Sleep stages classification based on time-frequency features of EEG signal

Sleep scoring is one of the most important diagnostic methods in psychiatry, neurology and diagnosis. Sleep staging is a time consuming and difficult task undertaken by sleep experts. This study aims to identify a method which would classify sleep stages automatically and with a high degree of accuracy. In this work, an efficient automated new approach for sleep stage identification based on the R&K standard is presented, and aims at automatic identification of various sleep stages like, wakefulness, sleep stages 1, 2, 3, 4 and REM sleep from single channel EEG signal. The propose approach employs time–frequency analysis in base and some other analysis for feature extraction from a single lead EEG channel of twenty subjects and the classification of the extracted features was done using SVM classifier. The result demonstrates that the proposed classifier using this features extracted from characteristic waves of EEG signals can classify sleep stages more efficiently and accurately that minimum accuracy is %72 and total accuracy is up to 83.99 percentage.