Automated Classification of Sleep Stages Using Single-Channel EEG

The main contribution of this paper is to present a novel approach for classifying the sleep stages based on optimal feature selection with ensemble learning stacking model using single-channel EEG signals.To find suitable features from extracted vector, we obtained ReliefF (ReF), Fisher Score (FS) and Online Stream Feature Selection (OSFS) algorithms.The proposed research work was performed two different subgroups data ISRUC-Sleep dataset. experimental results methodology signify that signal superior other machine classification models overall accuracies 97.93%, 97%, 95.96% subgroup-I (SG-I) similarly achieved an 98.16%, 98.78%, 95.26% subgroup-III (SG-III) FS, ReF OSFS respectively.