Cluster Validation with Generalized Dunn's Indices

  • Authors:
  • James C. Bezdek;Nikhil R. Pal

  • Affiliations:
  • -;-

  • Venue:
  • ANNES '95 Proceedings of the 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems
  • Year:
  • 1995

Quantified Score

Hi-index 0.00

Visualization

Abstract

Some generalizations of Dunn's index for validation of crisp clusters are discussed. Numerical examples suggest that this index, which uses the standard measures for inter-set distance and set diameter can be improved by using different functions for either or both of these operators.