A new approach to handling fuzzy decision-making problems

New techniques for handling fuzzy decision-making problems are introduced. Fuzzy production rules and fuzzy set theory are used for knowledge representation. In a classical production rule, the rule is executed if the pattern of its antecedent portion D_i perfectly matches the pattern of a set M of manifestations. However, in a fuzzy production rule, the rule is executed if the degree of matching is not less than a certain matching threshold value. By using a vector representation method, the antecedent portion of the fuzzy production rule and the set of manifestations can be represented by vectors of values and features, respectively. Then, a matching function can be used to measure the degree of similarity between the vectors, and the strength of confirmation calculation method can be used on the consequence d_i caused by M. An efficient algorithm to generate the maximum fuzzy cover of M to help the decision-maker make his decisions is proposed