Fuzzy-connective-based hierarchical aggregation networks for decision making

Decision making is usually based on the aggregation of several criteria. Although the aggregation can be performed at one level in simple cases, in more complex situations it becomes necessary that it be performed in a hierarchical manner in a multilevel framework. This is particularly true in many engineering applications. In this paper, the authors investigate the use of fuzzy connectives in multilayer networks to arrive at appropriate overall aggregation functions. The characteristics of suitable fuzzy connectives are studied and an iterative algorithm to determine the type of aggregation function and its parameters at each node in the network is proposed. The authors believe that the present aggregation scheme is powerful and flexible, since several types of aggregation connectives are used and since the parameters of the network can be determined using a simple algorithm. The behavior of the network can also be modified depending on the desired ‘attitude’. Conditions for unque convergence of the algorithm in simple cases are discussed, and examples of applications of the method are also presented.