摘要
对于多尺度直觉模糊决策系统,现有尺度生成的相邻合并或邻域方法会人为降低相似数据之间的关联性,导致无法精确反应数据之间的内在联系;在粒度变换过程中,数据合并的速度过快极大地限制了最优尺度选择的空间等问题。针对这些问题,定义了β多尺度直觉模糊粒度变换函数,构造了β多尺度直觉模糊决策系统,研究了β多尺度直觉模糊决策系统性质和结构;建立了满足单调性的β多尺度直觉模糊知识粒度,提出了决策和多尺度直觉模糊条件的β直觉模糊知识依赖度;基于星雀优化算法,构造了β多尺度直觉模糊决策系统的适应度函数,设计了β多尺度直觉模糊决策系统的最优尺度选择算法。通过数值实验验证表明,提出模型具有可行性和有效性。
Optimal scale selection is one of the key problems in multi-scale decision system,which provides more reasonable and efficient decision support for the final decision or classification.In the multi-scale intuitionistic fuzzy decision system,the adjacent merging or neighborhood method generated by the existing scale can artificially reduce the correlation between similar data.As a result,it cannot accurately reflect the internal relationships between the data.In the process of granularity transformation,the speed of data merging greatly limits the space of optimal scale selection.In order to overcome these limitations,firstly,theβmulti-scale intuitionistic fuzzy granularity transformation function is defined,theβmulti-scale intuitionistic fuzzy decision system is constructed,and the properties and structure of theβmulti-scale intuitionistic fuzzy decision system are studied.Secondly,theβmulti-scale intuitionistic fuzzy knowledge granularity satisfying monotonicity is established,and the dependency degree of the intuitionistic fuzzy knowledge for decision and multi-scale intuitionistic fuzzy conditions is proposed.Based on the nutcracker optimization algorithm,the fitness function ofβmulti-scale intuitionistic fuzzy decision system is constructed,and the optimal scale selection algorithm ofβmulti-scale intuitionistic fuzzy decision system is designed.Finally,the effectiveness and feasibility of the proposed model are verified by numerical experiments.
作者
郑美玲
马周明
李嘉坪
ZHENG Meiling;MA Zhouming;LI Jiaping(School of Mathematics and Statistics,Minnan Normal University,Zhangzhou 363000,P.R.China;Fujian Key Laboratory of Granular Computing and Applications,Minnan Normal University,Zhangzhou 363000,P.R.China)
出处
《重庆邮电大学学报(自然科学版)》
北大核心
2025年第6期805-816,共12页
Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition)
基金
国家自然科学基金项目(62476078)
福建省自然科学基金(2025J01362,2024J01799)。
关键词
粒度变换函数
最优尺度选择
星雀优化算法
β多尺度直觉模糊决策系统
granularity transformation function
optimal scale selection
nutcracker optimization algorithm
βmulti-scale intuitionistic fuzzy decision system
