Segmentation and identification of drifting dynamical systems

A method for the analysis of nonstationary time series with multiple operating modes is presented. In particular, it is possible to detect and to model a switching of the dynamics and also a less abrupt, time consuming drift from one mode to another. This is achieved by an unsupervised algorithm that segments the data according to inherent modes, and a subsequent search through the space of possible drifts. An application to physiological wake/sleep data demonstrates that analysis and modeling of real-world time series can be improved when the drift paradigm is taken into account. In the case of wake/sleep data, we hope to gain more insight into the physiological processes that are involved in the transition from wake to sleep.