Experience-Consistent Fuzzy Rule-Based System Modeling
The paper is concerned with an experience-consistent development of fuzzy rule-based systems. This design of such fuzzy models involves some locally available data and then reconciles the constructed model with some previously acquired domain knowledge. This type of domain knowledge is captured in the format of several rule-based models constructed on a basis of some auxiliary data sets. To emphasize the nature of modeling being guided by this reconciliation mechanism, the authors refer to the resulting fuzzy model as experience - consistent identification. By forming a certain extended form of the optimized performance index, it is shown that the domain knowledge captured by the individual rule-based models play a similar role as a regularization component typically encountered in identification problems.