作者: Yee Leung , Wei-Zhi Wu , Wen-Xiu Zhang
DOI: 10.1016/J.EJOR.2004.03.032
关键词: Association rule learning 、 Decision table 、 Complete information 、 Decision rule 、 Data mining 、 Mathematics 、 Optimal decision 、 Rough set 、 Knowledge acquisition 、 Information system
摘要: Abstract This paper deals with knowledge acquisition in incomplete information systems using rough set theory. The concept of similarity classes is first proposed. Two kinds partitions, lower and upper approximations, are then formed for the mining certain association rules decision tables. One type “optimal certain” two types association” generated. new quantitative measures, “random certainty factor” coverage factor”, associated each rule further proposed to explain relationships between condition parts a reduction descriptors induction optimal such tables also examined.