Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/48818
Title: Detection of obstructive sleep apnoea using dynamic filter-banked features
Authors: Martínez-Vargas, J. D.
Sepulveda-Cano, L. M.
Travieso-Gonzalez, C. 
Castellanos-Dominguez, G. 
UNESCO Clasification: 3314 Tecnología médica
Keywords: Obstructive sleep apnea
Heart rate variability
Dynamic filter-banked features
Spectral splitting
Issue Date: 2012
Publisher: 0957-4174
Journal: Expert Systems with Applications 
Abstract: There is a need for developing simple signal processing algorithms for less costly, reliable and noninvasive Obstructive Sleep Apnoea (USA) diagnosing. One of the promising directions is to provide the USA analysis based on the heart rate variability (HRV), which clearly shows a non-stationary behavior. So, a feature extraction approach, being capable of capturing the dynamic heart rate information and suitable for USA detection, remains an open issue. Grounded on discriminating capability of frequency bands of HRV activity between normal and USA patients, features can be extracted. However, some HRV normal spectrograms resemble like pathological ones, and vice versa: so, prior to extract the feature set, the energy spatial contribution contained in each subUband should be clarified. This paper presents a methodology for USA detection based on a set of short-time feature banked features that are extracted from the spectrogram of the HRV time series. The methodology introduces the spectral splitting scheme, which searches for spectral components with alike stochastic behavior improving the USA detection accuracy. Two different splitting approaches are considered (heuristic and relevance-based); both of them performing minute-by-minute classification comparable with other outcomes that are reported in literature, but avoiding more complex methods or more computed features. For validation purposes, the methodology is tested on 1-min HRV-segments estimated from 50 Physionet database recordings. Using a parallel combining k-nn classifier, the assessed dynamic feature set reaches as much as 80% value of accuracy, for both considered approaches of spectral splitting. Attained results can be oriented in research focused on finding alternative methods used for less costly and noninvasive USA diagnosing with the additional benefit of easier clinical interpretation of HRV-derived parameters.
URI: http://hdl.handle.net/10553/48818
ISSN: 0957-4174
DOI: 10.1016/j.eswa.2012.02.043
Source: Expert Systems with Applications[ISSN 0957-4174],v. 39, p. 9118-9128
Appears in Collections:Artículos
Thumbnail
Adobe PDF (1,34 MB)
Show full item record

SCOPUSTM   
Citations

13
checked on Jul 25, 2021

WEB OF SCIENCETM
Citations

8
checked on Jul 25, 2021

Page view(s)

11
checked on Jul 24, 2021

Download(s)

18
checked on Jul 24, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



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