AUTOMATED SLEEP STAGE DETECTION WITH A CLASSICAL AND A NEURAL LEARNING ALGORITHM – METHODOLOGICAL ASPECTS

For classification tasks in biosignal processing, several strategies and algorithms can be used. Knowledge-based systems allow prior knowledge about the decision process to be integrated, both by the developer and by self-learning capabilities. For the classification stages in a sleep stage detectio...

Full description

Saved in:
Bibliographic Details
Published inBiomedizinische Technik Vol. 47; no. s1a; pp. 318 - 320
Main Authors Schwaibold, M., Schöchlin, J., Bolz, A.
Format Journal Article
LanguageEnglish
Published Germany 2002
Subjects
Algorithms
Artificial Intelligence
Automated
Biomedical engineering
Diagnosis, Computer-Assisted - instrumentation
Fuzzy Logic
Humans
Learning
Neural Networks (Computer)
Polysomnography - instrumentation
Signal Processing, Computer-Assisted - instrumentation
Sleep
Sleep Stages - physiology
Online AccessGet full text
ISSN0013-5585
1862-278X
DOI10.1515/bmte.2002.47.s1a.318

Cover

More Information
Summary:For classification tasks in biosignal processing, several strategies and algorithms can be used. Knowledge-based systems allow prior knowledge about the decision process to be integrated, both by the developer and by self-learning capabilities. For the classification stages in a sleep stage detection framework, three inference strategies were compared regarding their specific strengths: a classical signal processing approach, artificial neural networks and neuro-fuzzy systems. Methodological aspects were assessed to attain optimum performance and maximum transparency for the user. Due to their effective and robust learning behavior, artificial neural networks could be recommended for pattern recognition, while neuro-fuzzy systems performed best for the processing of contextual information.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0013-5585
1862-278X
DOI:10.1515/bmte.2002.47.s1a.318