Author :
Domingues, A. ; Paiva, T. ; Sanches, J.M.
Author_Institution :
Bioeng. Dept., Tech. Univ. of Lisbon, Lisbon, Portugal
Abstract :
The automatic computation of the hypnogram and sleep Parameters, from the data acquired with portable sensors, is a challenging problem with important clinical applications. In this paper, the hypnogram, the sleep efficiency (SE), rapid eye movement (REM), and nonREM (NREM) sleep percentages are automatically estimated from physiological (ECG and respiration) and behavioral (Actigraphy) nocturnal data. Two methods are described; the first deals with the problem of the hypnogram estimation and the second is specifically designed to compute the sleep parameters, outperforming the traditional estimation approach based on the hypnogram. Using an extended set of features the first method achieves an accuracy of 72.8%, 77.4%, and 80.3% in the detection of wakefulness, REM, and NREM states, respectively, and the second an estimation error of 4.3%, 9.8%, and 5.4% for the SE, REM, and NREM percentages, respectively.
Keywords :
biomedical equipment; circadian rhythms; electrocardiography; feature extraction; medical signal processing; neurophysiology; parameter estimation; pneumodynamics; portable instruments; psychology; signal classification; sleep; ECG data; NREM sleep percentages; NREM state detection; actigraphy nocturnal data; activity data; automatic hypnogram parameter computation; automatic parameter estimation; automatic sleep parameter computation; behavioral data; cardiovascular data; clinical applications; estimation error; feature set; hypnogram estimation; nonREM sleep percentages; physiological data; portable sensors; rapid eye movement sleep percentages; respiration data; sleep efficiency percentages; wakefulness detection; Accuracy; Estimation; Feature extraction; Heart rate variability; Sleep apnea; Standards; Hypnogram estimation; rapid eye movement (REM)/nonREM (NREM) percentage; sleep efficiency (SE); sleep parameters;
