And the second the cho-lesterol total

46 CASE REPRESENTATION AND INDEXING

Since the price $55,000 has the highest membership value in the fuzzy set‘‘middle,’’ we could represent the price of the car as medium. Therefore, alterna-tively one can represent the attribute ‘‘price of the car’’ as a fuzzy set ‘‘middle’’with the corresponding membership value.

The theory of rough sets provides a new mathematical framework for analysis of data that are imprecise, vague, and uncertain. The main notion of rough sets is that if objects are similar or indiscernible in a given information system, the same set of information can be used to characterize them. Therefore, there may exist some objects that cannot be classified with certainty as members of the set or of its com-plement. In a rough set–theoretic approach, each vague concept is characterized by a pair of precise concepts (called the lower and upper approximations of the vague concept). Rough set approaches [4–6] deal primarily with the classification of data and synthesizing approximations of concepts. These approaches are also used to construct models that represent the underlying domain theory from a set of data. In CBR system development, it is often necessary to determine some properties