Assess Sleep Stage by Modern Signal Processing Techniques

TL;DR

This study introduces advanced signal processing methods to extract features from respiratory and EEG signals for automatic sleep stage classification, achieving accuracy comparable to human experts and highlighting the complementary information in respiratory signals.

Contribution

The paper applies Empirical Intrinsic Geometry and Synchrosqueezing transform to sleep signals, providing a rigorous theoretical foundation and demonstrating effective automatic classification of sleep stages.

Findings

Classification accuracy of 81.7% with respiratory signals

Classification accuracy of 89.3% with respiratory and EEG signals

Respiratory signals contain substantial sleep information

Abstract

In this paper, two modern adaptive signal processing techniques, Empirical Intrinsic Geometry and Synchrosqueezing transform, are applied to quantify different dynamical features of the respiratory and electroencephalographic signals. We show that the proposed features are theoretically rigorously supported, as well as capture the sleep information hidden inside the signals. The features are used as input to multiclass support vector machines with the radial basis function to automatically classify sleep stages. The effectiveness of the classification based on the proposed features is shown to be comparable to human expert classification -- the proposed classification of awake, REM, N1, N2 and N3 sleeping stages based on the respiratory signal (resp. respiratory and EEG signals) has the overall accuracy $81.7\%$ (resp. $89.3\%$) in the relatively normal subject group. In addition, by examining the combination of the respiratory signal with the electroencephalographic signal, we conclude that the respiratory signal consists of ample sleep information, which supplements to the information stored in the electroencephalographic signal.