Fuzzy Representations in Rough Set Approximations

  • Michael Hadjimichael
  • S. K. Michael Wong
Conference paper
Part of the Workshops in Computing book series (WORKSHOPS COMP.)

Abstract

Frequently, knowledge systems represent information crisply. That is, for a given object in the database, and a given property (attribute-value pair), there is no uncertainty whether or not the object has that property. This certainty restricts expressive power. Therefore, we present here an approach to knowledge representation and rough set-based inductive learning using a fuzzy set representation of information. Specifically, we introduce the Fuzzy Property Set model, which is an enhancement of the Property Set model in which each object is represented by a collection of properties. In this fuzzy enhancement, it is possible to denote the degree to which an object has a particular property. Fuzzy rough set upper and lower approximations are defined using this model, as a basis for the inductive learning of concepts. Various similarity and distance measures can then be used to rank objects according their similarity to the upper or lower concept approximations.

Keywords

Fuzzy Representation Object Description Atomic Concept Fuzzy Property Knowledge Representation System 
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. [1]
    M. Hadjimichael, S.K.M. Wong, “Quantifying Inductive Learning Generalization,” submitted for publication, 1993.Google Scholar
  2. [2]
    R. S. Michalski, J. B. Larson, “Selection of most representative training examples and incremental generation of VL1 hypothesis: the underlying methodology and the description of programs ESEL and AQ11,” Report No. 867, Department of Computer Science, University of Illinois, Urbana, Illinois, 1978.Google Scholar
  3. [3]
    A. Motro, “Accommodating Imprecision in Database Systems: Issues and Solutions,” SIGMOD Record,19, n4, 69–74, 1990Google Scholar
  4. [4]
    Z. Pawlak, “Rough Sets,” International Journal of Computer and Information Sciences, 11, 341–356, 1984.CrossRefMathSciNetGoogle Scholar
  5. [5]
    X.T. Peng, A. Kandel, “Concepts, Rules, and Fuzzy Reasoning: A Factor Space Approach,” IEEE Trans. Syst., Man, and Cyber., 21, nl, 194–205, 1991.CrossRefMATHMathSciNetGoogle Scholar
  6. [6]
    H. Prade, C. Testemale, “Generalizing Database Relational Algebra for the Treatment of Incomplete or Uncertain Information and Vague Queries,” Information Sciences, 34, 115–143, 1984.CrossRefMATHMathSciNetGoogle Scholar
  7. [7]
    J.R. Quinlan, “Learning efficient classification procedures and the application to chess end-games,” Machine Learning, an Artificial Intelligence Approach. (eds. Michalski, Carbonell, Mitchell), Tioga Publishing Co., Palo Alto, 1983.Google Scholar
  8. [8]
    L. Wang, J.M. Mandel, “Generating Fuzzy Rules by Learning from Examples,” IEEE Trans. Syst., Man, and Cyber., 2, n6, 1414–1427, 1992.CrossRefGoogle Scholar
  9. [9]
    S.K.M. Wong, Y. Yao, “A Statistical Similarity Measure,” Proc. 10th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, New Orleans, 3–12, 1987.Google Scholar
  10. [10]
    L. A. Zadeh, “Fuzzy Sets,” Inf. Control, 8, 338–353, 1965.CrossRefMATHMathSciNetGoogle Scholar
  11. [11]
    M. Zemankova, A. Kandel, “Implementing Imprecision in Information Systems,” Information Sciences, 37, 107–141, 1985.CrossRefMATHGoogle Scholar

Copyright information

© British Computer Society 1994

Authors and Affiliations

  • Michael Hadjimichael
    • 1
  • S. K. Michael Wong
    • 1
  1. 1.Department of Computer ScienceUniversity of ReginaReginaCanada

Personalised recommendations