粗糙集和证据理论相结合的数据挖掘方法  

A More Effective Data Mining Approach That Adroitly Combines Rough Set Theory with Evidence Theory

作　　者：倪龙强[1] 周振堂[2] 高社生[1] 

机构地区：[1]西北工业大学自动化学院,陕西西安710072 [2]白城师范学院机电系,吉林白城137000

出　　处：《西北工业大学学报》2010年第6期927-931,共5页Journal of Northwestern Polytechnical University

基　　金：航空科学基金(20080818004);陕西省自然科学基金(N9YU0001)资助

摘　　要：在粗糙集和证据理论相结合的数据挖掘技术中,常用的方法是以证据理论为主,而将粗糙集作为获取证据权重的辅助手段。这种结合方法既不能有效发挥证据理论的数值计算作用,也不能很好利用粗糙集理论的分类功能。因此,文章提出一种新的粗糙集和证据理论相结合的数据挖掘技术。首先通过粗集理论对决策表进行约简,消除系统冗余,得到决策规则。其次对经过约简所得到的决策表进行数值处理,降低预测代价,并构建证据焦元空间。最后将证据焦元空间用合成规则进行融合。计算结果表明,文中所提出的粗糙集与证据理论相结合的数据挖掘方法,不但细化了决策规则,而且给出了决策系统规则的定量描述,有效地补充和扩展了证据理论的应用范围。Aim.The introduction of the full paper reviews Refs.1 through 5 and then proposes what we believe to be a more effective data mining approach,which is mathematically explained in sections 1 and 2.The core of section 1 is that we use the rough set theory to reduce the decision table and eliminate redundent information,thus obtaining more concise decision rules.The core of section 2 consists of：（1） we conduct the numerical processing of the decision table thus reduced to cut down the prediction cost;（2） we construct the evidence elements of the combined space with eq.（3）,using the coverage factor obtained from the rough set thoery;（3） we apply the evicdece combination rules proposed in subsection 2.3 to synthesizing the conflicting evidences with eq.（7）.Section 3 gives a numerical example of fusing the decision rules.The fusion results,presented in Table 4,show preliminarily that our data mining approach,which we believe combines adroitly rough set theory with evidence theory,can effectively refine decision rules and describe them quantitatively.

关 键 词：粗糙集 证据合成 规则获取 数据挖掘 

分 类 号：C931[经济管理—管理学]