorJulia-Serda, Gabrielen_US
dc.contributor.authorMorgado-Dias, Fernandoen_US
dc.date.accessioned2021-02-01T08:47:35Z-
dc.date.available2021-02-01T08:47:35Z-
dc.date.issued2020en_US
dc.identifier.issn2169-3536en_US
dc.identifier.urihttp://hdl.handle.net/10553/77400-
dc.description.abstractObstructive sleep apnea (OSA) is a common sleep disorder characterized by interrupted breathing during sleep. Because of the cost, complexity, and accessibility issue related to polysomnography, the gold standard test for apnea detection, automation of the diagnostic test based on a simpler method is desired. Several signals can be used for apnea detection, such as air ow and electrocardiogram. However, the reduction of air ow normally leads to a decrease in the blood oxygen saturation level (SpO2). This signal is usually measured by a pulse oximeter, a sensor that is cheap, portable, and easy to assemble. Therefore, the SpO2 was chosen as the reference signal. Feature based classi ers with shallow neural networks have been developed to provide apnea detection using SpO2. However, two main issues arise, the need for feature creation and the selection of the more relevant features. Deep neural networks can solve these issues by employing featureless methods. Among multiple deep classi ers that have been developed, convolution neural networks (CNN) are gaining popularity. However, the selection of the CNN structure and hyperparameters are typically done by experts, where prior knowledge is essential. With these problems in mind, an algorithm for automatic structure selection and hyper parameterization of a one dimension CNN was developed to detect OSA events using only the SpO2 signal. Three different input sizes and databases were tested, and the best model achieved an average accuracy, sensitivity, and speci city of 94%, 92%, and 96%, respectively.en_US
dc.languageengen_US
dc.relationUID/EEA/50009/2019en_US
dc.relationM1420-01-0145-FEDER-000002en_US
dc.relation.ispartofIEEE Accessen_US
dc.sourceIEEE Access [ISSN 2169-3536], n. 8, p. 129586-129599en_US
dc.subject3307 Tecnología electrónicaen_US
dc.subject.otherBiomedical signal processingen_US
dc.subject.otherGenetic algorithmsen_US
dc.subject.otherMachine intelligenceen_US
dc.subject.otherMedical expert systemsen_US
dc.subject.otherPareto optimizationen_US
dc.subject.otherSleep apneaen_US
dc.titleMulti-Objective Hyperparameter Optimization of Convolutional Neural Network for Obstructive Sleep Apnea Detectionen_US
dc.typeinfo:eu-repo/semantics/articleen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/ACCESS.2020.3009149en_US
dc.investigacionIngeniería y Arquitecturaen_US
dc.type2Artículoen_US
dc.utils.revisionen_US
dc.identifier.ulpgcen_US
dc.contributor.buulpgcBU-TELen_US
dc.description.sjr0,587
dc.description.jcr3,367
dc.description.sjrqQ1
dc.description.jcrqQ2
dc.description.scieSCIE
item.grantfulltextopen-
item.fulltextCon texto completo-
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-
Colección:Artículos
Adobe PDF (3,07 MB)
Vista resumida

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.