\Lambda

Abstract We propose a novel method for the analysis of sequential data that exhibits an inherent mode switching. In particular, the data might be a non-stationary time series from a dynamical system that switches between multiple operating modes. Unlike other approaches, our method processes the data incrementally and without any training of internal parameters. We use an HMM with a dynamically changing number of states and an on-line variant of the Viterbi algorithm that performs an unsupervised segmentation and classification of the data on-the-fly, i.e. the method is able to process incoming data in real-time. The main idea of the approach is to track and segment changes of the probability density of the data in a sliding window on the incoming data stream. The usefulness of the algorithm is demonstrated by an application to a switching dynamical system. 1 Introduction Abrupt changes can occur in many different real-world systems like, for example, in speech, in climatological or industrial processes, in financial markets, and also in physiological signals (EEG/MEG). Methods for the analysis of time-varying dynamical systems are therefore an important issue in many application areas. In [12], we introduced the annealed competition of experts method for time series from nonlinear switching dynamics, related approaches were presented, e.g., in [2, 6, 9, 14]. For a brief review of some of these models see [5], a good introduction is given in [3]. We here present a different approach in two respects. First, the segmentation does not depend on the predictability of the system. Instead, we merely estimate the density distribution of the data and track its changes. This is particularly an improvement for systems where data is hard to predict, like, for example, EEG recordings [7] or financial data. Second, it is an on-line method. An incoming data stream is processed incrementally while keeping the computational effort limited by a fixe