数据集的粒化树及其建模应用  

Granular Trees Based on Different Data Sets and their Modeling Applications

作　　者：闫林[1] 宋金朋 

机构地区：[1]河南师范大学计算机与信息工程学院,新乡453007

出　　处：《计算机科学》2014年第3期258-262,共5页Computer Science

基　　金：河南省自然科学基金(082300410340)资助

摘　　要：通过对数据集的不同划分,得到了基于数据集的粒化树。结合关联元素的信息,建立了基于不同数据集粒化树之间的关联关系,确定了两种粒化树中的两条关联链,促成了它们经关联元素的相互联系。由于每一关联链中的粒从粗到细逐步变化,使得关联元素与粒度的逐步细化密切相关,这是粒计算数据处理模式的体现。相关的结论为人才供求问题的算法描述提供了数学模型,并通过实例予以展示。By classifying a data set into different partitions,a granular tree based on the data set was obtained.By using the information of associated elements,a relation called an associated relation was introduced,and connections between two granular trees based on different data sets were established,so that two associated chains were identified,which are connected with each other by an associated element.Because the granules in each associated chain gradually change from a coarse state to a fine state,the associated element model closely links with the changes of the granules,which is consistent with the data processing mode of granular computing.Consequently,as the basis of an algorithm,a mathematical model was created.It can be used to describe the relationship between talent supply and demand.Also,an example shows the process of using the model to carry out data processing.

关 键 词：分层算法 粒化树 关联元素 关联关系 关联链 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]