Induction of classification rules from imperfect data

  • Ning Shan
  • Howard J. Hamilton
  • Nick Cercone
Communications Session 1B Learning and Discovery Systems
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1079)


We present a method for inducing classification rules from imperfect data using an extended version of the rough set model. The salient feature of our method is that it makes use of the statistical information inherent in the information system. Our framework describes the overall induction task in terms of two key subtasks: approximate classification and rule generation.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Katzberg, J. and Ziarko, W., “Variable Precision Rough Sets with Asymmetric Bounds,” in Ziarko, W. (ed.), Rough Sets, Fuzzy Sets and Knowledge Discovery, Springer-Verlag, 1994, pp. 167–177.Google Scholar
  2. 2.
    Michalski, R.S., Carbonell J.G., and Mitchell, T.M. (eds.), Machine Learning: An Artificial Intelligence Approach, vols 1–2. Morgan Kaufmann, San Mateo, California, 1983 and 1986.Google Scholar
  3. 3.
    Pawlak, Z., Rough Sets: Theoretical Aspects of Reasoning About Data. Kluwer Academic, 1991.Google Scholar
  4. 4.
    Pawlak Z., and Wong, S.K.M., and Ziarko, W., “Rough Sets: Probabilistic Versus Deterministic Approaches,” International Journal of Man-Machine Studies, 29(1):81–95, 1988.Google Scholar
  5. 5.
    Quinlan, J. R., “Induction of Decision Trees”, Machine Learning, 1(1):81–106, 1986.Google Scholar
  6. 6.
    Quinlan, J. R., C4.5 Programs for Machine Learning, Morgan Kaufmann, San Mateo, California, 1992.Google Scholar
  7. 7.
    Shan, N., Hu, X., Ziarko, W., and Gercone, N., “A Generalized Rough Sets Model,” Proc. of the 3rd Pacific Rim International Conference on Artificial Intelligence, Beijing, China. 1994, pp. 437–443.Google Scholar
  8. 8.
    Shan, N., Rule Discovery From Data Using Decision Matrices, M.Sc. Thesis, Dept. of Computer Science, University of Regina, 1995.Google Scholar
  9. 9.
    Wong, S.K.M. and Ziarko, W., A Probabilistic Model of Approximate Classification in Inductive Learning, University of Regina, Technical Report CS-88-01, 1988.Google Scholar
  10. 10.
    Zhang, J., “Selecting Typical Instances in Instance-Based Learning,” Proc. of the 9th International Workshop on Machine Learning, pp. 474–479, 1992.Google Scholar
  11. 11.
    Ziarko, W. and Shan, N., “A method for computing all maximally general rules in attribute-value systems,” Computational Intelligence, in press.Google Scholar
  12. 12.
    Ziarko, W., “Variable Precision Rough Set Model,” Journal of Computer and System Sciences, 46(1):39–59, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Ning Shan
    • 1
  • Howard J. Hamilton
    • 1
  • Nick Cercone
    • 1
  1. 1.Department of Computer ScienceUniversity of ReginaReginaCanada

Personalised recommendations