A machine learning approach using EEG signals to measure sleep quality

Abstract

Sleep quality has a vital effect on good health and well-being throughout a life. Getting enough sleep at the right times can help protect mental health, physical health, quality of life, and safety. In this study, an electroencephalography (EEG)-based machine-learning approach is proposed to measure sleep quality. The advantages of this approach over standard Polysomnography (PSG) method are: 1) it measures sleep quality by recognizing three sleep categories rather than five sleep stages, thus higher accuracy can be expected; 2) three sleep categories are recognized by analyzing EEG signals only, so the user experience is improved because fewer sensors are attached to the body during sleep. Using quantitative features obtained from EEG signals, we developed a new automatic sleep-staging framework that consists of a multi-class support vector machine (SVM) classification based on a decision tree approach. We used polysomnographic data from PhysioBank database to train and evaluate and test the performance of the framework, where the sleep stages have been visually annotated. The results demonstrated that the proposed approach achieves high classification performance, which helps to measure sleep quality accurately. This framework can provide a robust and accurate sleep quality assessment that helps clinicians to determine the presence and severity of sleep disorders, and also evaluate the efficacy of treatments.