[in Japanese]

View full abstract

[in Japanese]

View full abstract

In this paper, by considering the experts' imprecise or fuzzy understanding of the nature of the parameters in the problem-formulation process, large-scale multiobjective block-angular linear fractional programming problems involving fuzzy numbers are formulated. By using the α-level sets of fuzzy numbers, the corresponding nonfuzzy α-programming problem is introduced. Through the introduction of an extended Pareto optimality concept, if the decision maker specifies the degree α and the reference objective values, the corresponding extended Pareto optimal solution can be obtained by solving the minimax problems for which the Dantzig-Wolfe decomposition method and the Ritter decomposition method are applicable. Then a linear programming-based interactive decision making method for deriving a satisficing solution for the decision maker efficiently from and extended Pareto optimal solution set is presented. An illustrative numerical example are provided to demonstrate the feasibility of the proposed method.

View full abstract

In this paper, we propose an interactive fuzzy satisficing method for the solution of multiobjective optimal control problems in one-dimensional linear stationary distributed-parameter systems controlled by boundary control functions. In order to reduce the control problem of this distributed-parameter system to approximate multiobjective linear programming problems, we use a numerical integration formula and introduce the suitable auxiliary variables.Then by considering the vague nature of human judgements, we assume that the decision maker may have fuzzy goals for the objective functions. Having elicited the corresponding linear membership functions through the interaction with the decision maker, if the decision maker specifies the reference membership values, the corresponding Pareto optimal solution can be obtained by solving the minimax problems. Then a linear programming-based interactive fuzzy satisficing method for deriving a satisficing solution for the decision maker effiviently from a Pareto optimal solution set is presented. An illustrative numerical example is worked out to indicate the effeciency of the proposed method.

View full abstract

In this paper, an interactive fuzzy decision meking method for large-scale multiobjective nonlinear programming problems with block angular structure is proposed, which is based on the dual decomposition method. After eliciting the membership function for each of the objective functions, the minimax problem is formulated to obtain the Pareto optimal solution which is in a sense close to the reference menbership values specified by the decision maker. In order to solve the slightly modified version of the minimax problem, two-level optimization algorithm(called Algorithm 1) is constructed on the basis of the dual decomposition method. By using Algorithm 1 repeatedly to obtain the corresponding Pareto optimal solution, the interactive algorithm(called Algorithm 2) is also constructed to obtain the satisficing solution of the decision maker from among Pareto optimal solution set.

View full abstract

Hitherto, the emphasis is placed on how to obtain the best solution under a given circumstance. Its objective is to maximize a profit or to minimize a cost. But in real situations of management under uncertainty risk must be taken into consideration to make a decision. In this paper a method of a decision meking is proposed not only to maximize the profit, but also to minimize the risk of a decision using time-series data of each factor included in a decision making. In the method genetic algorithm is employed to efficiently reduce the computation cost. The fuzzy mean-varianve method proposed here is discussed to analyze the decision making of a parsonnel allocation pronlem. In the problem a aspiration level is expressed using a membership function, and the optimal personnel allocation is obtained using the proposal method, where feasible solutions are evaluated using vague aspiration level of a decision maker. In order to reduce the stillbirths in the genetic algorithim the effective coding method is also applied here.

View full abstract

In order to help career decision meking effectively, it is important to make the decision mekers aware of the meaning of their career in their lifetime as well as their everyday life. For this reason, it is useful to structure the persons' motives in a hierarchy and to present the results to them. In this paper, we propose to use the Fuzzy Structural Modeling (FSM) to achieve the goal. FSM is a technique to arrange elements in a hierarchy by applying the fuzzy theory to the data obtained from paired comparisons. Further, we discuss the effectiveness of FSM through an example of the career decision making by college students.

View full abstract

There are many systems which aides purchase decision designed and built based on fuzzy theory. We notice they have similar structures in common, and define them as purchase decision support systems. In this paper it is shown that they have both characteristics of a decision suppot system and a data retrieval system, but they are different from each of them. We also discuss how to construct purchase decision support systems.

View full abstract

This paper introduced the simulation system that helps and supports the party concerned when they negotiate to make a decision. The negotiation model is designed to work by modifying the utility function to compromise in the decision making process. The simulation method based on fuzzy decision making is also suggested to find out the solution or the compromising point that would satisfy both sides. In solution of the problems with multi-stage the movement of each negotiator's opinion is taken into consideration in the view of their adherence to the attributes for decision making in order to make concession, and its concepts is based on human behaviors. After several variations of membership functions and rules basic to the fuzzy control are supposed, the sumulation is done to seek out the compromising point and its process. As a concerte example of the simulation, group car buying decision is dealt with for showing its actual process and the results. All the results suggerst that this method is expected to be efficient in searching for a compromising point to avoid an explosin of combinations of solutions available.

View full abstract

Fuzzy logic is formulated by means of Dempster-Shafer-theory-based models for modal logic of belief. Emphasis is put on the difference between objective and subjective truth values. A way to restrict possible objective truth values is introduced using states of belief formed in modal logic of belief based on plausibility functions derived from evidence. Then, it is shown that the set of subjective truth values, [0,1], of fuzzy logic is not a simple extension of the set of classical values, {0,1}. Extreme values, 1 and 0,of fuzzy sentences can be regarded as representing full belief and full disbelief for the sentences, respectively.

View full abstract

This paper proposes an interactive Japanese sign language interface. The proposed interface is useful to person who has difficulty in hearing. The interface has three functions explained; 1) Japanese sign language motin recognition, 2) Japanese sign language motin generation with animation, 3) Japanese sign language motion learning. Function 1) is realized by a fuzzy label matching method by means of associative inference, for unspecified human motion. Function 2) is realized by an associative inference's interactive inference feature. Function 3) is realized by an activation bidirectional propagation learning method. We show proposed interface usefulness from experiment results. We can apply the proposed interface to nonverbal interfaces.

View full abstract

Some results on fuzzy random variables are derived from the statistical view point. First, conditions for fuzzy random variables are discussed in connection with former definitions and simple sufficient conditions are given under the general definition of fuzzy random variables. Secondly, two kinds of expectation are considered and compared.Moreover some fundamental results are prepared for statistical inference.

View full abstract

A method of identification from input-output data is proposed for a fuzzy model in which the premise part of an if-then rule has a generalized form of the Takagi-Sugeno's fuzzy model This method consists of locally weighted regression for each observation and fuzzy clustering with respect to sample regression coefficients. Efficacy of the proposed method is demonstrated through numerical examples and an application to real data.

View full abstract

This paper presents a learning method based on linguistic instructions using a qualitative linguistic model of the controlled process. The operator's linguistic instructions are interpreted as an adjustment variable, a direction of the adjustment and an information of linguistic hedge.And then the fuzzy control rules are properly adjusted. At the same time, another learning of surpressing the influence of the learning to the other manipulated variables is carried out in addition to the learning about the instructed manipulated variables. The qualitative linguistic model is introduced for the knowledge of this learning. This learning method is applied to the fuzzy control of a chemical reaction process. As a result of simulation, it is shown that the adjustment suited to the operator's control intention is accomplished. Next, a method of using control informations for learning is described, where the weight of the linguistic hedge included in the operator's instruction is changed according to the amount of the control difference. It is also shown by simulation that the 40% of the instruction frequency can be reduced by this method.

View full abstract

Fuzzy Prolog is a logical programing language which is based on the first order fuzzy predicate logic, and Fuzzy Logic Programing is the theoretical foundation of Fuzzy Prolog. In this paper, the logic formulae is expressed by Kowalski's notation who has made the foundation of Logic Programming, not by clause-form which is used by the former investigations. At first, the former investigations of Fuzzy Logic Programming are summarized. Then, the inference on fuzzy logic is considered and the Lukasiewicz's implication is shown to be suitable for the inference on fuzzy logic. Lastly, Fuzzy Logic Programming which adopts Lukasiewicz's implication is defined and the soundnes and completeness of the resolution rule, which is a procedural inference method and plays the leading part of Fuzzy Logic Programming, are clarified.

View full abstract

The purpose of this paper is to combine the concept of fuzzy sets to represent more realistic situations with the well-established traditional queueing models. Information and data of a queueing model are incomplete frequently, when they are very little and there is no information about the model or some parameters of the model are vague.In that case, they may be sometimes given by experts subjectively. Therefore, it is neccessary to employ subjective probabilities for the queueing model of which information and data are including some fuzziness. In this paper, a fuzzy M/M/s queueing model is proposed as a fuzzification of an ordinary M/M/s queueing model. We also apply fuzzy set theory to the closed multiclass model with the fuzzy queues and the mixed multiclass model in which each node consists of fuzzy queues. Thus, we represent the characteristic and performance of the closed multiclass model and the mixed multiclass model based on the proposed fuzzy queueing system.

View full abstract