Subject-Adaptive, Real-Time Sleep Stage Classification Based on Conditional Random Field

• Activity Number: 144
• Type: Contributed
• Date/Time: Monday, July 30, 2007 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Gang Luo*+ and Wanli Min
• Companies: IBM T.J. Watson Research Center and IBM T.J. Watson Research Center
• Keywords: pattern recognition ; conditional random field ; sleep staging ; spectrum analysis ; subject adaptation ; machine learning

Abstract

Sleep stager performs one of the most important steps in sleep analysis: classifying sleep recordings into sleep stages. We report an online sleep stager using electroencephalogram (EEG) signal based on a recently developed statistical method, conditional random field. Using sleep recordings from human subjects and birds, we show that the average classification accuracy of our sleep stager almost approaches the theoretical limit and is about 8% higher than that of existing systems. Moreover, for a new subject snew with limited training data Dnew, we perform subject adaptation to improve classification accuracy. Using sleep recordings from human subjects, we show that even without any Dnew, our sleep stager can achieve an average classification accuracy of 70% on snew. This accuracy increases with the size of Dnew and eventually becomes close to the theoretical limit.