Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Neural network model: application to automatic analysis of human sleep

N Schaltenbrand1, R Lengelle, J P Macher

  • 1Foundation for Applied Neuroscience Research in Psychiatry, Centre Hospitalier Spécialisé of Rouffach, France.

Computers and Biomedical Research, an International Journal
|April 1, 1993
PubMed
Summary

This study presents an automated method for all-night sleep analysis using neural networks. The approach enhances sleep stage scoring accuracy and provides detailed numerical analysis of sleep patterns.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Serotonergic and noradrenergic function in depression: clinical correlates.

Dialogues in clinical neuroscience·2011
Same author

Suicidal behavior in schizophrenia and family history of suicide.

Dialogues in clinical neuroscience·2011
Same author

Restless legs syndrome and low brain iron levels in patients with haemochromatosis.

Journal of neurology, neurosurgery, and psychiatry·2005
Same author

A positron emission tomography (PET) study of cerebral dopamine D2 and serotonine 5-HT2A receptor occupancy in patients treated with cyamemazine (Tercian).

Psychopharmacology·2005
Same author

Characterization of the CNS effects of naftidrofuryl (Praxilène) by quantitative EEG and functional MRI: a study in healthy elderly subjects.

Neuropsychobiology·2003
Same author

[Pilot study comparing in blind the therapeutic effect of two doses of agomelatine, melatonin- agonist and selective 5HT2c receptors antagonist, in the treatment of major depressive disorders].

L'Encephale·2003

Area of Science:

  • Computational neuroscience
  • Sleep science
  • Artificial intelligence in medicine

Background:

  • Accurate sleep analysis is crucial for understanding neurological disorders.
  • Manual sleep scoring is time-consuming and subjective.
  • Automated methods offer potential for objective and efficient sleep assessment.

Purpose of the Study:

  • To develop and evaluate an automated all-night sleep analysis system.
  • To improve the accuracy of sleep stage scoring.
  • To provide a comprehensive numerical analysis of sleep dynamics.

Main Methods:

  • Utilized multilayer feedforward neural networks for automatic sleep stage scoring.
  • Implemented ambiguity and artifact rejection for supervision.
  • Performed all-night spectral analysis of EEG background activity.

Related Experiment Videos

  • Employed sleep pattern detectors for transient activity analysis.

    • Main Results:

    • Demonstrated a viable approach for automatic all-night sleep analysis.
    • Neural networks effectively performed sleep stage scoring.
    • Numerical analysis provided insights into sleep dynamics.

    Conclusions:

    • Computerized sleep analysis is an essential tool for sleep research.
    • This method can accurately describe the sleep process.
    • The approach reflects the dynamical organization of human sleep.