-
[in Japanese]
Article type: Article
1998 Volume 10 Issue 2 Pages
181-
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Eiichiro TAKAHAGI, Ayumi YOSHIKAWA
Article type: Article
1998 Volume 10 Issue 2 Pages
182-183
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Ayumi YOSHIKAWA
Article type: Article
1998 Volume 10 Issue 2 Pages
184-192
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Toru UEDA
Article type: Article
1998 Volume 10 Issue 2 Pages
193-199
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Haruki IMAOKA
Article type: Article
1998 Volume 10 Issue 2 Pages
200-205
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Katsunari FUJIMOTO
Article type: Article
1998 Volume 10 Issue 2 Pages
206-214
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Yoshiteru NAKAMORI
Article type: Article
1998 Volume 10 Issue 2 Pages
215-224
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Shigeru AKAMRTSU
Article type: Article
1998 Volume 10 Issue 2 Pages
225-235
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Hiroaki ISHII
Article type: Article
1998 Volume 10 Issue 2 Pages
236-241
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Article type: Bibliography
1998 Volume 10 Issue 2 Pages
242-246
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Toshihiko WATANABE
Article type: Article
1998 Volume 10 Issue 2 Pages
247-248
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Keiki TAKADAMA
Article type: Article
1998 Volume 10 Issue 2 Pages
249-251
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Hiroaki KIKUCHI
Article type: Article
1998 Volume 10 Issue 2 Pages
252-258
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1998 Volume 10 Issue 2 Pages
261-
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1998 Volume 10 Issue 2 Pages
261-
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1998 Volume 10 Issue 2 Pages
262-263
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1998 Volume 10 Issue 2 Pages
264-
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1998 Volume 10 Issue 2 Pages
264-
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
Takahiro HOZUMI, Osamu KAKUSHO, Yutaka HATA
Article type: Article
1998 Volume 10 Issue 2 Pages
265-274
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
An idea of an optimization method for logic design is proposed. For an objective logic design, we construct a network that can demonstrate the logic circuit based on the neural computing. We call the network the logic neuron network. We train the network until it demonstrates the system behavior using the back propagation method. Next, we optimize the network and train it again. The above process is repeated until the network can't demonstrate the circuit. After that, we extract necessary features and parameters from the last converged network. Thus, we obtain an optimum solution by applying these processes to the objective circuit. In this paper, mainly we apply the method to the binary logic design. First, we define the AND, OR and EXOR logic neurons and show the correspondence between the neurons and logic gates. Next, we construct the objective logic networks using these logic neurons and show the optimization method. The logic neuron network is applied to binary logic design of Sum-of-Products, Product-of-Sums and EXOR Sum-of-Products expression. The simulation results shows a good solution. Thus, we prove that our proposed method is applicable to various logic designs.
View full abstract
-
Takahiro MAEDA, Hihumi OOHASHI, Hideaki OGAWA, Masanao SEKINE
Article type: Article
1998 Volume 10 Issue 2 Pages
275-288
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
Various fuzzy-data-searching method in the study of data-searching are proposed up to now. In this paper, we review the characteristics of fuzzy-data-searching method from psychological point of view. And the problems is discussed and new fuzzy-data-searching method is proposed. Also, to the end of this paper, three systems based on our proposed method are proposed. (Cooking Menu Searching System, Stallion Data-base System and Ski Resort Searching System)
View full abstract
-
Takashi SHIMA
Article type: Article
1998 Volume 10 Issue 2 Pages
289-298
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
Time-optimal control by fuzzy controller is considered in this paper. Usually, very complicated numerical computation is necessary to obtain the solutions of time-optimal control problems. In this study, it is shown that such problems can be solved easily by fuzzy controllers obtained by using the Evolution Strategy(ES)as the learning algorithm of the parameters of Gaussian membership functions. Especially, this proposed global optimization approach is shown to be very useful and promising for the highly nonlinear problems which are very difficult to be solved by the conventional gradient based approaches such as a steepest descent, conjugate gradient, quasi-Newton methods.
View full abstract
-
Taizo HANAI, Hideki NOGUCHI, Hiroyuki HONDA, Takeshi FURUHASHI, Yoshik ...
Article type: Article
1998 Volume 10 Issue 2 Pages
299-306
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
FNN(fuzzy neural network)and HFNN(hierarchical fuzzy neural network)were applied to construct the models estimating the sensory evaluations of various Ginjo sake samples from the instrumental data of the samples. Errors between the sensory evaluations and estimation by FNN and HFNN models were about 10% and 7%, respectively. Input variables selected in FNN and HFNN models were in good agreement with experts' experience. By the analysis of fuzzy rules, the relationships between these input variables and output variables were found to be almost similar to those from experts' experience.
View full abstract
-
Tomomi HASHIMOTO, Toshiyuki OMATA, Toru YAMAGUCHI, Jyuichi MIYAMICHI
Article type: Article
1998 Volume 10 Issue 2 Pages
307-321
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
The purpose of this research is a knowledge acquisition and modification method for an agent based on the Rasmussen's intelligent systems model for Welfare Support Systems(WSS). The WSS are systems providing physical assistance to handicapped people. The agent is a locomotion robot. The knowledge acquisition method is ABLE(Activation Bidirectional propagation LEarning)using FAMOUS(Fuzzy Associative Memory Organizing Units Systems)to recognize gesticulated instructions, and the knowledge modification method is constructed with knowledge and sensor switches which use an evaluation function and weights. Experimental show the effectiveness of this method.
View full abstract
-
Takashi OHTANI, Takayuki FUKUYAMA, Hidetomo ICHIHASHI, Tetsuya MIYOSHI
Article type: Article
1998 Volume 10 Issue 2 Pages
322-329
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
Personal computers have potential possibility as a tool for aiding users who have disabilities. Though many computer input devices for the use of the handicapped have been developed, they do not work well when they are set away from the user or in aslant. We have developed a pointing device that translates handicapped person's movements into direct movements of the computer's cursor by measuring several color markers on the user's head. For sensitivity tuning of the cursor movement and coordinate transformation, the neurofuzzy GMDH is employed, whose partial descriptions are represented by RBFs. A heuristic model selection criterion called "Distorter" is employed to determine the optimum number of layers in neurofuzzy GMDH. The click motion is replaced with opening the mouth. The software is developed for the use of almost all MS-Windows95 application programs.
View full abstract
-
Mina RYOKE, Yoshiteru NAKAMORI, Hiroyuki TAMURA
Article type: Article
1998 Volume 10 Issue 2 Pages
330-337
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
There are two types of design parameters in the adaptive fuzzy regression, which influences the result of clustering and regression. These parameters change the shapes of clusters adaptively by creating a balance between the regression residuals and the volumes of clusters. This paper suggests, in the context of fuzzy modeling, how to determine these parameters in order to obtain better regression models and fuzzy clusters simultaneously.
View full abstract
-
Masatoshi SAKAWA, Ichiro NISHIZAKI, Yoshio UEMURA, Keiichi KUBOTA
Article type: Article
1998 Volume 10 Issue 2 Pages
338-347
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
This paper presents interactive fuzzy programming for two-level linear programming problems with fuzzy parameters. In fuzzy programming for two-level linear programming problems, recently developed by Lai et al., since the fuzzy goals are determined for both an objective function and decision variables at the upper level, undesirable solutions are produced when these fuzzy goals are inconsistent. In order to overcome such problems, after eliminating the fuzzy goals for decision variables, interactive fuzzy programming for two-level linear programming problems with fuzzy parameters is presented. In our interactive method, after determining the fuzzy goals of the decision makers at both levels, a satisfactory solution is derived efficiently by updating the satisfactory degree of the decision maker at the upper level with considerations of overall satisfactory balance between both levels. An illustrative numerical example is provided to demonstrate the feasibility of the proposed method.
View full abstract
-
Fumihiko SHIMADA, Hiroaki ISHII, Takeshi ITOH
Article type: Article
1998 Volume 10 Issue 2 Pages
348-355
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
We extend traditional shortest path models to fuzzy versions with the existence possibility of arcs and fuzzy arc length. First we consider the model where existence of each arc is fuzzy but its length is ordinary number. That is, we maximize the possibility of the existence of the path and minimize the length of the path, and seek nondominated paths since usually there does not exist a path optimizing both criteria at a time. In order to solve this problem, we first find an optimal path on an ordinary network with arcs whose existence possibility is maximum by Floyd-Warshall method. Next repeatedly arcs with lower existence possibilities are added to the network and nondominated paths are found. Further we extend this solution procedure to the shortest path problem whose arc lengths are fuzzy numbers.
View full abstract
-
Mitsuo GEN, Kenichi IDA, Jongryul KIM
Article type: Article
1998 Volume 10 Issue 2 Pages
356-365
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
Goal programming is one of the powerful methods for multiobjective decision making and is one of the excellent models for multiobjective decision making problem in many real-world problems. But in real-world problems such as the optimal design problems of system reliability, these problems are formulated by mixed integer programming model with nonlinear objective functions, real variables, and integer variables. There are many cases that the goal establishment of these objectives is difficult and imprecise. In this paper, we attempt to apply genetic algorithms, which have received a great deal of attention about their ability as optimization techniques for combinatorial problems and have been used to solve multiobjective decision making problems, to the reliability optimization problem formulated by fuzzy nonlinear mixed integer programming problem. Nonlinear mixed integer programming problem having fuzziness is difficult to solve directly. Fuzzy nonlinear mixed integer programming problem with multiple objectives is harder to manipulate. Therefore we employ the fuzzy goal programming technique to transform the system reliability optimization problem depicted by the fuzzy nonlinear mixed integer programming problem into the nonlinear mixed integer programming problem. We use the genetic algorithm to slove the nonlinear mixed integer programming problem without any transformation for nonlinear problem into a linear model or other methods. Also, we introduce the steepest descent method in order to make the proposed genetic algorithm better. Finally, we try to get some numerical experiments which have multiobjective, and imprecise nonlinear mixed integer information, using fuzzy goal programming and genetic algorithm.
View full abstract
-
Hiromi TERASHITA, Mieko OHSUGA, Futomi SHIMONO, Mamiko TODA
Article type: Article
1998 Volume 10 Issue 2 Pages
366-374
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
For the quantitative assessment of mental stress for workers such as operators, it is needed to collect physiological, subjective, behavioral and environmental measures effectively, and also analyze correlations among these parameters multidimensionally. Concerning subjective evaluation methods, it is possible that constraints in measurement procedures may have caused inconsistencies in subjective rating scores. Thus, psychometric methods including fuzzy rating methods are compared by conducting three experiments. The methods investigated in this study are a category rating scale, a graphic rating scale, a fuzzy category rating scale, and a fuzzy graphic rating scale. In the first experiment, twenty subjects participate in the psychological assessment task with questionnaires. The results of the first experiment indicate that subjects prefer verbal expressions for an emotional state assessment, though the most suitable rating method differs from person to person. In the second experiment, twelve out of twenty subjects in the first experiment participate in the psychological assessment task with computerized rating scales using a system, which is developed to concurrently collect behavioral and environmental data including subjective measures triggered by physiological response patterns. The results of the second experiment indicate, again, that the most suitable rating method and preferable input device differs from person to person. Finally, a fuzzy categorical rating method using voice input is chosen as an effective means of eliminating constraints on subjects' work. In the third experiment with this method, subjective assessment data are collected from twelve subjects using voice input, by prompting a subject when some typical patterns of the estimated physiological parameters are detected. It is possible to conclude that these computerized fuzzy rating methods can be effective for subjective assessments of emotional states at work, though it is desiable to chose a suitable method by concidering the subject' a preference and characteristics of stimuli to be evaluated.
View full abstract
-
Norio WATANABE, Hiroyuki SUGIE
Article type: Article
1998 Volume 10 Issue 2 Pages
375-380
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
A new formulation of a linear programming problem in a fuzzy environment is given for the case when constraints are fuzzy. In this formulation the goal is not transformed to a constraint and is treated as the objective function which should be maximized. In the maximization of the objective function, a concept of soft optimization is introduced for obtaining plural solutions which can be regarded as almost best. The solution in this formulation is defined as a fuzzy set. The proposed method is applicable in a situation when it is not appropriate to restrict to the unique solution.
View full abstract
-
Masatoshi SAKAWA, Kosuke KATO, Keiichiro OOURA
Article type: Article
1998 Volume 10 Issue 2 Pages
381-386
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
In this paper, we focus on chaos time series analysis studied widely and actively in recent years and propose a new deterministic nonlinear prediction technique of time series through fuzzy reasoning using neighborhoods' difference in the reconstructed state space based on the Takens's theorem. Then, the proposed method is compared with linear autoregressive prediction method and local fuzzy reconstruction method, which is one of deterministic nonlinear time series prediction methods through their application to actual time series data and its efficiency is demonstrated.
View full abstract
-
1998 Volume 10 Issue 2 Pages
387-390
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS
-
1998 Volume 10 Issue 2 Pages
391-
Published: April 15, 1998
Released on J-STAGE: January 07, 2018
JOURNAL
FREE ACCESS