Sleep spindle detection using time-frequency sparsity

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

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

Abstract

This paper proposes an EEG processor for sleep spindle detection algorithms. It non-linearly separates the raw EEG signal into non-oscillatory transient and sustained rhythmic oscillation components using long and short windows for the short-time Fourier transform. The processor utilizes the fact that sleep spindles can be sparsely represented via the inverse of a short-time Fourier transform. Five sleep spindle detectors were tested on the EEG database with and without the proposed EEG processor. We achieved an improvement of 13.3% in the by-sample F<inf>1</inf> score, and 13.9% in the by-sample Matthews Correlation Coefficient score of these algorithms when the processed EEG was used for spindle detection. The processor was able to improve the scores by reducing the number of false positive spindles and increasing the number of true positive spindles detected.

Original languageEnglish (US)
Title of host publication2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479981847
DOIs
StatePublished - Jan 6 2015
Event2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014 - Philadelphia, United States
Duration: Dec 13 2014Dec 13 2014

Other

Other2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014
CountryUnited States
CityPhiladelphia
Period12/13/1412/13/14

Fingerprint

Electroencephalography
Fourier transforms
Sleep
Detectors

Keywords

  • convex optimization
  • Pursuit algorithms
  • Short time Fourier transform
  • spectrogram

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering

Cite this

Parekh, A., Selesnick, I., Rapoport, D. M., & Ayappa, I. (2015). Sleep spindle detection using time-frequency sparsity. In 2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014 - Proceedings [7002965] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SPMB.2014.7002965

Sleep spindle detection using time-frequency sparsity. / Parekh, Ankit; Selesnick, Ivan; Rapoport, David M.; Ayappa, Indu.

2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. 7002965.

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

Parekh, A, Selesnick, I, Rapoport, DM & Ayappa, I 2015, Sleep spindle detection using time-frequency sparsity. in 2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014 - Proceedings., 7002965, Institute of Electrical and Electronics Engineers Inc., 2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014, Philadelphia, United States, 12/13/14. https://doi.org/10.1109/SPMB.2014.7002965
Parekh A, Selesnick I, Rapoport DM, Ayappa I. Sleep spindle detection using time-frequency sparsity. In 2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. 7002965 https://doi.org/10.1109/SPMB.2014.7002965
Parekh, Ankit ; Selesnick, Ivan ; Rapoport, David M. ; Ayappa, Indu. / Sleep spindle detection using time-frequency sparsity. 2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{8b8547b0da3f4cd389f2cd2f46421f6e,
title = "Sleep spindle detection using time-frequency sparsity",
abstract = "This paper proposes an EEG processor for sleep spindle detection algorithms. It non-linearly separates the raw EEG signal into non-oscillatory transient and sustained rhythmic oscillation components using long and short windows for the short-time Fourier transform. The processor utilizes the fact that sleep spindles can be sparsely represented via the inverse of a short-time Fourier transform. Five sleep spindle detectors were tested on the EEG database with and without the proposed EEG processor. We achieved an improvement of 13.3{\%} in the by-sample F1 score, and 13.9{\%} in the by-sample Matthews Correlation Coefficient score of these algorithms when the processed EEG was used for spindle detection. The processor was able to improve the scores by reducing the number of false positive spindles and increasing the number of true positive spindles detected.",
keywords = "convex optimization, Pursuit algorithms, Short time Fourier transform, spectrogram",
author = "Ankit Parekh and Ivan Selesnick and Rapoport, {David M.} and Indu Ayappa",
year = "2015",
month = "1",
day = "6",
doi = "10.1109/SPMB.2014.7002965",
language = "English (US)",
isbn = "9781479981847",
booktitle = "2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Sleep spindle detection using time-frequency sparsity

AU - Parekh, Ankit

AU - Selesnick, Ivan

AU - Rapoport, David M.

AU - Ayappa, Indu

PY - 2015/1/6

Y1 - 2015/1/6

N2 - This paper proposes an EEG processor for sleep spindle detection algorithms. It non-linearly separates the raw EEG signal into non-oscillatory transient and sustained rhythmic oscillation components using long and short windows for the short-time Fourier transform. The processor utilizes the fact that sleep spindles can be sparsely represented via the inverse of a short-time Fourier transform. Five sleep spindle detectors were tested on the EEG database with and without the proposed EEG processor. We achieved an improvement of 13.3% in the by-sample F1 score, and 13.9% in the by-sample Matthews Correlation Coefficient score of these algorithms when the processed EEG was used for spindle detection. The processor was able to improve the scores by reducing the number of false positive spindles and increasing the number of true positive spindles detected.

AB - This paper proposes an EEG processor for sleep spindle detection algorithms. It non-linearly separates the raw EEG signal into non-oscillatory transient and sustained rhythmic oscillation components using long and short windows for the short-time Fourier transform. The processor utilizes the fact that sleep spindles can be sparsely represented via the inverse of a short-time Fourier transform. Five sleep spindle detectors were tested on the EEG database with and without the proposed EEG processor. We achieved an improvement of 13.3% in the by-sample F1 score, and 13.9% in the by-sample Matthews Correlation Coefficient score of these algorithms when the processed EEG was used for spindle detection. The processor was able to improve the scores by reducing the number of false positive spindles and increasing the number of true positive spindles detected.

KW - convex optimization

KW - Pursuit algorithms

KW - Short time Fourier transform

KW - spectrogram

UR - http://www.scopus.com/inward/record.url?scp=84921710650&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921710650&partnerID=8YFLogxK

U2 - 10.1109/SPMB.2014.7002965

DO - 10.1109/SPMB.2014.7002965

M3 - Conference contribution

SN - 9781479981847

BT - 2014 IEEE Signal Processing in Medicine and Biology Symposium, IEEE SPMB 2014 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -