Operations Research and Management Science ›› 2022, Vol. 31 ›› Issue (2): 23-28.DOI: 10.12005/orms.2022.0038

• Theory Analysis and Methodology Sludy • Previous Articles     Next Articles

Probabilistic Dual Hesitant Fuzzy Multi-attribute Decision Making Method Based on Entropy and Correlation Coefficient

SU Bing-jie1,2, LU Fang-yuan2, ZHU Feng3   

  1. 1. School of Economics of Xiamen University, Xiamen 36100, China;
    2. School of Business Zhengzhou University, Zhengzhou 450001, China;
    3. School of Management Engineering Zhengzhou University, Zhengzhou 450001, China
  • Received:2020-03-05 Online:2022-02-25 Published:2022-03-11

基于熵和关联系数的概率对偶犹豫模糊多属性决策方法

苏冰杰1,2, 卢方元2, 朱峰3   

  1. 1.厦门大学 经济学院,福建 厦门 361001;
    2.郑州大学 商学院,河南 郑州 450001;
    3.郑州大学 管理工程学院,河南 郑州 450001
  • 通讯作者: 朱峰(1994-),男,河南信阳,博士生,研究方向:多属性决策,复杂系统建模。
  • 作者简介:苏冰杰(1993-),女,河南郑州,博士生,研究方向:模糊决策,数字经济;卢方元(1962-),男,河南郑州,博士,研究方向:模糊决策,区域创新
  • 基金资助:
    河南省软科学重点项目(202400410049)

Abstract: A multi-attribute decision making method based on entropy and correlation coefficient is proposed for multi-attribute decision making with completely unknown attribute weights under probabilistic dual hesitant fuzzy environment. First, the axiomatic definition and formula of probabilistic dual hesitant fuzzy entropy are defined. Then, based on the feature information set and entropy measure of probabilistic dual hesitant fuzzy set, the correlation coefficient of probabilistic dual hesitant fuzzy set is defined. Finally, the multi-attribute decision-making model is constructed based on the entropy and correlation coefficient of the probabilistic dual hesitant fuzzy set. And the validity and rationality of the model are verified by an example.

Key words: multi-attribute decision making, probabilistic dual hesitant fuzzy set, entropy, correlation coefficient

摘要: 针对概率对偶犹豫模糊环境下属性权重完全未知的多属性决策问题,提出基于熵和关联系数的多属性决策方法。首先定义了概率对偶犹豫模糊熵的公理化定义和公式,然后基于概率对偶犹豫模糊集的特征信息集合和熵测度定义了概率对偶犹豫模糊集的关联系数,最后根据概率对偶犹豫模糊集的熵和关联系数构建多属性决策模型,并通过算例验证了该模型的有效性和合理性。

关键词: 多属性决策, 概率对偶犹豫模糊集, 熵, 关联系数

CLC Number: