A neural network technique for feature selection and identification of obstructive sleep apnea

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

1 Citation (Scopus)

Abstract

A novel identification method of Obstructive Sleep Apnea from normal controls is presented in this paper. The method uses the approximate power spectral density of heart rate variability, which is estimated using a soft-decision wavelet-based decomposition in a combination with a neural network. The neural network is used for two purposes: to select the optimum frequency bands that can be used for identification during the feature extraction step, and to identify the data during the feature matching step. Two sets of data, training set and test set, which are downloaded from the MIT-data bases, are used in this work. The training set, which consists of 20 obstructive sleep apnea subjects and 10 normal subjects, is used to train the neural network of type feed-forward back-propagation. The test set, which consists also of 20 obstructive sleep apnea and 10 normal subjects is used to test the performance of the identification system. A best identification efficiency of 93.33% has been obtained in this work using three inputs only.

Original languageEnglish
Title of host publicationProceedings of the 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013
PublisherIEEE Computer Society
Pages182-186
Number of pages5
DOIs
Publication statusPublished - 2013
Event2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013 - Hangzhou, China
Duration: Dec 16 2013Dec 18 2013

Other

Other2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013
CountryChina
CityHangzhou
Period12/16/1312/18/13

Fingerprint

Feature extraction
Neural networks
Identification (control systems)
Power spectral density
Backpropagation
Frequency bands
Decomposition
Sleep

Keywords

  • Artificial Neural Networks
  • Feature Selection
  • Identification
  • Obstructive Sleep Apnea
  • Power Spectral Density
  • Soft-Decision Wavelet-Decomposition

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Hossen, A. (2013). A neural network technique for feature selection and identification of obstructive sleep apnea. In Proceedings of the 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013 (pp. 182-186). [6746930] IEEE Computer Society. https://doi.org/10.1109/BMEI.2013.6746930

A neural network technique for feature selection and identification of obstructive sleep apnea. / Hossen, Abdulnasir.

Proceedings of the 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013. IEEE Computer Society, 2013. p. 182-186 6746930.

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

Hossen, A 2013, A neural network technique for feature selection and identification of obstructive sleep apnea. in Proceedings of the 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013., 6746930, IEEE Computer Society, pp. 182-186, 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013, Hangzhou, China, 12/16/13. https://doi.org/10.1109/BMEI.2013.6746930
Hossen A. A neural network technique for feature selection and identification of obstructive sleep apnea. In Proceedings of the 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013. IEEE Computer Society. 2013. p. 182-186. 6746930 https://doi.org/10.1109/BMEI.2013.6746930
Hossen, Abdulnasir. / A neural network technique for feature selection and identification of obstructive sleep apnea. Proceedings of the 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013. IEEE Computer Society, 2013. pp. 182-186
@inproceedings{4e87392c98324d8c98614ea51131f24b,
title = "A neural network technique for feature selection and identification of obstructive sleep apnea",
abstract = "A novel identification method of Obstructive Sleep Apnea from normal controls is presented in this paper. The method uses the approximate power spectral density of heart rate variability, which is estimated using a soft-decision wavelet-based decomposition in a combination with a neural network. The neural network is used for two purposes: to select the optimum frequency bands that can be used for identification during the feature extraction step, and to identify the data during the feature matching step. Two sets of data, training set and test set, which are downloaded from the MIT-data bases, are used in this work. The training set, which consists of 20 obstructive sleep apnea subjects and 10 normal subjects, is used to train the neural network of type feed-forward back-propagation. The test set, which consists also of 20 obstructive sleep apnea and 10 normal subjects is used to test the performance of the identification system. A best identification efficiency of 93.33{\%} has been obtained in this work using three inputs only.",
keywords = "Artificial Neural Networks, Feature Selection, Identification, Obstructive Sleep Apnea, Power Spectral Density, Soft-Decision Wavelet-Decomposition",
author = "Abdulnasir Hossen",
year = "2013",
doi = "10.1109/BMEI.2013.6746930",
language = "English",
pages = "182--186",
booktitle = "Proceedings of the 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - A neural network technique for feature selection and identification of obstructive sleep apnea

AU - Hossen, Abdulnasir

PY - 2013

Y1 - 2013

N2 - A novel identification method of Obstructive Sleep Apnea from normal controls is presented in this paper. The method uses the approximate power spectral density of heart rate variability, which is estimated using a soft-decision wavelet-based decomposition in a combination with a neural network. The neural network is used for two purposes: to select the optimum frequency bands that can be used for identification during the feature extraction step, and to identify the data during the feature matching step. Two sets of data, training set and test set, which are downloaded from the MIT-data bases, are used in this work. The training set, which consists of 20 obstructive sleep apnea subjects and 10 normal subjects, is used to train the neural network of type feed-forward back-propagation. The test set, which consists also of 20 obstructive sleep apnea and 10 normal subjects is used to test the performance of the identification system. A best identification efficiency of 93.33% has been obtained in this work using three inputs only.

AB - A novel identification method of Obstructive Sleep Apnea from normal controls is presented in this paper. The method uses the approximate power spectral density of heart rate variability, which is estimated using a soft-decision wavelet-based decomposition in a combination with a neural network. The neural network is used for two purposes: to select the optimum frequency bands that can be used for identification during the feature extraction step, and to identify the data during the feature matching step. Two sets of data, training set and test set, which are downloaded from the MIT-data bases, are used in this work. The training set, which consists of 20 obstructive sleep apnea subjects and 10 normal subjects, is used to train the neural network of type feed-forward back-propagation. The test set, which consists also of 20 obstructive sleep apnea and 10 normal subjects is used to test the performance of the identification system. A best identification efficiency of 93.33% has been obtained in this work using three inputs only.

KW - Artificial Neural Networks

KW - Feature Selection

KW - Identification

KW - Obstructive Sleep Apnea

KW - Power Spectral Density

KW - Soft-Decision Wavelet-Decomposition

UR - http://www.scopus.com/inward/record.url?scp=84896271656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896271656&partnerID=8YFLogxK

U2 - 10.1109/BMEI.2013.6746930

DO - 10.1109/BMEI.2013.6746930

M3 - Conference contribution

AN - SCOPUS:84896271656

SP - 182

EP - 186

BT - Proceedings of the 2013 6th International Conference on Biomedical Engineering and Informatics, BMEI 2013

PB - IEEE Computer Society

ER -