Automated Analysis of Sleep Study Parameters Using Signal Processing and Artificial Intelligence

Abstract

An automated sleep stage categorization can readily face noise-contaminated EEG recordings, just as other signal processing applications. Therefore, the denoising of the contaminated signals is inevitable to ensure a reliable analysis of the EEG signals. In this research work, an empirical mode decomposition is used in combination with stacked autoencoders to conduct automatic sleep stage classification with reliable analytical performance. Due to the decomposition of the composite signal into several intrinsic mode functions, empirical mode decomposition offers an effective solution for denoising non-stationary signals such as EEG. Preliminary results showed that through these intrinsic modes, a signal with a high signal-to-noise ratio can be obtained, which can be used for further analysis with confidence. Therefore, later, when statistical features were extracted from the denoised signals and were classified using stacked autoencoders, improved results were obtained for Stage 1, Stage 2, Stage 3, Stage 4, and REM stage EEG signals using this combination.

Keywords: EEG signals; autoencoders; biomedical signals; deep learning; sleep stage classification; sleep study.

Figure 1

A block diagram of the proposed model.

Figure 2

A schematic diagram of stacked autoencoder-based deep neural network.

Figure 3

The EEG signals associated with the different sleep stages of a normal human being.

Figure 4

A diagram of an original EEG signal, its different IMFs, and the residual signal after decomposition through the empirical mode decomposition method.

Figure 5

(a) Distribution of statistical features without passing though stacked autoencoder-based deep neural network, (b) abstract features learned by stacked autoencoders for different classes.

Figure 6

Classification performance of the proposed algorithm and other popular classifiers.