Remote Limb Movement Analysis During Sleep by Means of Bioradar

Lack of effective non-contact ways for long-term sleep movements disorders detection, which may indicate the presence of different health and life-threatening conditions, is an up-to-date problem of modern sleep medicine. This paper presents a method for remote long-term sleep movements monitoring based on the analysis of a bioradar signal. The method was validated utilizing data of four volunteers, which underwent a sleep study in a sleep laboratory of Almazov National Medical Research Centre. The proposed method is based on the usage of a long short-term memory network to detect leg movements during sleep. We achieved accuracy and Cohen's kappa of 0.99 and 0.98 for leg movements during sleep classification, respectively. The results might be used while creating new methods for remote detection of sleep movement disorders.