MINING RULES FROM INCOMPLETE INFORMATION SYSTEM

摘要：

Although the rough sets theory is used for the classification of imprecise,uncertain or incomplete information, the use of the indiscernibility relation may be too rigid in some real situations.In this paper, after analyzing several present models based on rough sets for incomplete information systems,we propose a new method of automatic threshold selection for mining rules from the missing data.Also, a new definition of the discernibility matrix, discernibility function,reducts, and deduction of the decision rules at the present.The missing values are proposed. Finally, a simple example is used to illustrate the procedure of mining rules from incomplete information system.

关键词： Mining rules Incomplete information Similarity relation Automatic threshold selection Rough set

作者: Xuri Yin

作者单位: Institute of Automobile Management of PLA,Bengbu 233011,P.R.China

会议类型: 国际会议

会议名称: 2009 International Symposium on Computer Science and Technology(2009 中国宁波国际计算机科学与技术学术大会)

会议地点: 宁波

会议语种:英文

页码: 435-437

在线出版日期: 2009-11-20（万方平台首次上网日期，不代表论文的发表时间）