Advertisement

Discovering Dynamics Using Bayesian Clustering

  • Paola Sebastiani
  • Marco Ramoni
  • Paul Cohen
  • John Warwick
  • James Davis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1642)

Abstract

This paper introduces a Bayesian method for clustering dynamic processes and applies it to the characterization of the dynamics of a military scenario. The method models dynamics as Markov chains and then applies an agglomerative clustering procedure to discover the most probable set of clusters capturing the different dynamics. To increase efficiency, the method uses an entropy-based heuristic search strategy.

Keywords

Time Series Hide Markov Model Dynamic Time Warping Bayesian Cluster Multivariate Time Series 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    M. Atkin, D. L. Westbrook, P. R. Cohen, and G D. Jorstad. AFS and HAC: The last agent development toolkit you’ll ever need. In Proceedings of the AAAI Workshop on Software Tools for Developing Agents. American Association for Artificial Intelligence, 1998.Google Scholar
  2. [2]
    G. F. Cooper and E. Herskovitz. A Bayesian method for the induction of probabilistic networks from data. Machine Learning, 9:309–347, 1992.zbMATHGoogle Scholar
  3. [3]
    L. Firoiu and P. R. Cohen. Experiments in abstracting from robot sensor data using hidden markov models. In The Third Symposium on Intelligent Data Analysis. Springer Verlag, Berlin, 1999.Google Scholar
  4. [4]
    I. L. MacDonald and W. Zucchini. Hidden Markov and other Models for discretevalues Time Series. Chapman and Hall, London, 1997.Google Scholar
  5. [5]
    T. Oates. Identifying distinctive subsequences in multivariate time series by clustering. In Proceedings of the Sixteenth International Conference on Machine Learning. Morgan Kaufmann Publishers, Inc., 1999. To appear.Google Scholar
  6. [6]
    L. R. Rabiner. A tutorial on Hidden Markov Models and selected applications in speech recognition. In Proceedings of the IEEE, volume 77, pages 257–285, 1989.CrossRefGoogle Scholar
  7. [7]
    G. Ridgeway and S. Altschuler. Clustering finite discrete markov chains. In Proceedings of the Joint Statistical Meetings, Section on Physical and Engineering Sciences. ASA Press, 1998.Google Scholar
  8. [8]
    S. M. Ross. Stochastic Processes. Wiley, New York, 1996.zbMATHGoogle Scholar
  9. [9]
    P. Sebastiani, M. Ramoni, and P. R. Cohen. Bayesian unsupervised Classification of times series. Technical report, KMI, The Open University, 1999. Available at http://kmi.open.ac.uk/techreports/KMi-TR-76.
  10. [10]
    P. Sebastiani, M. Ramoni, and P. R. Cohen. Unsupervised Classification of sensory input in a mobile robot. In Proceedings of the IJCAI Workshop on Neural, Symbolic and Reinforcement Methods for Sequence Learning. 1999. To appear.Google Scholar
  11. [11]
    P. Smyth. Clustering sequences with hidden Markov models. In M. C. Mozer, M. I. Jordan, and T. Petsche,editors, Advances in Neural Information Precessing, pages 72–93. MIT Press, Cambridge, MA, 1997.Google Scholar
  12. [12]
    P. Smyth. Probabilistic model-based clustering of multivariate and sequential data. In Proceedings of Artificial Intelligence and Statistics 1999, pages 299–304. Morgan Kaufman, San Mateo CA, 1999.Google Scholar
  13. [13]
    R. St. Amant and P. R. Cohen. Evaluation of a semi-autonomous assistant for exploratory data analysis. In Proceedings of the First International Conference on Autonomous Agents, pages 355–362, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Paola Sebastiani
    • 1
  • Marco Ramoni
    • 2
  • Paul Cohen
    • 3
  • John Warwick
    • 3
  • James Davis
    • 3
  1. 1.Statistics DepartmentThe Open UniversityMilton KeynesUK
  2. 2.Knowledge Media InstituteThe Open UniversityMilton KeynesUK
  3. 3.Department of Computer ScienceUniversity of MassachusettsAmherstUSA

Personalised recommendations