In 4, we proposed a general learning method for automatically deriving fuzzy-if-then rules and membership functions from a set of given training examples by merging the decision tables and membership functions. In this paper, we present an appropriate data structure upon which to base that learning method. A decision array and membership function arrays are used. Depending on the data structure used, procedures for implementing each step in the original learning algorithm efficiently are available. The proposed method can save a great many records in dealing with blanks. It can also avoid problems that arise when using the original learning algorithm.
展开▼
