A Noise-Assisted Data Analysis Method for Automatic EOG-Based Sleep Stage Classification Using Ensemble Learning

Alexander Neergaard Olesen; Julie A E Christensen; Helge B D Sorensen; Poul J Jennum

doi:10.1109/EMBC.2016.7591548

A Noise-Assisted Data Analysis Method for Automatic EOG-Based Sleep Stage Classification Using Ensemble Learning

Alexander Neergaard Olesen, Julie A E Christensen, Helge B D Sorensen, Poul J Jennum

Afdeling for Hjerne- og Nerveundersøgelser

14 Citationer (Scopus)

Abstrakt

Reducing the number of recording modalities for sleep staging research can benefit both researchers and patients, under the condition that they provide as accurate results as conventional systems. This paper investigates the possibility of exploiting the multisource nature of the electrooculography (EOG) signals by presenting a method for automatic sleep staging using the complete ensemble empirical mode decomposition with adaptive noise algorithm, and a random forest classifier. It achieves a high overall accuracy of 82% and a Cohen's kappa of 0.74 indicating substantial agreement between automatic and manual scoring.

Originalsprog	Engelsk
Tidsskrift	I E E E Engineering in Medicine and Biology Society. Conference Proceedings
Vol/bind	2016
Sider (fra-til)	3769-3772
Antal sider	4
ISSN	1557-170X
DOI	https://doi.org/10.1109/EMBC.2016.7591548
Status	Udgivet - 2016

Adgang til dokumentet

10.1109/EMBC.2016.7591548

Citationsformater

A Noise-Assisted Data Analysis Method for Automatic EOG-Based Sleep Stage Classification Using Ensemble Learning. / Olesen, Alexander Neergaard; Christensen, Julie A E; Sorensen, Helge B D et al.

I: I E E E Engineering in Medicine and Biology Society. Conference Proceedings, Bind 2016, 2016, s. 3769-3772.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › peer review

@inproceedings{21a1b56bd5a5443c9fffb94d6225b3e0,

title = "A Noise-Assisted Data Analysis Method for Automatic EOG-Based Sleep Stage Classification Using Ensemble Learning",

abstract = "Reducing the number of recording modalities for sleep staging research can benefit both researchers and patients, under the condition that they provide as accurate results as conventional systems. This paper investigates the possibility of exploiting the multisource nature of the electrooculography (EOG) signals by presenting a method for automatic sleep staging using the complete ensemble empirical mode decomposition with adaptive noise algorithm, and a random forest classifier. It achieves a high overall accuracy of 82% and a Cohen's kappa of 0.74 indicating substantial agreement between automatic and manual scoring.",

keywords = "Journal Article",

author = "Olesen, {Alexander Neergaard} and Christensen, {Julie A E} and Sorensen, {Helge B D} and Jennum, {Poul J}",

year = "2016",

doi = "10.1109/EMBC.2016.7591548",

language = "English",

volume = "2016",

pages = "3769--3772",

journal = "I E E E Engineering in Medicine and Biology Society. Conference Proceedings",

issn = "1557-170X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A Noise-Assisted Data Analysis Method for Automatic EOG-Based Sleep Stage Classification Using Ensemble Learning

AU - Olesen, Alexander Neergaard

AU - Christensen, Julie A E

AU - Sorensen, Helge B D

AU - Jennum, Poul J

PY - 2016

Y1 - 2016

N2 - Reducing the number of recording modalities for sleep staging research can benefit both researchers and patients, under the condition that they provide as accurate results as conventional systems. This paper investigates the possibility of exploiting the multisource nature of the electrooculography (EOG) signals by presenting a method for automatic sleep staging using the complete ensemble empirical mode decomposition with adaptive noise algorithm, and a random forest classifier. It achieves a high overall accuracy of 82% and a Cohen's kappa of 0.74 indicating substantial agreement between automatic and manual scoring.

AB - Reducing the number of recording modalities for sleep staging research can benefit both researchers and patients, under the condition that they provide as accurate results as conventional systems. This paper investigates the possibility of exploiting the multisource nature of the electrooculography (EOG) signals by presenting a method for automatic sleep staging using the complete ensemble empirical mode decomposition with adaptive noise algorithm, and a random forest classifier. It achieves a high overall accuracy of 82% and a Cohen's kappa of 0.74 indicating substantial agreement between automatic and manual scoring.

KW - Journal Article

U2 - 10.1109/EMBC.2016.7591548

DO - 10.1109/EMBC.2016.7591548

M3 - Conference article

C2 - 28269109

VL - 2016

SP - 3769

EP - 3772

JO - I E E E Engineering in Medicine and Biology Society. Conference Proceedings

JF - I E E E Engineering in Medicine and Biology Society. Conference Proceedings

SN - 1557-170X

ER -

A Noise-Assisted Data Analysis Method for Automatic EOG-Based Sleep Stage Classification Using Ensemble Learning

Abstrakt

Adgang til dokumentet

Fingeraftryk

Citationsformater