Cepstrum Coefficients of the RR Series for the Detection of Obstructive Sleep Apnea Based on Different Classifiers

Autor:	Pedro J. Quintana-Morales, Antonio G. Ravelo-García, Iván Guerra-Moreno, Gabriel Juliá-Serdá, Juan L. Navarro-Mesa, Javier Navarro-Esteva, S. Martin-Gonzalez, Eduardo Hernández-Pérez
Předmět:	Series (mathematics) Computer science business.industry Speech recognition Detector Feature extraction Sleep apnea Pattern recognition Linear discriminant analysis medicine.disease Support vector machine Cepstrum medicine Preprocessor Artificial intelligence business
Zdroj:	ResearcherID Computer Aided Systems Theory-EUROCAST 2013 ISBN: 9783642538612 EUROCAST (2)
Popis:	Two automatic statistical methods for the classification of the obstructive sleep apnoea syndrome based on the cepstrum coefficients of the RR series obtained from the Electrocardiogram (ECG) are presented. We study the effect of working with Linear Discriminant Analysis (LDA) and compare its performance with a reference detector based on Support Vector Machines (SVM). These classifications methods require two previous stages: preprocessing and feature extraction. Firstly, R instants are detected previous to the feature extraction phase thanks to a preprocessing over the ECG. Secondly, Cepstrum Coefficients over the RR signal is applied to extract the relevant characteristics specially those related to the system modelled by the filter-type elements concentrated in the low time lag region.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ad7ab501db993993c0314093dab24c9 http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=ORCID&SrcApp=OrcidOrg&DestLinkType=FullRecord&DestApp=WOS_CPL&KeyUT=WOS:000378303900034&KeyUID=WOS:000378303900034 Zobrazit plný text záznamu