Recurrent Predictive Models for Sequence Segmentation

  • Saara Hyvönen
  • Aristides Gionis
  • Heikki Mannila
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4723)


Many sequential data sets have a segmental structure, and similar types of segments occur repeatedly. We consider sequences where the underlying phenomenon of interest is governed by a small set of models that change over time. Potential examples of such data are environmental, genomic, and economic sequences. Given a target sequence and a (possibly multivariate) sequence of observation values, we consider the problem of finding a small collection of models that can be used to explain the target phenomenon in a piecewise fashion using the observation values. We assume the same model will be used for multiple segments. We give an algorithm for this task based on first segmenting the sequence using dynamic programming, and then using k-median or facility location techniques to find the optimal set of models. We report on some experimental results.


Bayesian Information Criterion Facility Location Facility Location Problem Minimum Description Length Prediction Task 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bellman, R.: On the approximation of curves by line segments using dynamic programming. Communications of the ACM 4(6) (1961)Google Scholar
  2. 2.
    Bingham, E., et al.: Segmentation and dimensionality reduction. In: Jonker, W., Petković, M. (eds.) SDM 2006. LNCS, vol. 4165, Springer, Heidelberg (2006)Google Scholar
  3. 3.
    Charikar, M., Guha, S.: Improved combinatorial algorithms for the facility location and k-median problems. In: FOCS (1999)Google Scholar
  4. 4.
    Feige, U.: A threshold of ln n for approximating set cover. Journal of the ACM 45(4), 634–652 (1998)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Garey, M., Johnson, D.S.: Computers and Intractability: A Guide to the Theory of NP-Completeness. W.H. Freeman (1979)Google Scholar
  6. 6.
    Gionis, A., Mannila, H.: Finding recurrent sources in sequences. In: RECOMB (2003)Google Scholar
  7. 7.
    Guha, S., Koudas, N., Shim, K.: Data-streams and histograms. In: STOC (2001)Google Scholar
  8. 8.
    Gwadera, R., Gionis, A., Mannila, H.: Optimal segmentation using tree models. In: ICDM (2006)Google Scholar
  9. 9.
    Hand, D., Mannila, H., Smyth, P.: Principles of Data Mining. The MIT Press, Cambridge (2001)Google Scholar
  10. 10.
    Himberg, J., Korpiaho, K., Mannila, H., Tikanmaki, J., Toivonen, H.: Time series segmentation for context recognition in mobile devices. In: ICDM (2001)Google Scholar
  11. 11.
    Hinds, D.A., et al.: Wholegenome patterns of common DNA variation in three human populations. Science 307, 1072–1079 (2005)CrossRefGoogle Scholar
  12. 12.
    Hochbaum, D.: Heuristics for the fixed cost median problem. Mathematical Programming 222, 148–162 (1982)CrossRefMathSciNetGoogle Scholar
  13. 13.
    Hyafil, L., Rivest, R.L.: Constructing optimal binary decision trees is np-complete. Information Processing Letters 5, 15–17 (1976)MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Hyvönen, S., et al.: A look at aerosol formation using data mining techniques. Atmospheric Chemistry and Physics 5, 3345–3356 (2005)CrossRefGoogle Scholar
  15. 15.
    Keogh, E.J., et al.: Locally adaptive dimensionality reduction for indexing large time series databases. In: SIGMOD (2001)Google Scholar
  16. 16.
    Kleinberg, J.: Bursty and hierarchical structure in streams. In: KDD (2002)Google Scholar
  17. 17.
    Koivisto, M., et al.: An MDL method for finding haplotype blocks and for estimating the strength of haplotype block boundaries. In: PSB (2003)Google Scholar
  18. 18.
    Li, W.: DNA segmentation as a model selection process. In: RECOMB (2001)Google Scholar
  19. 19.
    Lin, J.-H., Vitter, J.S.: ε-approximations with minimum packing constraint violation. In: STOC (1992)Google Scholar
  20. 20.
    Rabiner, L.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE 77, 257–286 (1989)CrossRefGoogle Scholar
  21. 21.
    Sarawagi, S.: Efficient inference on sequence segmentation models. In: ICML (2006)Google Scholar
  22. 22.
    Terzi, E., Tsaparas, P.: Efficient algorithms for sequence segmentation. In: SDM (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Saara Hyvönen
    • 1
  • Aristides Gionis
    • 1
  • Heikki Mannila
    • 1
  1. 1.Helsinki Institute for Information Technology, Department of Computer Science, University of HelsinkiFinland

Personalised recommendations