K.M. Lee, D.H. Kwak, and H. Lee-Kwang. Fuzzy inference neural network for fuzzy model tuning. IEEE Transactions Systems Man Cybernetics, 26(4B):637--645, 1996.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....the consequent (THEN) part of the rule; and 4) Defuzzification, that is aggregating the consequent to produce the output. There are several kinds of fuzzy rules used to construct fuzzy models. These fuzzy rules can be classified into the following three types according to their consequent form [26]: 1) Fuzzy rules with a crisply defined constant in the con sequent i: IF 2 is Ai and. and : is Ai, THEN y is ci 2) Fuzzy rules with a linear combination of the systems input variables in the consequent R: IF :e is A, and and st: is A THEN y is g,i(x, x, bo bx . 3) ....

....the consequent) depending on what the input is. Sugeno models are similar to the Mamdani model [29] which has rules of the third type, and which is more intuitive, but computationally less efficient. Fuzzification and weighing, are exactly the same, but generation and defuzzification are different [26]. For the type of fuzzy rules used in Mamdani model various methods are available for defuzzification: the centroid of area, bisector of area, middle of maximum, largest of maximum etc. 10] but all of these methods are based on the calculation of the two dimensional shape surface, that is on ....

K. M. Lee, D. H. Kwak, and H. Lee-Kwang, "Fuzzy inference neural network for fuzzy model tuning," IEEE Trans. Syst. Man, Cybern., vol. 26, pp. 63%645, 1996.

....little theoretical guidance as to which of the design choices are correct for a particular domain. A number of approaches have been proposed for the development, tuning and optimization of fuzzy models. Many of these have been based on the integration of neural networks with fuzzy logic [8] [9], or hybrid neuro fuzzy clustering methods such as Fuzzy ARTMAP [10] or ANFIS [11] More general algorithmic approaches have included the Sigma PAFIO algorithm for model optimization [12] 13] a framework for synthesising fuzzy rules [14] and Genetic Algorithm based optimization methods [15] ....

K.M. Lee, D.H. Kwak, and H. Lee-Kwang, "Fuzzy inference neural network for fuzzy model tuning," IEEE Transactions Systems Man Cybernetics, vol. 26, no. 4B, pp. 637--645, 1996.

....N dimensional non linear optimisation, in which N is very large even for the most trivial of fuzzy systems. A number of approaches have been proposed for the development, tuning and optimisation of fuzzy models. Many of these have been based on the integration of neural networks with fuzzy logic [76, 72], or hybrid neuro fuzzy clustering methods such as F ARTMAP [18] or ANFIS [58] More general algorithmic approaches have included the S PAFIO algorithm for model optimisation [126, 96] a framework for synthesising fuzzy rules [103] and Genetic Algorithm based optimisation methods [95] The well ....

K.M. Lee, D.H. Kwak, and H. Lee-Kwang. Fuzzy inference neural network for fuzzy model tuning. IEEE Transactions Systems Man Cybernetics, 26(4B):637--645, 1996.

....the consequent (THEN) part of the rule; and 4) Defuzzification, that is aggregating the consequent to produce the output. There are several kinds of fuzzy rules used to construct fuzzy models. These fuzzy rules can be classified into the following three types according to their consequent form [26]: 1) Fuzzy rules with a crisply defined constant in the consequent IF is and and is THEN is . 2) Fuzzy rules with a linear combination of the systems input variables in the consequent IF is and and is THEN is . 3) Fuzzy rules with fuzzy set in the consequent IF is and and is THEN is where ....

....the consequent) depending on what the input is. Sugeno models are similar to the Mamdani model [29] which has rules of the third type, and which is more intuitive, but computationally less efficient. Fuzzification and weighing, are exactly the same, but generation and defuzzification are different [26]. For the type of fuzzy rules used in Mamdani model various methods are available for defuzzification: the centroid of area, bisector of area, middle of maximum, largest of maximum etc. 10] but all of these methods are based on the calculation of the two dimensional shape surface, that is on ....

K. M. Lee, D. H. Kwak, and H. Lee-Kwang, "Fuzzy inference neural network for fuzzy model tuning," IEEE Trans. Syst. Man, Cybern., vol. 26, pp. 637--645, 1996.

....using knowledge from a human expert. This task becomes difficult when the available knowledge is incomplete or when the problem space is very large, thus motivating the use of automatic approaches to fuzzy modeling. There are several approaches to fuzzy modeling, based on neural networks [11,16,18,31], genetic algorithms [9,17,24] and hybrid methods [8] Selection of relevant variables and adequate rules is critical for obtaining a good system. One of the major problems in fuzzy modeling is the curse of dimensionality, meaning that the computation requirements grow exponentially with the ....

Lee K-M, Kwak D-H, Lee-Kwang H. Fuzzy inference neural network for fuzzy model tuning. IEEE Trans Syst Man Cybern 1996;26(4):637 -- 45.

....using knowledge from a human expert. This task becomes difficult when the available knowledge is incomplete or when the problem space is very large, thus motivating the use of automatic approaches to fuzzy modeling. There are several approaches to fuzzy modeling, based on neural networks [9, 13, 15, 27], genetic algorithms [7, 14, 21] and hybrid methods [6] Selection of relevant variables and adequate rules is critical for obtaining a good system. One of the major problems in fuzzy modeling is the curse of dimensionality, meaning that the computation requirements grow exponentially with the ....

K.-M. Lee, D.-H. Kwak, and H. Lee-Kwang. Fuzzy inference neural network for fuzzy model tuning. IEEE Transactions on Systems, Man and Cybernetics, 26(4):637--645, August 1996.

....Table 5.1 delineates the parameters encoding, which together comprise one individual s genome. Table 5.1: Parameters encoding of an individual s genome. Total genome length is 64 18N r , where N r denotes the number of rules. Parameter Values Bits Qty Total bits P [1 10] 4 9 36 d [0 7] 3 9 27 A [0 3] 2 9N r 18N r C (1,2) 1 1 1 To evolve the fuzzy inference system, we used a simple genetic algorithm, with a fixed population size of 200 individuals, no generational overlap, and fitness proportionate selection. As for the fitness function of the genetic algorithm, the ....

K.-M. Lee, D.-H. Kwak, and H. Lee-Kwang, "Fuzzy inference neural network for fuzzy model tuning," IEEE Transactions. on Systems,Man and Cybernetics, vol. 26, no. 4, pp. 637--645, August 1996.

....[Raju88] is considered as a generalization of those of Buckles and Petry, Baldwin, Umano and so on. We hence explain his fuzzy database model in greater detail from now on. As a preliminary, a fuzzy set F in a classical universe of discourse, U is characterized by th following membership function [Lee96] [Kim97 ] gF: U [0, 1] where gF(U) for each u U denotes the grade of membership of u in the fuzzy set F. Based on the above definition, we can write F = gF(U0 Ul, gF(U2) U2 . gF(U0 U, for all ui U, 1 i n. The classical set operations have been extended to deal with the fuzzy ....

K. M. Lee, H. Lee-Kwang, "Fuzzy Inference Neural Network for Fuzzy Model Tuning," IEEE trans. System Man and Cybernetics, Vol.26, No. 4, pp637-645, 1996. 26

No context found.

K.M. Lee, D.H. Kwak, and H. Lee-Kwang. Fuzzy inference neural network for fuzzy model tuning. IEEE Transactions Systems Man Cybernetics, 26(4B):637--645, 1996.

No context found.

K.M. Lee, D.H. Kwak, and H. Lee-Kwang, "Fuzzy inference neural network for fuzzy model tuning," IEEE Transactions Systems Man Cybernetics, vol. 26, no. 4B, pp. 637--645, 1996.

No context found.

Lee, K. M.; Kwak, D. H.; and Hyung, L. K. 1996. Fuzzy Inference Neural Network for Fuzzy Model Tuning. IEEE Transactions on Systems, Man, and Cybernetics 26(4):637-645.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC