-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 2 Pages
185-
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Takamasa AKIYAMA
Article type: Article
1999 Volume 11 Issue 2 Pages
186-187
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Hiroshi TAKAHASHI, Takamasa AKIYAMA
Article type: Article
1999 Volume 11 Issue 2 Pages
188-195
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Hiroshi TAKAHASHI
Article type: Article
1999 Volume 11 Issue 2 Pages
196-204
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Takamasa AKIYAMA, Toshimitsu TAKABA, Kaori MIZUTANI
Article type: Article
1999 Volume 11 Issue 2 Pages
205-214
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Kunio YIKAI, Nakaji HONDA
Article type: Article
1999 Volume 11 Issue 2 Pages
215-221
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Ken-etsu UCHIDA, Seiichi KAGAYA, Keiichi SATOH
Article type: Article
1999 Volume 11 Issue 2 Pages
222-232
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Shinya KIKUCHI, Nobuhiro UNO
Article type: Article
1999 Volume 11 Issue 2 Pages
233-245
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Takamasa AKIYAMA, Chun Fu SHAO
Article type: Article
1999 Volume 11 Issue 2 Pages
246-258
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Toshiyuki MAEDA
Article type: Article
1999 Volume 11 Issue 2 Pages
259-262
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Article type: Bibliography
1999 Volume 11 Issue 2 Pages
263-270
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Kaori YOSHIDA
Article type: Article
1999 Volume 11 Issue 2 Pages
271-273
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Hisashi HANDA
Article type: Article
1999 Volume 11 Issue 2 Pages
274-275
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Koichi YAMADA
Article type: Article
1999 Volume 11 Issue 2 Pages
276-279
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
1999 Volume 11 Issue 2 Pages
280-284
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 2 Pages
285-
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 2 Pages
286-
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 2 Pages
287-
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 2 Pages
287-
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 2 Pages
288-
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1999 Volume 11 Issue 2 Pages
288-
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
-
Masaaki IDA
Article type: Article
1999 Volume 11 Issue 2 Pages
289-297
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
In this paper, we consider possibilistic multiobjective linear programming problems. A possibly efficient solution set is defined as a fuzzy set whose membership grades represent possibility degrees for which the feasible solutions are efficient. We restrict possibilistic distributions of the coefficients in possibilistic multiobjective linear programming problems, and propose the calculation mehtod of the degree of possible efficiency for a certain feasible solution based on the dual problem. Applying the result of calculation to sensitivity analysis, we can discuss the readjustment of the parameters of fuzzy numbers.
View full abstract
-
Tamotsu MITAMURA, Taka'aki WAKABAYASHI, Azuma OHUCHI
Article type: Article
1999 Volume 11 Issue 2 Pages
298-308
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
Fuzzy Structural Modeling is a problem of how to efficiently fill the fuzzy reachability matrix. To do it effectively, there are needs to supports of eliciting a set of elements and generating a fuzzy relational matrix. In this paper, support-methods with a repertory grid for generating the fuzzy reachability matrix are proposed. First, an algorithm of generating a fuzzy matrix from a repertory grid is proposed. Use of the repertory grid help the user to recognize important factors in his problem domain. Second, an algorithm to make a fuzzy reaczhability matrix from a user's fuzzy matrix using the transitive inconsistency is proposed. The algorithm makes a structural model that is not different from user's model. Use of the methods makes it possible to do a flexible and an efficient modeling for complex and fuzzy systems.
View full abstract
-
Masayoshi SHIMONO, Tsutomu MIKI, Takeshi YAMAKAWA
Article type: Article
1999 Volume 11 Issue 2 Pages
309-319
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
A cross-coupled network, which a Hopfield network belongs, can work as an associative memory and is attractively capable of storage and recovery of information. A Hopfield network can associate a stored patten similar to the given one, even though it is defective, noisy or incomplete. However, it can associate only one pattern corresponding to the given pattern, because the state of the network goes down to the locally or globally lowest level of energy. Thus the Hopfield network cannot associate more than one candidates for one given pattern, while a human brain candynamically associate some patterns similar to a presented one. An artificial neural network should be modeling of a biological neural system. The association of more than one pattern in a biological brain cannot be modeled by the Hopfield network. To imitate the dynamicalassociation in a human brain, the activation of the network state by noise or the chaotic behavior of neural units might be employed, such as a chaotic unit. In these systems, however, the state of the network is always activated and the network associates unstored patterns frequently. Because the state of the system can stay at any level of energy at the same probability in this case. So, a lot of researchers have tried to activate the network for dynamical association and proposed their own methods in recent years. Aihara, et al.improved the Nagumo's neuron model by replacing a step function with a sigmoidal function. The neuron model can exhibit chaotic behavior by itself, so that it is referred to as a "chaotic neuron". The chaotic neurons are cross-connected to each other to construct a network, in which individual chaotic behavior of each neuron activates to search another state after falling into a local minimum. Thus the dynamical association is realized and thus the networkis referred to as a chaotic network. In this network, the informationon the stored patterns is embedded in weight distribution and we have no other way to identify the stored patterns than the feature of the output sequence of the network. However, an overlapped pattern cannot be separated into its individual patterns, whereas a human being cando so at a glance. To cope with these problems, a novel non-equilibrium network which separates an overlapped pattern to individual ones is proposed in this paper. This network has following two properties. One is the ability of frequent association of stored patterns, that is, the network associates stored patterns more than non-stored ones. The other is a temporary degradation of the stored item. This degradation plays a role of a system reset for a new association. The implementation of the first property is based on a measure of similarity which is latent in cross-coupled networks, and realized by using an inverse N-shaped function as a mapping one. Besides, the second property is realized by changing connection weights between units. An algorithm separating overwritten patterns is based on the effects of these two properties.
View full abstract
-
Futoshi KOBAYASHI, Fumihito ARAI, Koji SHIMOJIMA, Toshio FUKUDA, Makot ...
Article type: Article
1999 Volume 11 Issue 2 Pages
320-327
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
Sensor fusion systems for estimating the states from sensor information have received much attention in various fields. In these days, various kinds of sensors have been developed. The measuring time and accuracy of each sensor are different because each sensor has particular characteristic for measuring. We have proposed the Recurrent Fuzzy Inference(RFI) with incremental learning for fusing multiple sensor information with different measuring time and accuracy. However, our method and traditional methods cannot evaluate the inferred result. In this paper, we propose the evalution method for the inferred result. In this method, we calculate the reliability of it by the degree of fuzziness which expresses the fuzziness of the learned membership function. For showing the effeciveness of our method, we apply our method to the grinding process. Then, we infer the surface roughness and calculate the reliability of it.
View full abstract
-
Tsuyoshi KAWAI, Atsushi OGAWA, Yoshio OZAWA, Masashi YSUDA, Masato OSU ...
Article type: Article
1999 Volume 11 Issue 2 Pages
328-337
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
We have developed a refrigerant flow controller of package airconditioners using fuzzy control technoligies. A look-up-table type fuzzy controller is employed for ease of implementation. An increasing demand is, however, to add adaptability to machines'setting environments into existing performances without affecting the look-up-table structure of the controller. In order to solve this problem, we developed new automatic tuning methods for look-up-table type fuzzy controllers using two coefficients of compensation, scaling factor(SF)and weighting factor(WF). The optimal SF is first decided by neural-networks, then repeated adjusting yields WF gradually. We evaluated these methods by simulations. The methods might find applications in many other electrical appliances, where loopk-up-table type controlleres are implementad.
View full abstract
-
Kazuhiko OTSUKA, Masashi EMOTO, Masao MUKAIDONO
Article type: Article
1999 Volume 11 Issue 2 Pages
338-346
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
In this paper, we consider trapezoid truth values which are truth values between interval truth values and fuzzy truth values. In trapezoid truth value, their membership values are 1 between two tops of a trepezoid are 0 at outside of two end-sides of a trapezoids. We defined the new logical operations on the set of trapezoid truth values, which are different from the definitions based on the extension principle. Because the result of operations based on the extension principle may not be trapezoid truth values, in the other word trapezoid truth values are not closed under these operations. The algebra which is composed of the trapezoid truth values and these operators satisfies De Morgan algebra like interval truth values. Furthermore, we show a necessary and sufficient condition for the trapezoid truth values to satisfy Kleene's laws. Finally, we show the properties of the sets of trapezoid truth values which are generated from finite trapezoid truth values and our logical operations. Especially, we show the maximum number of elements in the set which is generated from two trapezoid truth values, and the maximum number of elements when the generators satisfy Kleene's laws.
View full abstract
-
Lifeng HE, Lisong WANG, Yuyan CHAO, Tsuyoshi NAKAMURA, Hidenori ITOH
Article type: Article
1999 Volume 11 Issue 2 Pages
347-353
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS
In this paper, we propose an improvement of the digital image compression using Triangular Plane Patches(TPP method). TPP method uses two triangular plane patches to approximate original image's luminance curved surfaces of a block in xy-plane. Since triangular plane patches are constructed according to the original image's luminace values of 4 vertical pixels of the block, they could hardly be suitable ones. Addressing to this problem of TPP methods, we use fuzzy reasoning to adjust the luminance values of 4 vertical pixels of a block by considering the influnce of some other pixels in the block. In this way, we can derive suitable triangular plane patches for a block by using the adjusted 4 luminace values. Our method has been implemented and experiment results show that the performance of the F-TPP method is better than that of the TPP method.
View full abstract
-
1999 Volume 11 Issue 2 Pages
354-357
Published: April 15, 1999
Released on J-STAGE: January 08, 2018
JOURNAL
FREE ACCESS