This paper deals with the analysis of sleep quality, which involves a non-invasive sleep stage detection method with home deployability. Some physiological signals, such as heart rate, heart rate variation, and the number of times the subject rolled over, are collected to determine the sleep stage. A fuzzy inference system is adopted to evaluate the division of sleep stage. Then, a preliminary sleep depth is calculated. Furthermore, a finite-state machine is developed to detect the sleep stage changes. The difference between our research and other existing studies is that, first, both the pressure sensors and the heart rate device are employed; then, the fuzzy inference and a finite-state machine are introduced, which give us a higher precision than the traditional methods to evaluate the sleep stage. The experimental results show that the proposed method can well evaluate the sleep quality that is almost consistent with a polysomnography test. The latter is currently recognized as the best way to measure sleep quality, which, however, requires a variety of monitoring sensors and has to be performed by the nursing staff in a professional setting. The reported approach can be used for monitoring sleep quality or sleep disorder screening at home. INDEX TERMS Sleep analysis, non-invasive, fuzzy inference system, finite state machine.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations –citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.