基于模糊-粗糙集模型的一种归纳学习方法  

Inductive Learning Approach Based on Fuzzy-Rough Set Model

作　　者：石峰[1] 娄臻亮[1] 张永清[1] 陆金桂[2] 

机构地区：[1]上海交通大学塑性成形工程系,上海200030 [2]南京化工大学计算中心,南京210009

出　　处：《上海交通大学学报》2002年第7期920-924,共5页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金资助项目 ( 6 0 175 0 19);上海市高校青年科学基金资助项目

摘　　要：对传统粗糙集理论进行了扩展 ,提出了一种模糊 -粗糙集模型 .利用模糊集理论和 Koho-nen网络自组织映射算法对决策表的连续属性进行模糊化 ,并用模糊贴近度构造模糊相似矩阵 ,把普通粗糙集的不可分辨关系推广为模糊相似关系 .提出一种基于模糊 -粗糙集模型的归纳学习算法FRILA,此算法和决策树算法相比 ,具有得到的规则数目少、规则表示简单等优点 .A fuzzy-rough set model was proposed based on the extension of the classical rough set theory. The continuous attributes in the decision table are fuzzified with the proper fuzzy membership functions and the Kohonen's feature-map algorithm. The fuzzy similar matrix of the attributes is constructed with the fuzzy degree of nearness and the indiscernibility relation in classical rough set is generalized to the fuzzy similarity relation. An inductive learning algorithm based on fuzzy-rough set model(FRILA) was presented. Compared to the decision tree algorithm, it can generate less classification rules and the generated rules are more compact. Finally, an example was illustrated and proves that the approach is effective.

关 键 词：模糊-粗糙集模型 归纳学习方法 模糊集 模糊相似关系 决策表 Kohonen网络自组织映射算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]