Sleep Apnea Patient Monitoring Using Continuous-wave Radar

Abstract

Sleep apnea syndrome is a prevalent condition among the elderly people that is potentially dangerous and causes fatal complications. However, this syndrome is often undiagnosed since most patients do not know they have this condition because it only occurs during sleep. In this study, we proposed a non-contact sleep monitoring solution. The system used the support vector machines (SVM) model with three classes classification. The monitoring results give the ratios of three time durations, including the normal sleeping time, body movement time, and time of cessation of breathing. The training model obtained an accuracy of 96.1%, and the model was applied to a patient with apnea syndrome in Yokohama Hospital, Japan, showing consistency with the hospital recordings.