基于一般包含度的广义变精度粗糙集  

Generalized Variable Precision Rough Sets Based on Normal Inclusion Measures

作　　者：张红英[1] 董鸣皋[2] 

机构地区：[1]西安交通大学理学院,西安710049 [2]西安石油大学经管学院,西安710065

出　　处：《工程数学学报》2010年第1期37-46,共10页Chinese Journal of Engineering Mathematics

基　　金：国家自然科学基金(60673096;60773174;60703117); 陕西省教育厅社科基金(07JK101)~~

摘　　要：本文将变精度粗糙集模型推广到基于一般包含度的广义变精度粗糙集,利用包含度的性质讨论广义变精度粗糙集的性质。给出广义齐次包含度的定义,验证了常用的概率型包含度等均为广义齐次包含度;给出基于该广义变精度粗糙集的知识约简的方法。不同的包含度代表不同的决策语义,因此借助一般包含度研究变精度粗糙集,能够使尽可能多的有用信息被提取、挖掘,克服了基本粗糙集模型中由于要求绝对精确的包含关系而使大量有用信息丢失,进一步推广了粗糙集模型,拓宽了粗糙集在数据挖掘、知识发现、模式识别及决策分析等领域中的应用。This paper proposes approaches to the knowledge reduction based on generalized variable precision rough sets. The properties of generalized variable precision rough approximation operators are discussed based on the axiomatic definition of inclusion measure. A generalized homogeneous inclusion measure is introduced to study knowledge reduction based on a generalized variable precision rough set model. Since different inclusion measures mean various contexts, the generalized variable precision rough sets overcome the drawbacks which induce the loss of useful information in the classical rough set model and extend the usefulness and effectiveness of the rough set approach in data mining, knowledge discovery, pattern recognition, decision analysis and so on.

关 键 词：变精度粗糙集:包含度 知识约简 协调集 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]