-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 4 Pages
533-
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 4 Pages
534-
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Norifumi SAITO
Article type: Article
1999 Volume 11 Issue 4 Pages
535-544
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Yoshiyuki USAMI, Atsuko UDA, Saburo HIRANO
Article type: Article
1999 Volume 11 Issue 4 Pages
545-552
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Mari NAKAMURA, Koichi KURUMATANI
Article type: Article
1999 Volume 11 Issue 4 Pages
553-560
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Nobuyuki NAKAJIMA
Article type: Article
1999 Volume 11 Issue 4 Pages
561-576
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Article type: Bibliography
1999 Volume 11 Issue 4 Pages
577-585
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Naoyuki KUBOTA
Article type: Article
1999 Volume 11 Issue 4 Pages
586-587
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 4 Pages
588-
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 4 Pages
589-
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 4 Pages
589-
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 4 Pages
590-591
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 4 Pages
592-
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 4 Pages
592-
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Hiroshi MAEDA, Shinobu KAKIUCHI, Daisuke YAMAMOTO, Kazuo KUWANO
Article type: Article
1999 Volume 11 Issue 4 Pages
593-604
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
In this paper, Kansei evaluation problem and Kansei design problem are defined and a new method for dealing with those problems is proposed. First, a certain modeling method called Decomposed multidimensional fuzzy reasoning model is proposed for the modeling of a multiple inputs and single output system, and then the Kansei evaluation problem is formulated by this model. Next, it is shown that the solution for an inverse problem of the Decomposed multidimensional fuzzy reasoning model can express the Kansei design problem and also shown that the solution technique can be provided with the framework of multiobjective programming. Furthermore, a concrete solution technique using the notion of distance is given. Finely, the new method is applied to the Kansei evaluation and design of river landscapes.
View full abstract
-
Koichi YAMADA
Article type: Article
1999 Volume 11 Issue 4 Pages
605-615
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
Many systems analyzed in the real world include events with two kinds of fuzziness-uncertainty and intensity degress. As for uncertainty, there is a long and rich history of studies using Probabilities, and some new studies employing Possibility theory, which is suitable for ordering based on uncertainty, have been published recently. Then, for intensity degrees of events, several causal reasoning methods, such as Fuzzy cognitive maps that conduct analysis through a simulation by forward reasoning using fuzzy causalities, Abductive reasoning that employs causal knowledge with degrees of occurrence in the back ward manner, and Intensity reasoning that uses the causal knowledge both in forward and backward manner, have been proposed. However, there are few studies that cover both uncertainty and intensity as well as both forward and backward causal reasoning. This paper proposes a new reasoning technique that can deal with all of them. The proposed approach is an expansion of a Possibilistic causal reasoning conducted in forward and backward manner using Conditional causal possibilities.
View full abstract
-
Shini-chi YOSHIKAWA, Tetsuji OKUDA, Kiyoji ASAI
Article type: Article
1999 Volume 11 Issue 4 Pages
616-639
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
In this paper, we refer to the interval data whose boundary of interval is vague as fuzzy interval data. We propose the method of approximate Bayesian regression analysis based on data processing using fuzzy interval data. Here, we formulate the approximate Bayesian regression analysis using the concept of the probability of fuzzy events defined by Zadeh. However, the method with direct usage of the membership functions of fuzzy interval data, that is to say, treating the membership functions precisely causes the complexity of calculation. But our method treating the middle points of membership functions as the representative points can solve such problems. Here, we suppose that the fuzzy interval data are obtained from the k-dimensional normal population. When a prior distribution of regression coefficient β is a n-dimensional normal distribution, we can show that the posterior distribution of β forms the n-dimensional normal distribution approximately by using our proposed method. As a result, even if we obtain fuzzy interval data. we can show the Bayesian regression analysis which is not so far different from the conventional Bayesian regression analysis. Moreover, in realistic situations, we cannot always treat the ideal symmetrical membership functions of fuzzy interval data. So we performed the computer simulations under realistic circumstances which do not satisfy completely the condition of the symmetry of trapezoidal membership functions. And we examined the practicability of our method. As a result, we could proof the practicability.
View full abstract
-
Yasuo KUDO, Tetsuya MURAI, Tsutomu DA-TE
Article type: Article
1999 Volume 11 Issue 4 Pages
640-649
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
Belief update is a theoretical formulation of the way we change our beliefs by getting or losing information based on changes of the world. Katsuno and Mendelzon have proposed three kinds of belief update operations in logical framework, called update, erasure and symmetric erasure, respectively. Dubois and Prade have formulated update operations, and Kudo et.al have formulated erasure operations in possibility theory framework. However, their update and erasure in possibility theory are not well-defined. Moreover, symmetric erasure in the possibility theory had not been formulated. In this paper, we formulate belief update in the possibility theory framework strictly. First, we reformulate update operations in the possibility theory proposed by Dubois and Prade by improving their formulation of update. Next, we formulate erasure and symmetric erasure operations in the possibility theoty, and also characterize these two operations as minimal changes when losing information by changing the world. Finally, we propose belief update with uncertain inputs, and show that symmetric erasure is an essential operation of belief updates with uncertain inputs.
View full abstract
-
Toshihiko WATANABE, Hiroshi NARAZAKI, Yasutaka UCHIYAMA, Hiroaki NAKAN ...
Article type: Article
1999 Volume 11 Issue 4 Pages
650-657
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
This paper describes an adaptive fuzzy modeling method and its successful application to the feedforward control for a continuous galvanizing line (CGL)in an iron and steel making plant. In CGL, due to the time delay that exists in the process, the feedforward control is indispensable for the accurate control of the solidified zinc of a galvanized steel strip. For this feedforward control to be successful, a model having the following two properties is required : First, the model should be able to describe the nonlinear characteristics of the process. Secondly, the model should have an adaptive capability to maintain accuracy in the long run. In this paper, we present an adaptive fuzzy modeling method that satisfies the above two criteria. The usefulness of our method is demonstrted using experimental results.
View full abstract
-
Masatoshi SAKAWA, Ichiro NISHIZAKI, Yoshio UEMURA, Masatoshi HITAKA
Article type: Article
1999 Volume 11 Issue 4 Pages
658-666
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
It is natural to consider that possible values of parameters of mathematical programming problems are only ambiguously known to experts. From this point of view, in this paper, we formulate two-level nonconvex nonlinear programming problems with fuzzy parameters and present interactive fuzzy programming through genetic algorithms for the problems. Recently, the genetic algorithms attract a great deal of considerable attention as methods for optimization, adaptation and learning, and it has been shown that they effectively work in nonconvex nonlinear programming problems. In our interactive method, after determining the fuzzy goals of the decision makers at both levels, through genetic algorithms, a satisfactory solution is efficiently derived by updating the minimal satisfactory level of decision makers at the upper level with considerations of overall satisfactory balance between both levels. An illustrative numerical example for two-level nonconvex nonlinear programming problems with fuzzy parameters is provided to demonstrate the feasibility of the proposed method.
View full abstract
-
Yutaka MAEDA, Hideo TANAKA
Article type: Article
1999 Volume 11 Issue 4 Pages
667-676
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
Probability measures are well-defined measures which have additivity. However, it is slightly tight because of its condition of additivity. The substitute measures are proposed such as fuzzy measures which do not satisfy additivity. The only belief function involves a density function among them. In this paper, we propose two density functions by extending values of conventional density function to interval values, which do not satiafy additivity, and define a combination rule, a conditional probability and a expected value and then we clarify the properties of the proposed measure.
View full abstract
-
Isao HAYASHI, Toshiyuki MAEDA, Jun OZAWA
Article type: Article
1999 Volume 11 Issue 4 Pages
677-683
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
An ability of learning for AND operator is discussed here. The fuzzy ID3 is a poweful method to acquire fuzzy rules. Altenatively, the fuzzy ID3 with tuning function has been proposed by Umano. In the algorithm, the optimal fuzzy rules are obtained by tuning both parameters of AND connectives and the shape of membership functions. However, the obtained fuzzy rules strongly depend on the parameters and it is hard to get the most suitable fuzzy rules. In our fuzzy ID3, the AND connectives is formulated using parameters family of t-norm, which is adjusted suitably using golden section method, such that it takes the maximal value of the mutual information. We here formulate an efficient algorithm for tuning the parameter of AND connectives to acquire the optimal fuzzy rules and discuss a relationship between the parameter and the mutual information.
View full abstract
-
Mikihiko KONISHI, Tetsuji OKUDA, Kiyoji ASAI
Article type: Article
1999 Volume 11 Issue 4 Pages
684-689
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
When the data is observed in some systems which involve human beings, there are cases that the data is not always exact or it is difficult to observe the data exactly. In these cases, if we can observe the data including the human vagueness then its observation becomes easy. Then, in this paper, on the assumption that the observations include the human vagueness, we treat the fuzzy interval data including unclear border of intervals. And, we give the processing method of the canonical correlation analysis by fuzzy interval data. But, it is difficalt to treat the fuzzy interval data exactly. So, in our method, we execute the canonical correlation analysis apploximately. And, the usefulness of our method is illustrated using computer simulation.
View full abstract
-
Keiichi OGAWA
Article type: Article
1999 Volume 11 Issue 4 Pages
690-694
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
In this paper, disaggregate behavioral model using fuzzy integral utility function is proposed. The purpose of the modeling is to represent the mechanism that driver evaluates the alternatives by using offered information and his own perception to the traffic situation, in case of route choice behavior. This is based on the traffic information system, one of the ITS policies. As a result, it is possible to estimate efficient parameters that satisfy the sign conditions by using fuzzy integral utility functions, in case that each attribute to use for the evaluation of the altenatives is not independent mutually and that weight parameter of the attribute does not have finite additivity. Therefore, it is known that this model is efficient to analyze drivers' behavior in case that traffic information is offered to plural attributes.
View full abstract
-
1999 Volume 11 Issue 4 Pages
695-702
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
1999 Volume 11 Issue 4 Pages
703-
Published: August 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS