Sleep-Stage Decision Algorithm by Using Heartbeat and Body-Movement Signals

The auditory awakening thresholds of the major electroencephalographically defined sleep stages were compared. A modification of the method of constant stimuli was used in an apparently successful attempt to minimize the incorporation of the experimental stimuli into the mental activity of the sleeper. A total of 319 experimental trials were distributed among seven human Ss who served for about six experimental nights each. The sequence and timing of experimental trials were counterbalanced to control for nights, habituation, amount of accumulated sleep, and amount of sleep since last awakening. The results showed approximately equal awakening thresholds during REM periods (the rapid eye movement stage of sleep) and stage 2 (low voltage EEG and 12 to 14 cps “sleep spindles”). Both these stages had lower awakening thresholds than delta sleep (large slow EEG waves). Awakening thresholds became lower with accumulated sleep, independent of sleep stage. There were no significant stage independent relationships between awakening threshold and time since last awakening or time since last body movement, although the latter were varied over a relatively narrow range which limits the generality of these findings. There was no stage independent relationship between heart rate and awakening threshold. The possible physiological determinants of the awakening response were discussed.

Download Full-text

Sleep stage classification by body movement index and respiratory interval indices using multiple radar sensors

2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) ◽

10.1109/embc.2015.7320153 ◽

2015 ◽

Cited By ~ 7

Author(s):

Masayuki Kagawa ◽

Noriyuki Sasaki ◽

Kazuki Suzumura ◽

Takemi Matsui

Keyword(s):

Sleep Stage ◽

Body Movement ◽

Radar Sensors ◽

Stage Classification ◽

Sleep Stage Classification ◽

Movement Index

Download Full-text

Novel Sleep Stage Estimation Method for Children Using Body Movement

Public Health Frontier ◽

10.5963/phf0202002 ◽

2013 ◽

Vol 2 (2) ◽

pp. 61-68 ◽

Cited By ~ 1

Author(s):

Shima Okada ◽

Sachiko Shimizu ◽

Yuko Ohno ◽

Ikuko Mohri ◽

Masako Taniike ◽

...

Keyword(s):

Sleep Stage ◽

Body Movement ◽

Estimation Method ◽

Stage Estimation

Download Full-text

Book project: Body, movement and mental health - a physiotherapy perspective

PsycEXTRA Dataset ◽

10.1037/e573122012-064 ◽

2012 ◽

Author(s):

Riitta Keskinen Rosenqvist ◽

Gabriele Biguet ◽

Adrienne Levy-Berg

Keyword(s):

Mental Health ◽

Body Movement

Download Full-text

Standardized decision algorithm for selecting the next antidepressant using information on previous treatments: THE-Checklist

Pharmacopsychiatry ◽

10.1055/s-0029-1240148 ◽

2009 ◽

Vol 42 (05) ◽

Author(s):

U Keßler ◽

M Linden

Keyword(s):

Decision Algorithm

Download Full-text

Causal Probabilistic Network and Power Spectral Estimation Used in Sleep Stage Classification

Methods of Information in Medicine ◽

10.1055/s-0038-1636853 ◽

1997 ◽

Vol 36 (04/05) ◽

pp. 41-46

Author(s):

A. Kjaer ◽

W. Jensen ◽

T. Dyrby ◽

L. Andreasen ◽

J. Andersen ◽

...

Keyword(s):

Sleep Stage ◽

Spectral Estimation ◽

Interrater Agreement ◽

Probabilistic Networks ◽

Probabilistic Network ◽

Spectral Bands ◽

Power Spectral ◽

Stage Classification ◽

Sleep Stage Classification ◽

The Brain

Abstract.A new method for sleep-stage classification using a causal probabilistic network as automatic classifier has been implemented and validated. The system uses features from the primary sleep signals from the brain (EEG) and the eyes (AOG) as input. From the EEG, features are derived containing spectral information which is used to classify power in the classical spectral bands, sleep spindles and K-complexes. From AOG, information on rapid eye movements is derived. Features are extracted every 2 seconds. The CPN-based sleep classifier was implemented using the HUGIN system, an application tool to handle causal probabilistic networks. The results obtained using different training approaches show agreements ranging from 68.7 to 70.7% between the system and the two experts when a pooled agreement is computed over the six subjects. As a comparison, the interrater agreement between the two experts was found to be 71.4%, measured also over the six subjects.

Download Full-text