Fumiko Seo

Fuzzy multiattribute utility analysis for collective choice

An extension of multiattribute utility analysis for the multiple-agent decision problem is presented. Although multiattribute utility analysis is concerned with decision-making under uncertainty, assessment of the parameters of the multiattribute utility functions is actually performed deterministically by the single decision-maker. The authors are concerned with fuzzy evaluation of the multiattribute utility function, which is based on fuzzy preference ordering and scaling constants using membership functions of fuzzy set theory. The fuzzy approach treats a conceptual imprecision that accrues from a multiplicity of evaluation. A fuzzy multiattribute utility function with multiple agent evaluation is derived. A computer package, ICOPSS/FR, for ensuring the transistivity of collective preference ordering in an agreement level is demonstrated for assessment of fuzzy multiattribute utility functions.

Interactive Multiobjective Decisionmaking for Large-Scale Systems and Its Application to Environmental Systems

A new interactive multiobjective decisionmaking technique for solving large-scale multiobjective optimization problems is presented. Our method combines the desirable features of both the surrogate worth trade-off (SWT) method and the multiattribute utility function (MUF) method by incorporating the dual decomposition method to obtain Paretooptimal solutions. By assessing the marginal rates of substitution of the decisionmaker (DM) and maximizing the local proxy preference functions sequentially, we can interactively derive his preferred solution efficiently from among the Pareto-optimal solutions obtained by the dual decomposition method. The industrial pollution control problem in industrialized Osaka City in Japan is formulated, and it is demonstrated that the problem can be effectively solved by the proposed method.

Interactive multiobjective decision making in environmental systems using sequential proxy optimization techniques (SPOT)

In this paper, a new interactive multiobjective decision-making technique for solving multiobjective optimization problems: the sequential proxy optimization technique (SPOT), is presented. Using this technique, the preferred solution for the decision maker can be derived efficiently from among a pareto optimal solution set by assessing his marginal rates of substitution and maximizing the local proxy preference functions sequentially. Based on the algorithm of SPOT, a time-sharing computer program is also written to implement man-machine interactive procedures. The industrial pollution control problem in Osaka City in Japan is formulated and the interaction processes are demonstrated together with the computer outputs.

A game theoretic approach with risk assessment for international conflict solving

A game-theoretic approach based on risk assessment for evaluating the effectiveness of the formation of international concords is discussed. An n-person cooperative game in the characteristic-function form is used for international conflict solving. A concept for solution of a game called a nucleolus and its alternative forms are derived, and a two-layer hierarchical system for the evaluation is constructed. At the first layer, the concept of the multiattribute risk function (MRF) is defined and derived by assessing value tradeoffs in the risk profile for each country. At the second layer, for effective formation of international coalitions for international conflict solving, a game theoretic approach is used. The characteristic function of the n-person cooperative game is constructed in terms of the decrease of the MRF values due to the formation of coalitions. The alternative concepts for the augmented nucleolus are compared with each other in terms of the dual solution concept. >

A Configuration of Intelligent Decision Support Systems for Strategic Use: Concepts and Demonstrations for Group Decision Making

This paper presents a new concept of Intelligent Decision Support Systems for Strategic Use (IDS3) and its demonstration for constructing group utility functions based on possibility distributions.

An experimental method for diversified evaluation and risk assessment with conflicting objectives

An experimental method is presented for treating diversity of evaluation for alternative regional policies with conflicting multiple objectives. A measure to assess the risk that an implementation of alternative regional policies are constructed under an efficiency criterion based on sensitivity analysis of multiattribute utility functions. Then an entropy problem is solved to evaluate dispersion of selection for policy attributes; the diversity of evaluation is considered under an equity criterion. The default index is constructed from the probability assessment by the entropy model for measuring quantitatively the diversity of evaluation, and is used to compare the acceptability of alternative policies to various groups in society. The method is applied to an empirical case study of a regional problem in the southern part of Osaka Prefecture in Japan.

Multiattribute Utility Analysis

Multiattribute utility analysis is concerned with the judgmental phase of MCDM. This method provides a heuristic device for constructing the scalar-valued valuation function defined on multiple objectives. This device for scalarization of vector-valued objectives intends to directly cope with the noncommensurability of the multiple objectives and to assess the value trade-offs among these criteria. The theoretical background of this method is founded on the von Neumann-Morgenstern expected utility hypothesis. This chapter provides a methodological description of multiattribute utility analysis. In this section, the main concepts of multiattribute utility analysis are examined and the representation theorems are discussed.

Evaluation of Telecommunication Systems with Multiple Criteria Decision Analysis: A Game Theoretic Approach

In this contribution, we present a method based on multiple criteria decision analysis for evaluating the formation of a new integrated telecommunications system. Our method is a game theoretic approach based on fuzzy multiattribute utility analysis. Game theory, which has been developed for multiple agents decision making, is used to evaluate the efficiency of forming an integrated information network. First, the construction of alternative integrated systems for existing individual communication networks is evaluated from the point of view of utility exchanges, and here fuzzy multiattribute utility analysis is applied. For considering a diversity in the evaluation due to multiperson decision making, a fuzzy preference relation is introduced into the process in order to assess the multiattribute utility function (MUF). This device is used for numerically assessing agreement levels in constructing MUFs. The fuzzy MUF (FMUF) is assessed for each service of the telecommunications systems. Second, the characteristic function of an n-person cooperative game is assessed in terms of an incremental value of FMUF. The payoff value based on the incremental value of FMUF is calculated for each service treated as a player who will participate in an integrated network to be regarded as a coalition. Alternative concepts of the nucleolus are used as the solution concepts of a game. Third, we will provide a device to measure these alternative solutions in comparable terms.

Technology Assessment and Decision-Aid Utility Analysis in Fossil Fuel-to-Fuel Conversion

In dealing with energy shortage problems around the world, energy utilization is closely related to technological development of fossil fuel-to-fuel conversion processes which provide alternatives to petroleum. Among the fossil fuel-to-fuel processes several processes of making synthetic gas and oil from coal have been developed by several agencies. These processes are characterized by competitiveness and substitutability of diversified technologies in the same research and development area, and they have many deleterious effects on society such as resource exhaustion and environmental pollution. Thus alternative processes of technologies and their effects on human society should be examined and compared not only from the economic but from various social points of view as well. Thus, we propose the socio-technique (SOTEC) concept for selecting the appropriate technology to the existing society. Technology assessment is a multicriteria problem in which the evaluation criteria are not comparable because they are noncommensurable. A multicriteria method which takes uncertainty into account is known as decision analysis. In decision analysis the utility concept is used as a device to commensurate noncommensurable multiple criteria into a unified term. In this paper, we intend to apply a modified form of decision analysis to selecting appropriate substitute-energy technologies with regard to specific regional conditions. A numerical measurement of comprehensive evaluation, named “utility”, is derived for each alternative technical process.

Imputation of Dual Prices

This chapter presents a device for using the dual optimal solutions, or the Kuhn-Tucker (Lagrange) multipliers generated from mathematical programming as the theoretical valuation prices for MCDM, with which multiple criteria can be made commensurate in a comparable term and based on which the judgmental phase of MCDM can be meaningfully combined with the analytical phase.