scientific article; zbMATH DE number 1163085

MaRDI QIDQ4394572zbMATH OpenFDO

Authors Chongfu Huang, Da Ruan

Publication date 11 June 1998

zbMATH Keywords

BP neural networkearthquake datafuzzy approximate reasoningfuzzy informationsincomplete knowledgeinformation diffusion principleinformation distribution functioninformation distribution matrixinput and output neuronsknowledge set

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Seismology (including tsunami modeling), earthquakes (86A15) Neural networks for/in biological studies, artificial life and related topics (92B20) Fuzzy sets and logic (in connection with information, communication, or circuits theory) (94D05)

Review text

Both the measuring scale and the incompleteness of the sample knowledge give fuzzy informations. In this paper the fuzziness of fuzzy informations is demonstrated. An embryonic form of a theory of fuzzy information optimization processing which is connected with incompleteness is established by developing the method of information distribution to an information diffusion principle. 14 definitions are given. The following theorems are obtained: the theorem of asymptotically unbiased property of the diffusion estimator and the theorem of mean square consistent property of the diffusion estimator. A partial differential equation of information diffusion is introduced. An application in fuzzy neuron to estimate earthquake intensity shows that information diffusion methods have obvious advantages and future applications. An appendix shows the earthquakes records and the results of forecast. For the entire collection see [Zbl 0887.00010].

Recommendations

• Towards efficient fuzzy information processing. Using the principle of information diffusion
• scientific article; zbMATH DE number 78014
• Banded approximation with diffusion-neural-network
• Estimating the relationship between isoseismal area and earthquake magnitude by a hybrid fuzzy-neural-network method

Cited in

(5)

• Estimating the relationship between isoseismal area and earthquake magnitude by a hybrid fuzzy-neural-network method
• A diffusion-neural-network for learning from small samples
• scientific article; zbMATH DE number 78014 (Why is no real title available?)
• Banded approximation with diffusion-neural-network
• Towards efficient fuzzy information processing. Using the principle of information diffusion

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4394572)