Automated Sleep Staging System Based on Ensemble Learning Model Using Single-Channel EEG Signal

Abstract

Sleep is essential for people health and well-being. However, numerous individuals face sleep problems. These problems can lead to several neurological and physical disorder diseases, and therefore, decrease their overall life quality. Artificial intelligence methods for automated sleep stage classification (ASSC) are a fundamental approach to evaluate and treat this public health challenge. The main contribution of this paper is to present the design and development of an automated sleep staging system based on the ensemble techniques using single-channel of EEG signal. In this study, a novel method is applied for signal preprocessing, feature screening and classification models. In signal preprocessing we obtain the Online Streaming Feature Selection (OSFS). In feature extraction, we obtain a total of 28 features based on both time and frequency domain features and non-linear features. The important contribution of this research work is establishes two-layers an ensembling learning model. The base learning model consists of Random forest (RF), Gradient Boosting Decision Tree (GDBT), and Extreme Gradient Boosting (XGBoost) and the second layer is Logistic Regression. We obtained the ISRUC-Sleep subgroup-III subjects sleep recordings for our proposed experimental work. Comparing with the recent contributions on sleep staging performances, it has seen that our proposed ensemble learning model was reported best sleep staging classification accuracy performance for five sleep stages classification task (CT-5). The overall classification accuracy reported as 96.86% for OSFS selected features with SG-III dataset.KeywordsSleep scoringElectroencephalographyStacking modelMachine learning