摘要
区间值决策信息系统作为一种广义的决策信息系统,比传统实数值信息系统具有更强的描述不确定性的能力,即它通过一个区间数来刻画对象关于条件的属性值,那么基于等价关系对论域进行划分就显得过于严格。因此,利用区间数之间的相似性度量建立邻域,然后基于邻域构造粗糙集模型。由于在一个决策信息系统中,部分条件属性对于决策是不重要的甚至是冗余的,那么对信息系统进行恰当的约简对于降低数据规模至关重要,而正域决策过程对应于确定性规则是决策者最为关心的部分。因此,在区间值决策信息系统中,基于决策属性关于条件属性的正域设计了一种启发式属性约简算法。通过对案例分析,展现了在区间值决策信息系统中的粗糙集建模和约简求解过程。实验结果表明:设计的基于正域的启发式属性约简算法是可行的。
Interval-valued decision information system,as a generalized decision information system,has a stronger ability to describe uncertainty than traditional real-valued information systems,that is,it uses an interval number to characterize the object’s conditional attribute value.That means the classification based on an equivalence relation is too strict with respect to this scenario.Therefore,this paper uses the similarity measure between interval numbers to establish the neighborhood,and then constructs the rough set model based on the neighborhood.Since some conditional attributes are not important or even redundant in decision-making information systems,proper reduction of information systems is essential to reduce the size of the data,while the positive region as the most concerned part for decision maker associates with certain decision rule.Therefore,in the interval value decision information system,a heuristic attribute reduction algorithm is designed based on the positive domain of the decision attribute with respect to the condition attribute.Through the case analysis,the rough set modeling and reduction process in the interval value decision information system are presented.The experimental results show that the positive domain based heuristic attribute reduction algorithm designed in this paper is feasible.
作者
陈华峰
龙建武
瞿先平
CHEN Huafeng;LONG Jianwu;QU Xianping(Department of Foundation,Chongqing Telecommunication Polytechnic College,Chongqing 402247,China;College of Computer Science and Engineering,Chongqing University of Technology,Chongqing 400054,China)
出处
《重庆理工大学学报（自然科学）》
CAS
北大核心
2019年第11期130-136,共7页
Journal of Chongqing University of Technology：Natural Science
基金
国家自然科学基金资助项目(61502065)
重庆市科委基础科学与前沿技术研究(重点)项目(cstc2015jcyj BX0127)
重庆市教委科学技术研究项目(KJ1500922,KJ1605201)
关键词
区间值
决策信息系统
邻域
正域
属性约简
interval-valued
decision information system
neighborhood
positive region
attribute reduction
