Partitional Cluster Analysis with Genetic Algorithms: Searching for the Number of Clusters

  • J. A. Lozano
  • P. Larrañaga
  • M. Graña
Conference paper
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)

Summary

In this article we deal with the problem of searching for the number of clusters in partitional clustering in R 2. We set up the problem as an optimization problem by giving a real function on the different partitions that is optimized when the number of clusters and the classes are the most natural. We use the Genetic Algorithm for optimizing this function. The algorithm has been applied to the well-known Ruspini data and to synthetic cally generated datasets, with different cluster numbers and underlying distributions. The results are encouraging.

Keywords

Genetic Algorithm Search Space Convex Hull Travel Salesman Problem Cluster Problem 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Babu, G.P. and Nlurty, M.N. (1994): Clustering with evolution strategies, Pattern Recognition, 27, 2, 321–329.CrossRefGoogle Scholar
  2. Bezdek, J.C. et al. (1994): Genetic Algorithm Guided Clustering, In: Proc. of The First IEEE Conference on Evolutionary Computation, 34–40.Google Scholar
  3. Bozdogan. H. (1994): Choosing the number of clusters; subset selection of variables, and outlier detection in the standard mixture-model cluster analysis, In: Diday E., Lechevallier Y., Schader NI., Bertrand P. and Burtschy B. (eds.), New Approaches in Classification and Data Analysis, Springer-Verlag, 169–177.Google Scholar
  4. Bhuyan, J.N. et al. (1991): Genetic Algorithms for clustering with an ordered representation, In: Belew and Booker (eds.), proceedings of the Fourch international Conference on Gnetic Algorthms, 408–415, Morgan Kaufmann.Google Scholar
  5. Celeux, G. and Soromenho, G. (1993): An entropy criterion for assesing the number of clusters in a mixture model, Technical Report 1874 INRIA, France.Google Scholar
  6. Cucchiara, R (1993): Analysis and comparison of different genetic models for the clustering problem in image analysis, In: Albrecht R.F., Reeves C.R. and Steele N.C. (eds.), Artificial Neural Networks and Genetic Algorithms, Springer-Verlag, 423–427.Google Scholar
  7. Everitt, B.S (1974): Cluster Analysis, John Wiley & Sons, Inc.Google Scholar
  8. Goldberg, D.E. (1989): Genetic Algorithms in Search, Optimization, Machine Learning, Addison-Wesley.Google Scholar
  9. Gordon, A.D. (1995): Test for asessing clusters, Statistics in Transition, 2, 207–217.Google Scholar
  10. Hardy, A. (1994): An examination of procedures for determining the number of clusters in a data set, In: Diday E., Lechevallier Y., Schader NI., Bertrand P. and Burtschy B. (eds.), New Approaches in Classification and Data Analysis, Springer-Verlag, 178–185.Google Scholar
  11. Hartigan, J.A. (1975): Clustering Algorithms, John Wiley & Sons, New York. Jain, A.Ií. and Dubes, R.C. ( 1988 ): Algorithms for Clustering Data, Prentice Hall.Google Scholar
  12. Jones, D.R. and Beltramo, M.A. (1993): Solving partitioning problems with Genetic Algorithms, In Albrecht R.F., Reeves C.R and Steele N.C. (eds.), Artificial Neural Networks and Genetic Algorithms, Springer-Verlag, 423–427.Google Scholar
  13. Krovi, R. (1991): Genetic Algorithms for clustering: A preliminary investigation, In: Proceedings of the Twenty-Fifth International Conference on System Sciences, 4, 540–544.Google Scholar
  14. Larraüaga, P. et al. (1996): Learning Bayesian Networks Structures by Searching for theGoogle Scholar
  15. Best Ordering with Genetic Algorithms, IEEE Transactions on Systems Alan and Cybernetics, 26, 4. In press.Google Scholar
  16. Lozano, J.A. et al. (1995): Genetic Algorithms: Bridging the Convergence Gap, submitted to Evolutionary Computation.Google Scholar
  17. Luchian, S. et al. (1994): Evolutionary automated classification, In: Proc. of The FirstGoogle Scholar
  18. IEEE Conference on Evolutionary Computation, 585–589.Google Scholar
  19. Rasson, J.P. and hubushishi, T. (1994): The gap test: an optimal method for determining the number of natural classes in cluster analysis, In Diday E., Lechevallier Y., Schader M., Bertrand P. and Burtschy B. (eds.), New Approaches in Classification and Data Analysis, Springer-Verlag, 186–193.Google Scholar
  20. Whitley, D. and Kauth. J. (1988): Genitor: A different Genetic Algorithm, In: Proceedings of the Rocky Jfoun.tain. Conference on Artificial Intelligence, 2, 189–214.Google Scholar

Copyright information

© Springer Japan 1998

Authors and Affiliations

  • J. A. Lozano
    • 1
  • P. Larrañaga
    • 1
  • M. Graña
    • 1
  1. 1.Dept. of Computer Science and Artificial IntelligenceUniversity of the Basque CountrySan SebastiánSpain

Personalised recommendations