A similarity-based bidirectional approximate reasoning method for decision-making systems

This paper presents a similarity-based bidirectional approximate reasoning method which can express the decision maker's disposition. For this, we shall propose a new type of similarity measure based on the ordered weighted aggregation (OWA) operator. The proposed similarity measure has a structure to involve the disposition of a decision maker by choosing a suitable weighting vector of the OWA operator. From this property, we derive a simple and flexible type of similarity-based bidirectional approximate reasoning method which can support the making of a decision under more complex situations such as industrial inspection systems for example. (C) 2001 Elsevier Science B.V. All rights reserved.