Sleep’s depth detection using electroencephalogram signal processing and neural network classification

Abstract

The sleep related diseases became common nowadays and thus sleep stages detection has an important role in the diagnosis of such kinds of diseases. However, conventional sleep stages detection methods face challenges from the complex mathematical models associated with them and the feature extraction processes. In addition, there may be rapid fluctuations between sleep stages which may affect the accurate features extraction and would possibly lead to an inaccurate evaluation of electroencephalogram (EEG) sleep phases. Hence, we suggest an automatic sleep stages classification approach based totally on a neural community, blended with a wavelet-based function extraction method. In this work 4 sleep ranges will be classified, consisting of Awake, Stage 1 + rapid eye movement (REM), Stage two and Slow Wave Stage primarily based only on the EEG signal. In order to validate the efficiency of our algorithm, we used PhysioNet database EEG signals for in vitro tests. After the sleep stages detection, we target the brain computer interface (BCI) design, in order to control some equipment around the subject of study. Actually, our target is to establish the communication between the brain and the external world. Because the sleep stages detection is useful for other areas, like the tiredness detection and drowsiness detection for drivers as well. But in this work, we aim to detect only the sleep stages in an efficient method.