DocumentCode :
3300618
Title :
A Weighted Fuzzy Reasoning Process Neural Network and Its Application
Author :
Liu Xian-de ; Li Huan
Author_Institution :
Sch. of Comput. & Inf. Technol., Daqing Pet. Inst., Daqing
Volume :
3
fYear :
2008
fDate :
18-20 Oct. 2008
Firstpage :
59
Lastpage :
63
Abstract :
According to dynamic information processing problems concerning process fuzzy information or domain rules, this paper presents a weighted fuzzy reasoning process neuron and a weighted fuzzy reasoning process neural network model. The weighted fuzzy reasoning process neuron uses dynamic information processing methods of fuzzy process reasoning rules and numerical process neuron in combination, and implements adaptive fuzzy reasoning to the process quantitative and qualitative mixed information with learning mechanism of process neuron. The fuzzy reasoning process neural network that makes up of weighted fuzzy reasoning process neuron and other types of neurons according to certain information transmission and fuzzy reasoning rules, extends fuzzy function mapping relation of traditional fuzzy neural networks to mapping relation of fuzzy functional, which improves comprehensive information treatment capacity for various kinds of process information. A weighted fuzzy reasoning process neural network model and its learning algorithm have been given. Practical application results proved the effectiveness of the model and the algorithm.
Keywords :
fuzzy set theory; inference mechanisms; learning (artificial intelligence); neural nets; adaptive fuzzy reasoning; dynamic information processing methods; numerical process neuron; weighted fuzzy reasoning process neural network; Computer networks; Fuzzy control; Fuzzy neural networks; Fuzzy reasoning; Fuzzy systems; Information processing; Neural networks; Neurons; Signal processing; Time varying systems; fuzzy process neural network; fuzzy process neuron; fuzzy process reasoning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Natural Computation, 2008. ICNC '08. Fourth International Conference on
Conference_Location :
Jinan
Print_ISBN :
978-0-7695-3304-9
Type :
conf
DOI :
10.1109/ICNC.2008.244
Filename :
4667101
Link To Document :
بازگشت