Automatic estimation of macro-sleep-architecture using a aingle channel of EEG

Swarnkar, Vinayak, Abeyratne, Udantha R. and Hukins, Craig (2009). Automatic estimation of macro-sleep-architecture using a aingle channel of EEG. In: Fourth International Conference on Industrial and Information Systems 2009. International Conference on Industrial and Information Systems, Peradeniya, Sri Lanka, (295-300). 28-31 December 2009. doi:10.1109/ICIINFS.2009.5429847


Author Swarnkar, Vinayak
Abeyratne, Udantha R.
Hukins, Craig
Title of paper Automatic estimation of macro-sleep-architecture using a aingle channel of EEG
Conference name International Conference on Industrial and Information Systems
Conference location Peradeniya, Sri Lanka
Conference dates 28-31 December 2009
Proceedings title Fourth International Conference on Industrial and Information Systems 2009
Journal name 2009 International Conference On Industrial and Information Systems
Place of Publication Piscataway, NJ, United States
Publisher I E E E
Publication Year 2009
Sub-type Fully published paper
DOI 10.1109/ICIINFS.2009.5429847
ISBN 9781424448371
Start page 295
End page 300
Total pages 5
Language eng
Abstract/Summary Scoring of Macro Sleep Architecture (MSA) is a critical process in assessing several sleep disorders. MSA is defined as classification of sleep into three major states of sleep, State Wake, State REM and State NREM. Existing methods of MSA analysis require the recording of six channels of electrophysiological signals such as the EEG, EOG and EMG. They depend on the manual scoring of overnight data records using the R&K Criteria (1968), developed for visual analysis of signals based on morphological features. Manual analysis of MSA is tedious, subjective and suffers from both inter and intra scorer variability. In addition to this due to dependency of MSA on several biological signals, makes it impossible to incorporate in portable apnea screening devices. Non-availability of MSA hampers these devices accuracy making them non-acceptable among medical community. In this paper we propose a novel method for MSA analysis, which requires just one channel of only EEG data. We also develop a fully automated, objective MSA analysis technique, which uses a single one-dimensional slice of the Bisprectrum of EEG, representing a nonlinear transformation of a system function that can be considered as the EEG generator. The method was evaluated on an overnight clinical database of 23 patients. The results were compared with those obtained by an experienced human scorer. The method proposed in this paper led to agreements in the range of 70%-87%, comparable to that possible between two expert human scorers.
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Sun, 14 Nov 2010, 00:04:58 EST