Detection of movement activity and breathing cycles on bioradiolocation signals

This paper presents an algorithm for the detection of movement activity periods and breathing cycles on bioradilocation signals for sleeping subjects. The algorithm was validated using data of 27 subjects without sleep-disordered breathing, who underwent a polysomnography study in a sleep laboratory. The results of manual scoring were used as ground truth. Accuracy, specificity and sensitivity for activity period detection are 90%. Accuracy of the peak detection is 97%, and sensitivity is 98%. Our results will be useful for the development of tools for unobtrusive health and sleep monitoring.