An Automatic Sleep Spindle Detector based on WT, STFT and WMSD

Arnaldo Manuel Guimarães Batista; Manuel Duarte Ortigueira; DEE Group Author

An Automatic Sleep Spindle Detector based on WT, STFT and WMSD

Arnaldo Manuel Guimarães Batista, Manuel Duarte Ortigueira, DEE Group Author

Research output: Contribution to journal › Article › peer-review

Abstract

Sleep spindles are the most interesting hallmark of stage 2 sleep EEG. Their accurate identification in a polysomnographic signal is essential for sleep professionals to help them mark Stage 2 sleep. Sleep Spindles are also promising objective indicators for neurodegenerative disorders. Visual spindle scoring however is a tedious workload. In this paper three different approaches are used for the automatic detection of sleep spindles: Short Time Fourier Transform, Wavelet Transform and Wave Morphology for Spindle Detection. In order to improve the results, a combination of the three detectors is presented and comparison with human expert scorers is performed. The best performance is obtained with a combination of the three algorithms which resulted in a sensitivity and specificity of 94% when compared to human expert scorers.

Original language	Unknown
Pages (from-to)	2154-2157
Journal	Proceedings Of World Academy Of Science, Engineering And Technology
Volume	68
Issue number	NA
Publication status	Published - 1 Jan 2012

Cite this

@article{6814dce73dbe4d03b7e43ee969cf94d5,

title = "An Automatic Sleep Spindle Detector based on WT, STFT and WMSD",

abstract = "Sleep spindles are the most interesting hallmark of stage 2 sleep EEG. Their accurate identification in a polysomnographic signal is essential for sleep professionals to help them mark Stage 2 sleep. Sleep Spindles are also promising objective indicators for neurodegenerative disorders. Visual spindle scoring however is a tedious workload. In this paper three different approaches are used for the automatic detection of sleep spindles: Short Time Fourier Transform, Wavelet Transform and Wave Morphology for Spindle Detection. In order to improve the results, a combination of the three detectors is presented and comparison with human expert scorers is performed. The best performance is obtained with a combination of the three algorithms which resulted in a sensitivity and specificity of 94% when compared to human expert scorers.",

keywords = "Sleep Spindles, Short Time Fourier Transform, Wavelet Transform, EEG, Wave Morphology for Spindle Detection",

author = "Batista, {Arnaldo Manuel Guimar{\~a}es} and Ortigueira, {Manuel Duarte} and {DEE Group Author}",

year = "2012",

month = jan,

day = "1",

language = "Unknown",

volume = "68",

pages = "2154--2157",

journal = "Proceedings Of World Academy Of Science, Engineering And Technology",

issn = "2070-3740",

number = "NA",

}

TY - JOUR

T1 - An Automatic Sleep Spindle Detector based on WT, STFT and WMSD

AU - Batista, Arnaldo Manuel Guimarães

AU - Ortigueira, Manuel Duarte

AU - DEE Group Author

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Sleep spindles are the most interesting hallmark of stage 2 sleep EEG. Their accurate identification in a polysomnographic signal is essential for sleep professionals to help them mark Stage 2 sleep. Sleep Spindles are also promising objective indicators for neurodegenerative disorders. Visual spindle scoring however is a tedious workload. In this paper three different approaches are used for the automatic detection of sleep spindles: Short Time Fourier Transform, Wavelet Transform and Wave Morphology for Spindle Detection. In order to improve the results, a combination of the three detectors is presented and comparison with human expert scorers is performed. The best performance is obtained with a combination of the three algorithms which resulted in a sensitivity and specificity of 94% when compared to human expert scorers.

AB - Sleep spindles are the most interesting hallmark of stage 2 sleep EEG. Their accurate identification in a polysomnographic signal is essential for sleep professionals to help them mark Stage 2 sleep. Sleep Spindles are also promising objective indicators for neurodegenerative disorders. Visual spindle scoring however is a tedious workload. In this paper three different approaches are used for the automatic detection of sleep spindles: Short Time Fourier Transform, Wavelet Transform and Wave Morphology for Spindle Detection. In order to improve the results, a combination of the three detectors is presented and comparison with human expert scorers is performed. The best performance is obtained with a combination of the three algorithms which resulted in a sensitivity and specificity of 94% when compared to human expert scorers.

KW - Sleep Spindles

KW - Short Time Fourier Transform

KW - Wavelet Transform

KW - EEG

KW - Wave Morphology for Spindle Detection

M3 - Article

SN - 2070-3740

VL - 68

SP - 2154

EP - 2157

JO - Proceedings Of World Academy Of Science, Engineering And Technology

JF - Proceedings Of World Academy Of Science, Engineering And Technology

IS - NA

ER -