A Constructive Feature Induction Mechanism Founded on Evolutionary Strategies with Fitness Functions Generated on the Basis of Decision Trees

  • Mariusz Wrzesień
  • Wiesław Paja
  • Krzysztof Pancerz
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6954)

Abstract

In the paper, we present a novel approach to calculating a new (extra) attribute (feature) using a constructive feature induction mechanism. The problem being solved is founded on coefficients for values of existing attributes determined empirically using evolutionary strategies with fitness functions based on parameters calculated from decision trees generated for extended decision tables.

Keywords

constructive feature induction mechanism decision trees evolutionary strategies melanoma 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    The UC Irvine Machine Learning Repository, http://archive.ics.uci.edu/ml/
  2. 2.
    Hippe, Z.: Computer database NEVI on endangerment by melanoma. TASK Quarterly 3(4), 483–488 (1999)MathSciNetGoogle Scholar
  3. 3.
    Knap, M.: Research on new algorithms for decision trees generation. Ph.D. thesis, AGH University of Science and Technology, Krakow, Poland (2009) (in Polish)Google Scholar
  4. 4.
    Michalewicz, Z. (ed.): Genetic Algorithms + Data Structures = Evolution Programs. Springer, Heidelberg (1996)MATHGoogle Scholar
  5. 5.
    Michalski, R., Bratko, I., Kubat, M. (eds.): Machine Learning and Data Mining. Methods and Applications. John Wiley & Sons, Chichester (1997)Google Scholar
  6. 6.
    Paja, W., Pancerz, K., Wrzesień, M.: A new hybrid method of generation of decision rules using the constructive induction mechanism. In: Yu, J., Greco, S., Lingras, P., Wang, G., Skowron, A. (eds.) RSKT 2010. LNCS, vol. 6401, pp. 322–327. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Quinlan, J.: C4.5. Programs for machine learning. Morgan Kaufmann Publishers, San Francisco (1993)Google Scholar
  8. 8.
    Varmuza, K.: Chemometrics: Multivariate view on chemical problems. In: Schleyer, P., Allinger, N., Clark, T., Gasteiger, J., Kollman, P., Schaefer III, H., Schreiner, P. (eds.) The Encyclopedia of Computational Chemistry, vol. 1, pp. 346–366. John Wiley & Sons, Chichester (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mariusz Wrzesień
    • 1
  • Wiesław Paja
    • 1
  • Krzysztof Pancerz
    • 1
  1. 1.University of Information Technology and ManagementRzeszówPoland

Personalised recommendations