Automatic estimation of sleep level for nap based on conditional probability of sleep stages and an exponential smoothing method

Author

Bei Wang ; Xingyu Wang ; Tao Zhang ; Nakamura, Mitsutoshi

Author_Institution

Key Lab. of Adv. Control & Optimization for Chem. Processes, East China Univ. of Sci. & Technol., Shanghai, China

fYear

2013

fDate

3-7 July 2013

Firstpage

4243

Lastpage

4246

Abstract

An automatic sleep level estimation method was developed for monitoring and regulation of day time nap sleep. The recorded nap data is separated into continuous 5-second segments. Features are extracted from EEGs, EOGs and EMG. A parameter of sleep level is defined which is estimated based on the conditional probability of sleep stages. An exponential smoothing method is applied for the estimated sleep level. There were totally 12 healthy subjects, with an averaged age of 22 yeas old, participated into the experimental work. Comparing with sleep stage determination, the presented sleep level estimation method showed better performance for nap sleep interpretation. Real time monitoring and regulation of nap is realizable based on the developed technique.

Keywords

electro-oculography; electroencephalography; electromyography; feature extraction; medical signal processing; sleep; smoothing methods; EEG data; EMG data; EOG data; day time nap sleep; exponential smoothing method; features extraction; real time monitoring; sleep level automatic estimation; sleep stages conditional probability; Educational institutions; Electroencephalography; Estimation; Monitoring; Probability; Sleep; Smoothing methods; Conditional probability; Nap regulation; Sleep level estimation; Sleep stage;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE

Conference_Location

Osaka

ISSN

1557-170X

Type

conf

DOI

10.1109/EMBC.2013.6610482

Filename

6610482