Biosleep: A Comprehensive Sleep Analysis System

Abstract

Traditionally the analysis of sleep has used two distinct manual EEC analysis methods: one for general structure, the other for short time-scale events. Both methods suffer from high levels of inter-expert variability. In this paper we present a system which uses a neural net network classifier to analyze each second of sleep. Post-processing techniques are described which result in outputs which mimic both of the traditional manual analysis methods. This combination of methods results in a comprehensive sleep analysis system providing information on both the macro and microstructure of sleep. Our results show that it is possible to use a combined approach to sleep analysis and that there is strong correlation between expert scoring and the post-processed neural network output.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 25, 2001
Accession Number
ADA409354

Entities

People

  • E. Braithwaite
  • L. Tarassenko
  • N. Mcgrogan

Organizations

  • University of Oxford

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Arousal (Physiology)
  • Cardiovascular Diseases
  • Classification
  • Coefficients
  • Detection
  • Diseases And Disorders
  • Electroencephalography
  • Engineering
  • Frequency
  • Frequency Shift
  • Machine Learning
  • Microstructure
  • Neural Networks
  • Psychophysiology
  • Signal Processing
  • Sleep Disorders
  • Standards

Fields of Study

  • Computer science

Readers

  • Acoustical Oceanography.
  • Computational Modeling and Simulation
  • Neuroscience

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks