计算机工程与应用 ›› 2016, Vol. 52 ›› Issue (14): 54-61.

• 理论与研发 • 上一篇    下一篇

基于Tversky参数化的犹豫模糊集相似性测度研究

彭定洪1,2,聂  军1   

  1. 1.昆明理工大学 质量发展研究院,昆明 650093
    2.哈尔滨理工大学 管理学院,哈尔滨 150040
  • 出版日期:2016-07-15 发布日期:2016-07-18

Research about similarity measure of hesitant fuzzy set based on Tversky’s parameterized model

PENG Dinghong1,2, NIE Jun1   

  1. 1.Institute of Quality Development, Kunming University of Science and Technology, Kunming 650093, China
    2.School of Management, Harbin University of Science and Technology, Harbin 150040, China
  • Online:2016-07-15 Published:2016-07-18

摘要: 针对传统的犹豫模糊集相似性测度对原始数据信息处理不全面的问题,提出一种基于Tversky参数化比率相似性模型的犹豫模糊集相似性测度函数,分析其差异化系数在不同需求情况下的转换形式,并运用于犹豫模糊信息的聚类分析。新的相似性测度函数一方面可避免因添加或取特定的值而导致原始数据信息不准确,另一方面通过对差异化系数的赋值,得出多组可供比较的相似性结果,体现出相似性测度函数良好的动态性和数值的精确性。

关键词: 犹豫模糊Tversky相似性测度, 犹豫模糊集, Tversky参数化比率相似性模型, 聚类分析

Abstract: Since former hesitant fuzzy similarity measure function cannot calculate the original data completely, this paper proposes a new kind of hesitant fuzzy similarity measure based on Tversky’s parameterized ratio model of similarity. Then it analyzes the conversion form of differential coefficient under the condition of different demand. And it also applies the hesitant fuzzy similarity measure to cluster analysis based on hesitant fuzzy information. The new similarity measure can avoid the inaccuracy of?the raw data information caused?by adding or taking specific values. By assigning to the differential coefficient, it also can obtain many groups of comparable results, and the results can reflect the well dynamics and numerical accuracy of the new similarity measure.

Key words: hesitant fuzzy Tversky similarity measure, hesitant fuzzy set, Tversky’s parameterized ratio model of similarity, cluster analysis