Consistency-Driven Automatic Methodology to Set Interval Numerical Scales of 2-Tuple Linguistic Term Sets and Its Use in the Linguistic GDM With Preference Relation
Consistency-Driven Automatic Methodology to Set Interval Numerical Scales of 2-Tuple Linguistic Term Sets and Its Use in the Linguistic GDM With Preference Relation
复制标题
DOI：
10.1109/tcyb.2014.2336808
复制
发表时间：
2015-04-01
影响因子：
11.8
通讯作者：
Herrera-Viedma, Enrique
中科院分区：
文献类型：
--
作者：
Dong, Yucheng;Herrera-Viedma, Enrique
二元语义模型是一种常用的决策计算工具。为了处理非均匀对称分布的语言项集，提出了数值尺度模型来推广二元语义模型。在数值尺度模型中，基于二元组的模型的关键任务是定义数值尺度函数，该函数在语言信息和数值之间建立一一映射。针对具有语言偏好关系的决策问题，提出了一种基于一致性驱动的二元语义项集区间数值标度自动设定方法。这种一致性驱动的方法是基于一个自然的前提下，关于偏好关系的一致性。如果专家提供的语言偏好关系具有可接受的一致性，则用所建立的区间数值标度转换后的数值偏好关系也是一致的。与现有的基于规范特征值的方法相比，一致性驱动方法提供了一种新的方法来设置区间数值标度，而不需要区间2型模糊集定义的语义。同时，将区间乘性偏好关系引入到两两比较方法中，为区间乘性偏好关系的自动构造提供了一种新的方法，该理论可用于两两比较方法中.最后，我们提出了使用一致性驱动的自动方法在语言群体决策问题的框架和两个数值例子来说明这一建议的可行性和有效性。
The 2-tuple linguistic modeling is a popular tool for computing with words in decision making. In order to deal with the linguistic term sets that are not uniformly and symmetrically distributed, the numerical scale model has been developed to generalize the 2-tuple linguistic modeling. In the numerical scale model, the key task of the 2-tuple based models is the definition of a numerical scale function that establishes a one to one mapping between the linguistic information and numerical values. In this paper, we propose a consistency-driven automatic methodology to set interval numerical scales of 2-tuple linguistic term sets in the decision making problems with linguistic preference relations. This consistency-driven methodology is based on a natural premise regarding the consistency of preference relations. If linguistic preference relations provided by experts are of acceptable consistency, the corresponding transformed numerical preference relations by the established interval numerical scale are also consistent. Compared with the existing approach based on canonical characteristic values, the consistency-driven methodology provides a new way to set the interval numerical scale without the need of the semantics defined by interval type-2 fuzzy sets. Meanwhile, interval multiplicative preference relations are used in the pairwise comparisons method and the presented theory can be utilized in the pairwise comparisons method as it provides a novel approach to automatic construct interval multiplicative preference relations. Finally, we present the framework for the use of the consistency-driven automatic methodology in linguistic group decision making problems and two numerical examples are given to illustrate the feasibility and validity of this proposal.