DECISION PERSONAL INDEX OF FUZZY NUMBERS BASED ON NEURAL NETWORKS

In a previous work, we showed that artificial neural networks (ANNs) c ould learn the criteria for comparing fuzzy numbers of a real decision maker. A multilayer feed-forward ANN and the backpropagation algorith m, and trapezoidal fuzzy numbers were considered. The criteria of thre e people were learnt with an ANN. The trained ANN is considered as a p ersonal method of the decision-maker to compare fuzzy utilities and it has been applied to some decision problems. In this paper, a decision personal index (DPI) of fuzzy numbers based on the trained ANN is dev eloped in order to measure distance between the numbers. The DPI ranks them with values in [0,1] interval, and we apply it to some problems on matrix games and linear optimization with a fuzzy environment. Some examples are also shown.