Improved sleep-wake and behavior discrimination using MEMS accelerometers

Sridhar Sunderam, Nick Chernyy, Nathalia Peixoto, Jonathan P. Mason, Steven L. Weinstein, Steven Schiff, Bruce Gluckman

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

State of vigilance is determined by behavioral observations and electrophysiological activity. Here, we improve automatic state of vigilance discrimination by combining head acceleration with EEG measures. We incorporated biaxial dc-sensitive microelectromechanical system (MEMS) accelerometers into head-mounted preamplifiers in rodents. Epochs (15 s) of behavioral video and EEG data formed training sets for the following states: Slow Wave Sleep, Rapid Eye Movement Sleep, Quiet Wakefulness, Feeding or Grooming, and Exploration. Multivariate linear discriminant analysis of EEG features with and without accelerometer features was used to classify behavioral state. A broad selection of EEG feature sets based on recent literature on state discrimination in rodents was tested. In all cases, inclusion of head acceleration significantly improved the discriminative capability. Our approach offers a novel methodology for determining the behavioral context of EEG in real time, and has potential application in automatic sleep-wake staging and in neural prosthetic applications for movement disorders and epileptic seizures.

Original languageEnglish (US)
Pages (from-to)373-383
Number of pages11
JournalJournal of Neuroscience Methods
Volume163
Issue number2
DOIs
StatePublished - Jul 30 2007

Fingerprint

Electroencephalography
Sleep
Head
Rodentia
Grooming
Wakefulness
REM Sleep
Movement Disorders
Discriminant Analysis
Epilepsy

All Science Journal Classification (ASJC) codes

  • Neuroscience(all)

Cite this

Sunderam, Sridhar ; Chernyy, Nick ; Peixoto, Nathalia ; Mason, Jonathan P. ; Weinstein, Steven L. ; Schiff, Steven ; Gluckman, Bruce. / Improved sleep-wake and behavior discrimination using MEMS accelerometers. In: Journal of Neuroscience Methods. 2007 ; Vol. 163, No. 2. pp. 373-383.
@article{7f271db7e8b14f73a4b047109076570a,
title = "Improved sleep-wake and behavior discrimination using MEMS accelerometers",
abstract = "State of vigilance is determined by behavioral observations and electrophysiological activity. Here, we improve automatic state of vigilance discrimination by combining head acceleration with EEG measures. We incorporated biaxial dc-sensitive microelectromechanical system (MEMS) accelerometers into head-mounted preamplifiers in rodents. Epochs (15 s) of behavioral video and EEG data formed training sets for the following states: Slow Wave Sleep, Rapid Eye Movement Sleep, Quiet Wakefulness, Feeding or Grooming, and Exploration. Multivariate linear discriminant analysis of EEG features with and without accelerometer features was used to classify behavioral state. A broad selection of EEG feature sets based on recent literature on state discrimination in rodents was tested. In all cases, inclusion of head acceleration significantly improved the discriminative capability. Our approach offers a novel methodology for determining the behavioral context of EEG in real time, and has potential application in automatic sleep-wake staging and in neural prosthetic applications for movement disorders and epileptic seizures.",
author = "Sridhar Sunderam and Nick Chernyy and Nathalia Peixoto and Mason, {Jonathan P.} and Weinstein, {Steven L.} and Steven Schiff and Bruce Gluckman",
year = "2007",
month = "7",
day = "30",
doi = "10.1016/j.jneumeth.2007.03.007",
language = "English (US)",
volume = "163",
pages = "373--383",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",
number = "2",

}

Improved sleep-wake and behavior discrimination using MEMS accelerometers. / Sunderam, Sridhar; Chernyy, Nick; Peixoto, Nathalia; Mason, Jonathan P.; Weinstein, Steven L.; Schiff, Steven; Gluckman, Bruce.

In: Journal of Neuroscience Methods, Vol. 163, No. 2, 30.07.2007, p. 373-383.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Improved sleep-wake and behavior discrimination using MEMS accelerometers

AU - Sunderam, Sridhar

AU - Chernyy, Nick

AU - Peixoto, Nathalia

AU - Mason, Jonathan P.

AU - Weinstein, Steven L.

AU - Schiff, Steven

AU - Gluckman, Bruce

PY - 2007/7/30

Y1 - 2007/7/30

N2 - State of vigilance is determined by behavioral observations and electrophysiological activity. Here, we improve automatic state of vigilance discrimination by combining head acceleration with EEG measures. We incorporated biaxial dc-sensitive microelectromechanical system (MEMS) accelerometers into head-mounted preamplifiers in rodents. Epochs (15 s) of behavioral video and EEG data formed training sets for the following states: Slow Wave Sleep, Rapid Eye Movement Sleep, Quiet Wakefulness, Feeding or Grooming, and Exploration. Multivariate linear discriminant analysis of EEG features with and without accelerometer features was used to classify behavioral state. A broad selection of EEG feature sets based on recent literature on state discrimination in rodents was tested. In all cases, inclusion of head acceleration significantly improved the discriminative capability. Our approach offers a novel methodology for determining the behavioral context of EEG in real time, and has potential application in automatic sleep-wake staging and in neural prosthetic applications for movement disorders and epileptic seizures.

AB - State of vigilance is determined by behavioral observations and electrophysiological activity. Here, we improve automatic state of vigilance discrimination by combining head acceleration with EEG measures. We incorporated biaxial dc-sensitive microelectromechanical system (MEMS) accelerometers into head-mounted preamplifiers in rodents. Epochs (15 s) of behavioral video and EEG data formed training sets for the following states: Slow Wave Sleep, Rapid Eye Movement Sleep, Quiet Wakefulness, Feeding or Grooming, and Exploration. Multivariate linear discriminant analysis of EEG features with and without accelerometer features was used to classify behavioral state. A broad selection of EEG feature sets based on recent literature on state discrimination in rodents was tested. In all cases, inclusion of head acceleration significantly improved the discriminative capability. Our approach offers a novel methodology for determining the behavioral context of EEG in real time, and has potential application in automatic sleep-wake staging and in neural prosthetic applications for movement disorders and epileptic seizures.

UR - http://www.scopus.com/inward/record.url?scp=34249887360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34249887360&partnerID=8YFLogxK

U2 - 10.1016/j.jneumeth.2007.03.007

DO - 10.1016/j.jneumeth.2007.03.007

M3 - Article

VL - 163

SP - 373

EP - 383

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

IS - 2

ER -