A class of fuzzy random optimization: expected value models

Fuzzy random variable is a measurable mapping from a probability space to a collection of fuzzy variables. This concept may be regard as an extension of both random variable and fuzzy variable. In this paper, the linearity of a scalar value expected value operator of fuzzy random variable is discussed, and a fuzzy random simulation approach is suggested to evaluate the expected value of a fuzzy random variable. In addition, three types of fuzzy random expected value models are presented to model fuzzy random decision systems. Moreover, a hybrid intelligent algorithm, which incorporates simulation, neural network and genetic algorithm, is designed in order to solve general fuzzy random expected value models. At the end of this paper, the effectiveness of this algorithm is showed via three numerical examples. (C) 2003 Elsevier Inc. All rights reserved.