Title :
A efficiency complete algorithm for attribute reduction
Author :
Yu, Jiang ; Bin, Du
Author_Institution :
Coll. of Software Eng., Chengdu Univ. of Inf. Technol., Chengdu, China
Abstract :
A complete algorithm for attribute reduction in rough set theory based on discernibility matrix was introduced. This algorithm was composed of algorithm1 and algorithm2. Algorithm1 is to select those important condition attributes based on attribute frequency function in every iteration. Algorithm2 removes redundancy and incompatibility attributes in R found out by algorithm1. The time complexity of the algorithms in the worst case was analyzed and the proof of its completeness was given. Algorithm1 and algorithm2 guarantee that the reduction is probable a smallest or smaller one.
Keywords :
data mining; data reduction; matrix algebra; rough set theory; attribute frequency function; attribute reduction; complete algorithm; condition attribute; discernibility matrix; rough set theory; Algorithm design and analysis; Data mining; Delta modulation; Educational institutions; Frequency; Information technology; Pattern recognition; Set theory; Software algorithms; Software engineering; attribute significance; complete algorithm; discernibility matrix; optimal reduction; rough set;
Conference_Titel :
Computer Science and Information Technology, 2009. ICCSIT 2009. 2nd IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-4519-6
Electronic_ISBN :
978-1-4244-4520-2
DOI :
10.1109/ICCSIT.2009.5234522
