Sleep staging with deep structured neural net using Gabor layer and data augmentation

Abstract

Slow wave sleep (SWS) and rapid eye movement (REM) are two of the most important sleep stages that are considered in many studies. Detection of these two sleep stages will help researchers in many applications to detect sleeprelated diseases and disorders and also in many fields of neuroscience studies such as cognitive impairment and memory consolidation. Since manual sleep staging is time-consuming, subjective, and expensive; designing an efficient automatic sleep scoring system will overcome some of these difficulties. Many studies have proposed automatic sleep staging systems with different methods. In recent years, deep learning methods show their potential in different applications. In this study, we propose SWS and REM detection system by using a deep neural network. In the proposed system we use a kernel-based layer to get the system closer to the manual scoring approach. Also, we use a new method for augmenting EEG signals to prevent overfitting the network. The results show the efficiency of the designed system in SWS and REM detection.