A Superiority Index Based Method for MCDM Under Uncertain Linguistic Setting
This paper proposes a method to aid the selection process of multi-criteria decision making (MCDM) problem, in which the criteria values provided by experts are in the form of uncertain linguistic variables. Based on the partial order of uncertain linguis
- PDF / 170,338 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 34 Downloads / 171 Views
A Superiority Index Based Method for MCDM Under Uncertain Linguistic Setting Zhibin Wu
Abstract This paper proposes a method to aid the selection process of multi-criteria decision making (MCDM) problem, in which the criteria values provided by experts are in the form of uncertain linguistic variables. Based on the partial order of uncertain linguistic variables, the superiority index of one alternative over another for a given criterion and the overall superiority index of one alternative are defined. Some properties of the superiority index are presented and discussed. Then a procedure based on the superiority indices is presented to select the best alternative(s). The proposed method is also extended to multi-criteria group decision making. Finally, one example of evaluating the technological innovation capability of enterprises is given to verify the proposed method. Keywords Multi-criteria decision making (MCDM) · Superiority index · Linguistic variable · Group decision making
23.1 Introduction Multi-criteria decision making (MCDM) addresses the problem of choosing an optimum choice from a set of alternatives associated with non-commensurate and conflicting attributes [7]. MCDM problems arise in many practical situations and have drawn much attention in the management and engineering field. A lot of methods for solving such problems have been proposed under numerical settings, for example, simple additive weighting, multiplicative exponential weighting, the entropy method and technique for order preference by similarity to ideal solution (TOPSIS) [7].
Z. Wu (B) Uncertainty Decision-Making Laboratory, Sichuan University, Chengdu 610064, People’s Republic of China e-mail: [email protected]
J. Xu et al. (eds.), Proceedings of the Eighth International Conference on Management Science and Engineering Management, Advances in Intelligent Systems and Computing 280, DOI: 10.1007/978-3-642-55182-6_23, © Springer-Verlag Berlin Heidelberg 2014
253
254
Z. Wu
There are cases in which the information cannot be expressed precisely in a quantitative form but may be stated only in linguistic terms. For example, when attempting to qualify phenomena related to human perception, we are likely to use words in natural language instead of numerical values. (e.g. when evaluating the “comfort” or “design” of a car, terms like “bad”, “poor”, “tolerable”, “average”, or “good” can be used [9]). A more realistic measurement is to use linguistic assessments instead of numerical values [11, 12]. Linguistic variables are very useful in situations where the decision making problems are too complex or ill-defined to be described properly using conventional quantitative expressions. A number of studies have emphasized the impotence of MCDM with fuzzy or linguistic data [8]. Fuzzy or linguistic MCDM approaches have been applied to many areas, for example, technology transfer strategy selection [2], product design and selection [10], alternative-fuel buses selection [19], collaboration satisfaction evaluation [5], supplier evaluation [1
Data Loading...
