In this paper, we use the interior-outer-set model to calculate the risk of crop flood and order farming alternatives for Huarong County, China, where only a small sample of eight observations is available.Any risk assessment from the data must be imprecise. The risk calculated by this suggested model is a particular case among imprecise probabilities, called possibility-probability distribution.We discuss in detail how to order alternatives based on a possibility-probability distribution.The result shows, aside subjective assessment, the fuzzy risk can also be calculated.The comparison shows that the ordering based on a calculated fuzzy risk is better than one based on a histogram estimate.

The method of the information distribution is used to produce a more intelligent architecture, called primary information matrix. Then, without any assumption, we can construct a fuzzy relation matrixf or fuzzy inference. To display the advantage of the new framework, in this paper, we use it to study the relationship between epicentre intensity, I0, and earthquake magnitude, M. The result shows that the new model is better than the traditional regression model.

. Mit der neuen Methode kann die kleine Anzahl sich wie eine groK {ere Anzahl auswirken, so da{ wir ein genaueres Ergebnis erhalten. Rechnersimulationen zeigen, daβ die Leistungsfáhigkeit der neuen Methode ungefaK hr 28% höher liegt als die Histogram-mmethode.

Utilizing information diffusion method and artificial neural networks, we propose in this paper a hybrid fuzzy neural network to estimate the relationship between isoseismal area and earthquake magnitude. We focus on the study of in-completeness and contradictory nature of patterns in scanty historical earthquake records. Information diffusion method is employed to construct fuzzy relationships which are equal to the number of observations, integration of the relationships can change the contradictor), patterns into more compatible ones which, in turn, can smoothly and quickly train the feed-forward neural network with backpropagation algorithm (BP) to obtain the final relationship. A practical application is employed to show the superiority of the model. c 1999 Elsevier Science B.V. All rights reserved,