Abstract
Sleep is a dynamic process which can be described by a finite set of sleep stages. In
contrast to the standard discrete Rechtschaffen and Kales sleep model continuous sleep representation
provided by the Probabilistic Sleep Model allows to take into account the whole
dynamic of the sleep process. However, analysis of the sleep probabilistic curves faces problems
when the time misalignment is present. In this article we highlight the necessity of curves
synchronisation before further analysis. Original and in time aligned sleep probabilistic curves
are transformed into finite dimensional vector space and their ability to predict age or daily
measures is computed. We observed that curves alignment significantly improves the prediction
of the daily measures especially in the case of the REM sleep stage.
Go back