期刊
INFORMATION FUSION
卷 51, 期 -, 页码 271-286出版社
ELSEVIER
DOI: 10.1016/j.inffus.2019.04.002
关键词
Unbalanced double hierarchy linguistic term set; Linguistic sale function; Semantic model; Qualitative decision making; TOPSIS; Green mine
资金
- National Natural Science Foundation of China [71771156]
- 2018 Key Project of the Key Research Institute of Humanities and Social Sciences in Sichuan Province [Xq18A01, LYC18-02]
- Electronic Commerce and Modern Logistics Research Center Program
- Key Research Base of Humanities and Social Science, Sichuan Provincial Education Department [DSWL18-2]
- Spark Project of Innovation at Sichuan University [2018hhs-43]
The double hierarchy linguistic term set is a linguistic technique to elaborately and accurately represent complex linguistic information for qualitative decision-making problems. Considering that unbalanced semantics may appear in the first and second hierarchy linguistic term sets, the unbalanced double hierarchy linguistic term set (UDHLTS) is proposed in this paper. To characterize the unbalanced distribution of semantics of the second hierarchy linguistic terms, we propose three linguistic scale functions with cognitive bias parameters. Then, a non-linear fitting method is presented to determine these parameters. Combining the first and second hierarchy linguistic term set, we construct eight semantic models with distinct risk appetite parameters and linguistic cognitive bias parameters to capture the semantics of linguistic terms in the UDHLTS. In this way, we can use specific semantic model to represent experts' opinions associated with the UDHLTS. In addition, by using the semantic model of the UDHLTS, linguistic information from different experts can be compared and aggregated quantitatively. To illustrate the applicability of the UDHLTS, we develop a UDHL-TOPSIS method for multi-expert qualitative decision making problems. An engineering example concerning green mine selection is given to illustrate the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据