Information theory applications in soft computing

Abstract

An overview of information theory metrics and the ranges of their values for extreme probability cases is provided. Imprecise database models including similarity based fuzzy models and rough set models are described. Various entropy measures for these database models’ content and responses to querying is provided. Aggregation of uncertainty representations are also considered. In particular the possibilistic conditioning of probability aggregation is examined. Information measures are used to compare the resultant conditioned probability to the original probability for three cases of possibility distributions.