A Comprehensive Survey and New Investigation on Sleep Disorder Detection Using EEG Signal

Abstract

In the current scenario, sleep-related problems increase day by day, which is a problem of public health, where lot of many people are suffering from sleep disorder that affects their normal day-to-day life. A proper scoring of the entire sleep stages can give clinical information regarding diagnosis of sleep disorder. Some traditional methods were available for detection of sleep disorder, but traditional visual scoring of the entire sleep is time-consuming and highly dependent on experts experiences. The limitations of manual sleep stage scoring have escalated the demand for developing automatic sleep stage scoring, which reduces the manual tasks and improves stage detection and classification accuracy. There are several stable physiological stages that the human brain goes through during sleep. Currently, many biomedical signals such as electroencephalogram (EEG), electrocardiogram (ECG), electromyogram (EMG), and electrooculogram (EOG) offer useful details for clinical setups that are used in identifying sleep disorders. The aim of this paper is to survey the progress and different challenges in various existing electroencephalogram (EEG) signal-based methods used for identification of different sleep stages. The analysis of EEG can yield much useful information about brain function, including indications of sleep stage. There are two standards available for scoring R&K and AASM, and according to Rechtschaffen and Kales (R&K) rule, EEG signal is analyzed by dividing each signal into periods of 30 s small parts called segments. For this purpose, automatic sleep stage classification is used which reduces the manual tasks and improves stage detection and classification accuracy. Sleep stage detection comprises detection and classification of the data into classes such as awake, NREM, and REM stages. Sleep identification involves feature extraction from each segment, classification of each selected features, and ensemble of result of each classifier. This paper reviews the system for sleepiness detection using EEG signal.KeywordsSleep stagingEEGAutomatic sleep stage classification