Different neural networks approaches for identification of obstructive sleep apnea

Sarah Qasim Ali, Abdulnasir Hossen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Obstructive sleep apnea (OSA) is one of the most common breathing-related sleep disorders affecting individuals of different age groups, genders and origins. It is characterized by short-duration of cessations in breathing during sleep due to the collapse of the upper airway. The golden standard and reliable test for the detection of OSA is conducted by specialized physicians performing a polysomnographic sleep study. However, this test is time/labor consuming, expensive and cumbersome. In this paper, a non-invasive technique employing three different artificial neural networks to analyze spectral and statistical features of the Heart Rate Variability (HRV) signal to identify OSA subjects from normal control is investigated. The artificial networks include the single perceptron network, the feedforward network with back-propagation and the probabilistic neural network. The highest performance on MIT standard data is achieved by the feedforward network with back propagation using wavelet-based frequency domain features with specificity, sensitivity, and accuracy of 90%, 100% and 96.67%, respectively.

Original languageEnglish
Title of host publicationISCAIE 2018 - 2018 IEEE Symposium on Computer Applications and Industrial Electronics
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages281-284
Number of pages4
ISBN (Electronic)9781538635278
DOIs
Publication statusPublished - Jul 5 2018
Event2018 IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2018 - Penang Island, Malaysia
Duration: Apr 28 2018Apr 29 2018

Other

Other2018 IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2018
CountryMalaysia
CityPenang Island
Period4/28/184/29/18

Fingerprint

sleep
Sleep
respiration
Neural Networks
Neural networks
Feedforward Networks
Back Propagation
breathing
Backpropagation
Heart Rate Variability
Probabilistic Neural Network
heart rate
self organizing systems
physicians
labor
Perceptron
Specificity
Frequency Domain
Artificial Neural Network
Disorder

Keywords

  • ANN
  • HRV
  • OSA
  • Time-Domain features
  • Wavelet Packet Decomposition

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Computer Networks and Communications
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Control and Optimization
  • Instrumentation

Cite this

Ali, S. Q., & Hossen, A. (2018). Different neural networks approaches for identification of obstructive sleep apnea. In ISCAIE 2018 - 2018 IEEE Symposium on Computer Applications and Industrial Electronics (pp. 281-284). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAIE.2018.8405485

Different neural networks approaches for identification of obstructive sleep apnea. / Ali, Sarah Qasim; Hossen, Abdulnasir.

ISCAIE 2018 - 2018 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2018. p. 281-284.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ali, SQ & Hossen, A 2018, Different neural networks approaches for identification of obstructive sleep apnea. in ISCAIE 2018 - 2018 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., pp. 281-284, 2018 IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2018, Penang Island, Malaysia, 4/28/18. https://doi.org/10.1109/ISCAIE.2018.8405485
Ali SQ, Hossen A. Different neural networks approaches for identification of obstructive sleep apnea. In ISCAIE 2018 - 2018 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc. 2018. p. 281-284 https://doi.org/10.1109/ISCAIE.2018.8405485
Ali, Sarah Qasim ; Hossen, Abdulnasir. / Different neural networks approaches for identification of obstructive sleep apnea. ISCAIE 2018 - 2018 IEEE Symposium on Computer Applications and Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 281-284
@inproceedings{3a1b72ee48cc45829aa3c17eac1688e0,
title = "Different neural networks approaches for identification of obstructive sleep apnea",
abstract = "Obstructive sleep apnea (OSA) is one of the most common breathing-related sleep disorders affecting individuals of different age groups, genders and origins. It is characterized by short-duration of cessations in breathing during sleep due to the collapse of the upper airway. The golden standard and reliable test for the detection of OSA is conducted by specialized physicians performing a polysomnographic sleep study. However, this test is time/labor consuming, expensive and cumbersome. In this paper, a non-invasive technique employing three different artificial neural networks to analyze spectral and statistical features of the Heart Rate Variability (HRV) signal to identify OSA subjects from normal control is investigated. The artificial networks include the single perceptron network, the feedforward network with back-propagation and the probabilistic neural network. The highest performance on MIT standard data is achieved by the feedforward network with back propagation using wavelet-based frequency domain features with specificity, sensitivity, and accuracy of 90{\%}, 100{\%} and 96.67{\%}, respectively.",
keywords = "ANN, HRV, OSA, Time-Domain features, Wavelet Packet Decomposition",
author = "Ali, {Sarah Qasim} and Abdulnasir Hossen",
year = "2018",
month = "7",
day = "5",
doi = "10.1109/ISCAIE.2018.8405485",
language = "English",
pages = "281--284",
booktitle = "ISCAIE 2018 - 2018 IEEE Symposium on Computer Applications and Industrial Electronics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Different neural networks approaches for identification of obstructive sleep apnea

AU - Ali, Sarah Qasim

AU - Hossen, Abdulnasir

PY - 2018/7/5

Y1 - 2018/7/5

N2 - Obstructive sleep apnea (OSA) is one of the most common breathing-related sleep disorders affecting individuals of different age groups, genders and origins. It is characterized by short-duration of cessations in breathing during sleep due to the collapse of the upper airway. The golden standard and reliable test for the detection of OSA is conducted by specialized physicians performing a polysomnographic sleep study. However, this test is time/labor consuming, expensive and cumbersome. In this paper, a non-invasive technique employing three different artificial neural networks to analyze spectral and statistical features of the Heart Rate Variability (HRV) signal to identify OSA subjects from normal control is investigated. The artificial networks include the single perceptron network, the feedforward network with back-propagation and the probabilistic neural network. The highest performance on MIT standard data is achieved by the feedforward network with back propagation using wavelet-based frequency domain features with specificity, sensitivity, and accuracy of 90%, 100% and 96.67%, respectively.

AB - Obstructive sleep apnea (OSA) is one of the most common breathing-related sleep disorders affecting individuals of different age groups, genders and origins. It is characterized by short-duration of cessations in breathing during sleep due to the collapse of the upper airway. The golden standard and reliable test for the detection of OSA is conducted by specialized physicians performing a polysomnographic sleep study. However, this test is time/labor consuming, expensive and cumbersome. In this paper, a non-invasive technique employing three different artificial neural networks to analyze spectral and statistical features of the Heart Rate Variability (HRV) signal to identify OSA subjects from normal control is investigated. The artificial networks include the single perceptron network, the feedforward network with back-propagation and the probabilistic neural network. The highest performance on MIT standard data is achieved by the feedforward network with back propagation using wavelet-based frequency domain features with specificity, sensitivity, and accuracy of 90%, 100% and 96.67%, respectively.

KW - ANN

KW - HRV

KW - OSA

KW - Time-Domain features

KW - Wavelet Packet Decomposition

UR - http://www.scopus.com/inward/record.url?scp=85050690712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050690712&partnerID=8YFLogxK

U2 - 10.1109/ISCAIE.2018.8405485

DO - 10.1109/ISCAIE.2018.8405485

M3 - Conference contribution

AN - SCOPUS:85050690712

SP - 281

EP - 284

BT - ISCAIE 2018 - 2018 IEEE Symposium on Computer Applications and Industrial Electronics

PB - Institute of Electrical and Electronics Engineers Inc.

ER -