Expert Knowledge-based Automatic Sleep Stage Determination Bymulti-valued Decision Making Method

摘要

In this study,an eXpert knowledge-based automatic sleep stage determination system working on a multivalued decision making method is developed.Visual inspection by a qualified clinician is adopted to obtainrnthe expert knowledge database.The expert knowledge database consists of probability density functions ofrnparameters for various sleep stages.Sleep stages are determined automatically according to the conditionalrnprobability.Tbtally,four subjects were participated.The automatic sleep stage determination results showedrnClose agreements with the visual inspection on sleep stages of awake,REM(rapid eye movement),light sleeprnand deep sleep.The constructed expert knowledge database reflects the distributions of characteristic parameters which can be adaptive to variable sleep data in hospitals.The developed automatic determinationrntechnique based on expert knowledge of visual inspection can be anassistant tool enabling further inspectionrnof sleep disorder cases for clinical practice.