Detection of K-complexes and sleep spindles (DETOKS) using sparse optimization

Ankit Parekh, Ivan Selesnick, David M. Rapoport, Indu Ayappa

Research output: Contribution to journalArticle

Abstract

Background: This paper addresses the problem of detecting sleep spindles and K-complexes in human sleep EEG. Sleep spindles and K-complexes aid in classifying stage 2 NREM human sleep. New method: We propose a non-linear model for the EEG, consisting of a transient, low-frequency, and an oscillatory component. The transient component captures the non-oscillatory transients in the EEG. The oscillatory component admits a sparse time-frequency representation. Using a convex objective function, this paper presents a fast non-linear optimization algorithm to estimate the components in the proposed signal model. The low-frequency and oscillatory components are used to detect K-complexes and sleep spindles respectively. Results and comparison with other methods: The performance of the proposed method is evaluated using an online EEG database. The F1 scores for the spindle detection averaged 0.70 ± 0.03 and the F1 scores for the K-complex detection averaged 0.57 ± 0.02. The Matthews Correlation Coefficient and Cohen's Kappa values were in a range similar to the F1 scores for both the sleep spindle and K-complex detection. The F1 scores for the proposed method are higher than existing detection algorithms. Conclusions: Comparable run-times and better detection results than traditional detection algorithms suggests that the proposed method is promising for the practical detection of sleep spindles and K-complexes.

Original languageEnglish (US)
Pages (from-to)37-46
Number of pages10
JournalJournal of Neuroscience Methods
Volume251
DOIs
StatePublished - Aug 5 2015

Fingerprint

Sleep
Electroencephalography
Nonlinear Dynamics
Databases

Keywords

  • Convex optimization
  • K-complex detection
  • Sleep spindle detection
  • Sparse signal

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

Detection of K-complexes and sleep spindles (DETOKS) using sparse optimization. / Parekh, Ankit; Selesnick, Ivan; Rapoport, David M.; Ayappa, Indu.

In: Journal of Neuroscience Methods, Vol. 251, 05.08.2015, p. 37-46.

Research output: Contribution to journalArticle

Parekh, Ankit ; Selesnick, Ivan ; Rapoport, David M. ; Ayappa, Indu. / Detection of K-complexes and sleep spindles (DETOKS) using sparse optimization. In: Journal of Neuroscience Methods. 2015 ; Vol. 251. pp. 37-46.
@article{9945c78260294374a0ae91ce40284161,
title = "Detection of K-complexes and sleep spindles (DETOKS) using sparse optimization",
abstract = "Background: This paper addresses the problem of detecting sleep spindles and K-complexes in human sleep EEG. Sleep spindles and K-complexes aid in classifying stage 2 NREM human sleep. New method: We propose a non-linear model for the EEG, consisting of a transient, low-frequency, and an oscillatory component. The transient component captures the non-oscillatory transients in the EEG. The oscillatory component admits a sparse time-frequency representation. Using a convex objective function, this paper presents a fast non-linear optimization algorithm to estimate the components in the proposed signal model. The low-frequency and oscillatory components are used to detect K-complexes and sleep spindles respectively. Results and comparison with other methods: The performance of the proposed method is evaluated using an online EEG database. The F1 scores for the spindle detection averaged 0.70 ± 0.03 and the F1 scores for the K-complex detection averaged 0.57 ± 0.02. The Matthews Correlation Coefficient and Cohen's Kappa values were in a range similar to the F1 scores for both the sleep spindle and K-complex detection. The F1 scores for the proposed method are higher than existing detection algorithms. Conclusions: Comparable run-times and better detection results than traditional detection algorithms suggests that the proposed method is promising for the practical detection of sleep spindles and K-complexes.",
keywords = "Convex optimization, K-complex detection, Sleep spindle detection, Sparse signal",
author = "Ankit Parekh and Ivan Selesnick and Rapoport, {David M.} and Indu Ayappa",
year = "2015",
month = "8",
day = "5",
doi = "10.1016/j.jneumeth.2015.04.006",
language = "English (US)",
volume = "251",
pages = "37--46",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",

}

TY - JOUR

T1 - Detection of K-complexes and sleep spindles (DETOKS) using sparse optimization

AU - Parekh, Ankit

AU - Selesnick, Ivan

AU - Rapoport, David M.

AU - Ayappa, Indu

PY - 2015/8/5

Y1 - 2015/8/5

N2 - Background: This paper addresses the problem of detecting sleep spindles and K-complexes in human sleep EEG. Sleep spindles and K-complexes aid in classifying stage 2 NREM human sleep. New method: We propose a non-linear model for the EEG, consisting of a transient, low-frequency, and an oscillatory component. The transient component captures the non-oscillatory transients in the EEG. The oscillatory component admits a sparse time-frequency representation. Using a convex objective function, this paper presents a fast non-linear optimization algorithm to estimate the components in the proposed signal model. The low-frequency and oscillatory components are used to detect K-complexes and sleep spindles respectively. Results and comparison with other methods: The performance of the proposed method is evaluated using an online EEG database. The F1 scores for the spindle detection averaged 0.70 ± 0.03 and the F1 scores for the K-complex detection averaged 0.57 ± 0.02. The Matthews Correlation Coefficient and Cohen's Kappa values were in a range similar to the F1 scores for both the sleep spindle and K-complex detection. The F1 scores for the proposed method are higher than existing detection algorithms. Conclusions: Comparable run-times and better detection results than traditional detection algorithms suggests that the proposed method is promising for the practical detection of sleep spindles and K-complexes.

AB - Background: This paper addresses the problem of detecting sleep spindles and K-complexes in human sleep EEG. Sleep spindles and K-complexes aid in classifying stage 2 NREM human sleep. New method: We propose a non-linear model for the EEG, consisting of a transient, low-frequency, and an oscillatory component. The transient component captures the non-oscillatory transients in the EEG. The oscillatory component admits a sparse time-frequency representation. Using a convex objective function, this paper presents a fast non-linear optimization algorithm to estimate the components in the proposed signal model. The low-frequency and oscillatory components are used to detect K-complexes and sleep spindles respectively. Results and comparison with other methods: The performance of the proposed method is evaluated using an online EEG database. The F1 scores for the spindle detection averaged 0.70 ± 0.03 and the F1 scores for the K-complex detection averaged 0.57 ± 0.02. The Matthews Correlation Coefficient and Cohen's Kappa values were in a range similar to the F1 scores for both the sleep spindle and K-complex detection. The F1 scores for the proposed method are higher than existing detection algorithms. Conclusions: Comparable run-times and better detection results than traditional detection algorithms suggests that the proposed method is promising for the practical detection of sleep spindles and K-complexes.

KW - Convex optimization

KW - K-complex detection

KW - Sleep spindle detection

KW - Sparse signal

UR - http://www.scopus.com/inward/record.url?scp=84930646733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930646733&partnerID=8YFLogxK

U2 - 10.1016/j.jneumeth.2015.04.006

DO - 10.1016/j.jneumeth.2015.04.006

M3 - Article

VL - 251

SP - 37

EP - 46

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

ER -