Advertisement

Robust Pseudo-hierarchical Support Vector Clustering

  • Michael Sass Hansen
  • Karl Sjöstrand
  • Hildur Ólafsdóttir
  • Henrik B. W. Larsson
  • Mikkel B. Stegmann
  • Rasmus Larsen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)

Abstract

Support vector clustering (SVC) has proven an efficient algorithm for clustering of noisy and high-dimensional data sets, with applications within many fields of research. An inherent problem, however, has been setting the parameters of the SVC algorithm. Using the recent emergence of a method for calculating the entire regularization path of the support vector domain description, we propose a fast method for robust pseudo-hierarchical support vector clustering (HSVC). The method is demonstrated to work well on generated data, as well as for detecting ischemic segments from multidimensional myocardial perfusion magnetic resonance imaging data, giving robust results while drastically reducing the need for parameter estimation.

Keywords

Adjacency Matrix Regularization Parameter Ischemic Segment Discrimination Feature Support Vector 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.

References

  1. 1.
    Ben-Hur, A., Horn, D., Siegelmann, H.T., Vapnik, V.: Support vector clustering. Journal of Machine Learning 2, 125–137 (2001)CrossRefGoogle Scholar
  2. 2.
    Tax, D.M.J., Duin, R.P.W.: Support vector domain description. Pattern Recognition Letters 20, 1191–1199 (1999)CrossRefGoogle Scholar
  3. 3.
    Ben-Hur, A., Horn, D., Siegelmann, H.T., Vapnik, V.: A support vector clustering method. In: Proceedings of conference on Advances in Neural Information Processing Systems (2001)Google Scholar
  4. 4.
    Yang, J., Estivill-Castro, V., Chalup, S.K.: Support vector clustering through proximity graph modelling (2002)Google Scholar
  5. 5.
    Sjöstrand, K., Larsen, R.: The Entire Regularization Path for the Support Vector Domain Description. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 241–248. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  6. 6.
    Ólafsdóttir, H., Stegmann, M.B., Larsson, H.B.W.: Automatic Assessment of Cardiac Perfusion MRI. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3217, pp. 1060–1061. Springer, Heidelberg (2004)Google Scholar
  7. 7.
    Stegmann, M.B., Ólafsdóttir, H., Larsson, H.B.W.: Unsupervised motion-compensation of multi-slice cardiac perfusion mri. Medical Image Analysis 9(4), 394–410 (2005)CrossRefGoogle Scholar
  8. 8.
    Hansen, M.S., Ólafsdóttir, H., Sjöstrand, K., Erbou, S.G., Larsson, H.B., Stegmann, M.B., Larsen, R.: Ischemic segment detection using the support vector domain description. In: The International Society for Optical Engineering (SPIE) (ed.): International Symposium on Medical Imaging (Feb. 2007)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Michael Sass Hansen
    • 1
  • Karl Sjöstrand
    • 1
  • Hildur Ólafsdóttir
    • 1
  • Henrik B. W. Larsson
    • 2
  • Mikkel B. Stegmann
    • 3
  • Rasmus Larsen
    • 1
  1. 1.Informatics and Mathematical Modelling, Technical University of Denmark, LyngbyDenmark
  2. 2.Hospital of Glostrup, GlostrupDenmark
  3. 3.3shape A/S, CopenhagenDenmark

Personalised recommendations