A Dynamic HMM for On-line Segmentation of Sequential Data

Part of Advances in Neural Information Processing Systems 14 (NIPS 2001)

Bibtex Metadata Paper


Jens Kohlmorgen, Steven Lemm


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 ap(cid:173) proaches, our method processes the data incrementally and without any training of internal parameters. We use an HMM with a dy(cid:173) namically 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 pro(cid:173) cess 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.