Detection of K-complexes based on the wavelet transform

Lærke K. Krohne; Rie B. Hansen; Julie Anja Engelhard Christensen; Helge Bjarup Dissing Sørensen; Poul Jennum

doi:10.1109/EMBC.2014.6944859

Detection of K-complexes based on the wavelet transform

Lærke K. Krohne, Rie B. Hansen, Julie Anja Engelhard Christensen, Helge Bjarup Dissing Sørensen, Poul Jennum

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Sleep scoring needs computational assistance to reduce execution time and to assure high quality. In this pilot study a semi-automatic K-Complex detection algorithm was developed using wavelet transformation to identify pseudo-K-Complexes and various feature thresholds to reject false positives. The algorithm was trained and tested on sleep EEG from two databases to enhance its general applicability. When testing on data from subjects from the DREAMS© database, a mean true positive rate of 74 % and a positive predictive value of 65 % were achieved. After adjusting a few thresholds to adapt to the second database, the Danish Center for Sleep Medicine, a similar performance was achieved. The algorithm performs at the level of the State of the Art and surpasses the inter-rater agreement rate.

Original language	English
Title of host publication	2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Publisher	IEEE
Publication date	2014
Pages	5450-5453
ISBN (Print)	978-1-4244-7929-0
DOIs	https://doi.org/10.1109/EMBC.2014.6944859
Publication status	Published - 2014
Event	36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Chicago, IL, United States Duration: 26 Aug 2014 → 30 Aug 2014 Conference number: 36 http://embc.embs.org/2014/

Conference

Conference	36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Number	36
Country/Territory	United States
City	Chicago, IL
Period	26/08/2014 → 30/08/2014
Internet address	http://embc.embs.org/2014/

Keywords

Bioengineering
Databases
Electroencephalography
Feature extraction
Prediction algorithms
Sleep
Visualization
Wavelet transforms

Access to Document

10.1109/EMBC.2014.6944859

OpenUrl availability

Full text

36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Krohne, L. K. (Participant)
26 Aug 2014 → 30 Aug 2016
Activity: Attending an event › Participating in or organising a conference

Cite this

@inproceedings{f95ae501dd634ebfa9247e8e1804ffbc,

title = "Detection of K-complexes based on the wavelet transform",

abstract = "Sleep scoring needs computational assistance to reduce execution time and to assure high quality. In this pilot study a semi-automatic K-Complex detection algorithm was developed using wavelet transformation to identify pseudo-K-Complexes and various feature thresholds to reject false positives. The algorithm was trained and tested on sleep EEG from two databases to enhance its general applicability. When testing on data from subjects from the DREAMS{\textcopyright} database, a mean true positive rate of 74 % and a positive predictive value of 65 % were achieved. After adjusting a few thresholds to adapt to the second database, the Danish Center for Sleep Medicine, a similar performance was achieved. The algorithm performs at the level of the State of the Art and surpasses the inter-rater agreement rate.",

keywords = "Bioengineering, Databases, Electroencephalography, Feature extraction, Prediction algorithms, Sleep, Visualization, Wavelet transforms",

author = "Krohne, {L{\ae}rke K.} and Hansen, {Rie B.} and Christensen, {Julie Anja Engelhard} and S{\o}rensen, {Helge Bjarup Dissing} and Poul Jennum",

year = "2014",

doi = "10.1109/EMBC.2014.6944859",

language = "English",

isbn = "978-1-4244-7929-0",

pages = "5450--5453",

booktitle = "2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society",

publisher = "IEEE",

address = "United States",

note = "36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC ; Conference date: 26-08-2014 Through 30-08-2014",

url = "http://embc.embs.org/2014/",

}

Krohne, LK, Hansen, RB, Christensen, JAE, Sørensen, HBD & Jennum, P 2014, Detection of K-complexes based on the wavelet transform. in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society . IEEE, pp. 5450-5453, 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, United States, 26/08/2014. https://doi.org/10.1109/EMBC.2014.6944859

Detection of K-complexes based on the wavelet transform. / Krohne, Lærke K.; Hansen, Rie B.; Christensen, Julie Anja Engelhard et al.
2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society . IEEE, 2014. p. 5450-5453.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Detection of K-complexes based on the wavelet transform

AU - Krohne, Lærke K.

AU - Hansen, Rie B.

AU - Christensen, Julie Anja Engelhard

AU - Sørensen, Helge Bjarup Dissing

AU - Jennum, Poul

N1 - Conference code: 36

PY - 2014

Y1 - 2014

N2 - Sleep scoring needs computational assistance to reduce execution time and to assure high quality. In this pilot study a semi-automatic K-Complex detection algorithm was developed using wavelet transformation to identify pseudo-K-Complexes and various feature thresholds to reject false positives. The algorithm was trained and tested on sleep EEG from two databases to enhance its general applicability. When testing on data from subjects from the DREAMS© database, a mean true positive rate of 74 % and a positive predictive value of 65 % were achieved. After adjusting a few thresholds to adapt to the second database, the Danish Center for Sleep Medicine, a similar performance was achieved. The algorithm performs at the level of the State of the Art and surpasses the inter-rater agreement rate.

AB - Sleep scoring needs computational assistance to reduce execution time and to assure high quality. In this pilot study a semi-automatic K-Complex detection algorithm was developed using wavelet transformation to identify pseudo-K-Complexes and various feature thresholds to reject false positives. The algorithm was trained and tested on sleep EEG from two databases to enhance its general applicability. When testing on data from subjects from the DREAMS© database, a mean true positive rate of 74 % and a positive predictive value of 65 % were achieved. After adjusting a few thresholds to adapt to the second database, the Danish Center for Sleep Medicine, a similar performance was achieved. The algorithm performs at the level of the State of the Art and surpasses the inter-rater agreement rate.

KW - Bioengineering

KW - Databases

KW - Electroencephalography

KW - Feature extraction

KW - Prediction algorithms

KW - Sleep

KW - Visualization

KW - Wavelet transforms

U2 - 10.1109/EMBC.2014.6944859

DO - 10.1109/EMBC.2014.6944859

M3 - Article in proceedings

C2 - 25571227

SN - 978-1-4244-7929-0

SP - 5450

EP - 5453

BT - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

PB - IEEE

T2 - 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 26 August 2014 through 30 August 2014

ER -

Detection of K-complexes based on the wavelet transform

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Activities

36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Cite this