-
[in Japanese]
Article type: Article
1997 Volume 9 Issue 3 Pages
301-
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
Yasuhiko KITAMURA
Article type: Article
1997 Volume 9 Issue 3 Pages
302-311
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
Takashi KATO
Article type: Article
1997 Volume 9 Issue 3 Pages
312-317
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
Akihiro YAGI
Article type: Article
1997 Volume 9 Issue 3 Pages
318-326
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
Kunihiko IIZUKA
Article type: Article
1997 Volume 9 Issue 3 Pages
327-331
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
Yushi UNO
Article type: Article
1997 Volume 9 Issue 3 Pages
332-336
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Bibliography
1997 Volume 9 Issue 3 Pages
337-340
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
1997 Volume 9 Issue 3 Pages
341-
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
1997 Volume 9 Issue 3 Pages
342-343
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
1997 Volume 9 Issue 3 Pages
344-345
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
Marimin
1997 Volume 9 Issue 3 Pages
346-349
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
Article type: Article
1997 Volume 9 Issue 3 Pages
349-
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1997 Volume 9 Issue 3 Pages
350-
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1997 Volume 9 Issue 3 Pages
350-351
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1997 Volume 9 Issue 3 Pages
351-352
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
1997 Volume 9 Issue 3 Pages
353-
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
1997 Volume 9 Issue 3 Pages
353-
Published: 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
[in Japanese]
Article type: Article
1997 Volume 9 Issue 3 Pages
354-
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
1997 Volume 9 Issue 3 Pages
355-362
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
-
Yujiro MIYATA, Takeshi FURUHASHI, Yoshiki UCHIKAWA
Article type: Article
1997 Volume 9 Issue 3 Pages
363-372
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
Abduction is one of the methods of inference for creative thinking support systems or diagnosis support systems. Peng and Reggia proposed abductive inference based on associations between causes and effects for fault diagnosis. Their method had the advantages in the calculation cost for of explanations. They discussed the probabilistic relations between the disorders and the manifestations for the evaluation of the explanations. However, it is required for the real world fault / medical diagnosis to treat the degree of manifestation. There are cases where that the probability of the calculated explanation is low but its belief which is calculated based on the degress of manifestations is high. In this paper we propose a diagnostic problem-solving fuzzy abductive inference which can treat the degree of manifestation. This method can infer the combinations of disorders with their degress of belief using the degress of manifestations. This method provides the flexible description of the target system using the degress of disorders by linguistic labels and the necessary cause-and-effect relationships.
View full abstract
-
Chihiro IWANAGA, Ken SASAKI, Takashi HAMAOKA
Article type: Article
1997 Volume 9 Issue 3 Pages
373-383
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
We investigated the suitability of the palatable water standards established by the Ministry of Welfare in Japan using chemical analyses and sensory tests data on 82 water samples obtained in Hiroshima and other districts. We confirmed hjgh correlations between the results of sensory tests and four explanatory variables (organic matter, total handness, iron, bicarbonate), indicating appropriateness of the standards. Furthermore, we constructed multiple linear regressions and simplified fuzzy models using the four factors as explanatory variables. It shows that simplified fuzzy models are more practical than multiple linear regressions.
View full abstract
-
Ichiro NISHIZAKI, Mastoshi SAKAWA
Article type: Article
1997 Volume 9 Issue 3 Pages
384-394
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
When game theory is applied to real world problems such as decision making in public and managerial problems, there are occasions when it is difficult to assess exact payoffs because of inaccuracy in information and uncertainty of describing states. To analyze such situations, games with fuzzy payoffs, in which payoffs are represented as fuzzy numbers, are often employed.In this paper, we consider equilibrium solutions in bimatrix games with fuzzy payoffs. First, we examine the case where there is no information on the preferences of players. The equilibrium solutions are defined from a viewpoint of possibility and necessity, and existence conditions of these solutions are investigated. Second, we examine the case where the preferences of the players are represented by fuzzy goals to the payoffs of the players and consider equilibrium solutions with respect to the attainment of each of their goals. Third, we assume that each player maximized the mean of the fuzzy expected payoff and minimizes its spread, and then consider equilibrium solutions of the games with fuzzy payoffs in which the players optimize these objectives in accordance with their preferences.
View full abstract
-
Makoto ASANO, Kazuhiko HIJIKATA, Ken KOYAMA
Article type: Article
1997 Volume 9 Issue 3 Pages
395-401
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
In the possiblistic regression analysis, the obtained fuzzy mean values bu applying to various data seem alike as to the coefficients obtained by normal multi regression analysis.On the other hand, the spreads of fuzzy coefficients are generally determined by including entire independent variables subject to minimize the summation of spreads.However, sometimes it happens to that it is very hard to explain the spreads rationally.Why does this happen and what is needed to improve this are investigated through simple examples.And real data obtained from experimental testes are also analyzed by proposed method in this paper.
View full abstract
-
Hiroshi TAKAYANAGI, Takahiro YAMANOI
Article type: Article
1997 Volume 9 Issue 3 Pages
402-407
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
The grade of agricultural products in Japan is in many cases based on the degree of bend in the product, and the degree of curvature is especially reflected in the price of asparagus and cucumbers. Because this property has many aspects, machine classification is not easily achievable. However, there is an increasing demand for automated grading of seasonal agricultural products. In order to classify shapes of asparagus automatically, we applied the fuzzy logic to determine the degree of curvature and a neural network to classify shapes of this product. Classification by this system has a 93% coincidence with results from visual classification by experts.
View full abstract
-
Koichi YAMADA
Article type: Article
1997 Volume 9 Issue 3 Pages
408-418
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
This paper describes a way of reasoning through propagation of truth value constraints in the hierarchical Multi-valued Logic Network. Multi-valued Logic Network (MVL network) is a directed acyclic graph that expresses causal relations among nodes as implications of a multi-valued logic. Each node expresses a proposition of event arising, and has a logical variable that takes a truth value in [0,1]. Each arc between two nodes expresses the causal relation between them, and also has a truth value in [0,1]. This paper focuses on one of the simplest type of MVL networks - hierarchical networks with two layers, and proposes a way of reasoning in which truth value constraints given to arbitrarily nodes are propagated to the other ones in the network. The constraints are expressed as truth intervals.First, the paper defines the propagation of truth interval using causal inference and inverted causal inference based on a multi-valued logic. The propagation is done in two directions - forward and backward - aong the arc. It also has two types; weak and sterong propagation. The weak one propagates a truth constrainst so that the truth intervals of the connected two nodes can be consistent. The strong one propagates it so that the propagated interval can support or can be supported by the propagating one. Then, the paper proposes a way to derive truth intervals of all nodes using the weak propagation under the restriuction that teh derived intervals should be included in the given intervals at first. Furthermore, it proposes a way based on the strong propagation to derive truth intervals of all nodes when those of some nodes are fixed. Finally, the paper shows a numerical example.
View full abstract
-
Wataru OKAMOTO, Shun'ichi TANO, Toshiharu IWATANI, Atsushi INOUE
Article type: Article
1997 Volume 9 Issue 3 Pages
419-425
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS
In this paper, we consider an effect on inference results for truth-qualified natural language propositions involving fuzzy quantigiers by truth-qualifiers. We proposed an inference method previously. For examples, for the proposition "Many tall men are heavy is τ", we can infer a modified proposition "Most tall men are more or less heavy is τ" by the method, where the fuzzy quantifier "Most" in the inferred proposition can be resolved analytically, according to the modifier "more or less". Here τ is a monotone and injective truth-qualifier.In this paper, we propose a method which effects on the inference results following to adding a weight attribute to truth-qualified fuzzy sets by given truth-qualifiers. By the method, when we infer the proposition "Most tall men are more or less heavy is true" from the proposition "many tal men are heavy is true", it is possible that we infer the proposition "Almost all of tall men are more or less heavy is very true" from the proposition "Many tall men are heavy is very true".By the method, it is possible that we get different inference results depending on the effect by truth-qualifiers.
View full abstract
-
1997 Volume 9 Issue 3 Pages
426-429
Published: June 15, 1997
Released on J-STAGE: September 25, 2017
JOURNAL
FREE ACCESS