A Comparative Study of Clustering Methods for Long Time-Series Medical Databases

  • Shusaku Tsumoto
  • Shoji Hirano
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3131)


This paper presents a comparative study of methods for clustering long-term temporal data. We split a clustering procedure into two processes: similarity computation and grouping. As similarity computation methods, we employed dynamic time warping (DTW) and multiscale matching. As grouping methods, we employed conventional agglomerative hierarchical clustering (AHC) and rough sets-based clustering (RC). Using various combinations of these methods, we performed clustering experiments of the hepatitis data set and evaluated validity of the results. The results suggested that (1) complete-linkage (CL) criterion outperformed average-linkage (AL) criterion in terms of the interpret-ability of a dendrogram and clustering results, (2) combination of DTW and CL-AHC constantly produced interpretable results, (3) combination of DTW and RC would be used to find the core sequences of the clusters, (4) multiscale matching may suffer from the treatment of ’no-match’ pairs, however, the problem may be eluded by using RC as a subsequent grouping method.


Cluster Method High Scale Dynamic Time Warping Planar Curf Agglomerative Hierarchical Cluster 
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.
    Keogh, E.: Mining and Indexing Time Series Data. Tutorial at the, IEEE International Conference on Data Mining (2001)Google Scholar
  2. 2.
    Chu, S., Keogh, E., Hart, D., Pazzani, M.: Iterative Deepening Dynamic Time Warping for Time Series. In: proceedings of the second SIAM International Conference on Data Mining (2002)Google Scholar
  3. 3.
    Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series.In: Proceedings of AAAI Workshop on Knowledge Discovery in Databases pp. 359-370 (1994)Google Scholar
  4. 4.
    Hirano, S., Tsumoto, S.: Mining Similar Temporal Patterns in Long Time-series Data and Its Application to Medicine. In: Proceedings of the IEEE 2002 International Conference on Data Mining, pp. 219–226 (2002)Google Scholar
  5. 5.
    Ueda, N., Suzuki, S.: A Matching Algorithm of Deformed Planar Curves Using Multiscale Convex/Concave Structures. IEICE Transactions on Information and Systems J73-D-II(7), 992–1000 (1990)Google Scholar
  6. 6.
    Mokhtarian, F., Mackworth, A.K.: Scale-based Description and Recognition of planar Curves and Two Dimensional Shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-8(1), 24–43 (1986)CrossRefGoogle Scholar
  7. 7.
  8. 8.
    Everitt, B.S., Landau, S., Leese, M.: Cluster Analysis, 4th edn. Arnold Publishers (2001)Google Scholar
  9. 9.
    Hirano, S., Tsumoto, S.: An Indiscernibility-based Clustering Method with Iterative Refinement of Equivalence Relations. Journal of Advanced Computational Intelligence and Intelligent Informatics (2003) (in press)Google Scholar
  10. 10.
    Lowe, D.G.: Organization of Smooth Image Curves at Multiple Scales. International Journal of Computer Vision 3, 119–130 (1980)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Shusaku Tsumoto
    • 1
  • Shoji Hirano
    • 1
  1. 1.Department of Medical InformaticsShimane University, School of MedicineIzumoJapan

Personalised recommendations