Analysis of specificity of fuzzy sets
暂无分享,去创建一个
A comprehensive model for evaluating specificity of fuzzy sets is presented. It is designed in terms of possibility values, independent of the domain of discourse. For a discrete distribution two measures are defined. One is exponential, and the other is logarithmic. The exponential measure is derived from a few intuitively plausible properties of specificity, and the logarithmic measure is dual to nonspecificity in Dempster-Shafer theory. Specificity measures for arbitrary measurable sets are defined as domains of discourse. They can be discrete, finite, or infinite, or, as a measurable set X, have mu (X)< infinity or mu (X)= infinity . The framework for measurable domains is built directly, through an extensive use of a technique borrowed from inequalities of mathematical physics. It consists of rearranging a measurable function according to a prespecified pattern.<<ETX>>
[1] A. Ramer. CONCEPTS OF FUZZY INFORMATION MEASURES ON CONTINUOUS DOMAINS , 1990 .
[2] A. Ramer. Uniqueness of information measure in the theory of evidence , 1987 .
[3] G. Klir,et al. ON MEASURES OF FUZZINESS AND FUZZY COMPLEMENTS , 1982 .
[4] D. Dubois,et al. Properties of measures of information in evidence and possibility theories , 1987 .