Lewicke, Aaron T.; Sazonov, Edward S.; Schuckers, Stephanie A. C. Proceedings of 2004 IEEE Engineering in Medicine and Biology Conference. San-Francisco, September 2004.
Heart rate variability and actigraphy offer alternative techniques for sleep-wake identification compared to manual sleep scoring from a polysomnograph. The
advantages include high accuracy, simplicity of use, and low intrusiveness. These advantages are valuable for determining sleep-wake states in such highly sensitive groups as infants. A learning vector quantization neural network was tested as a predictor. The accuracy of the neural network was compared
to “gold standard” hand-scored polysomnographs. The prediction results are in agreement with other studies, thus validating the suggested methodology.