Font Size: a A A

Based On Rough Set Of Rules For The Algorithm And Covering Rough Set Model

Posted on:2010-04-19Degree:MasterType:Thesis
Country:ChinaCandidate:X W WuFull Text:PDF
GTID:2208360278467470Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
Rough set theory is a powerful tool to deal with inaccurate and indefinite knowledge that was carried out by Pawlak in the beginning of 1980s.It is absorbs lots of popular attention because of its successful applications in many domains such as machine learning,pattern recognition,decision analysis,process control.knowledge discovering in database.expert system,and so on.Attributes reduction and rule extraction are the core of Rough Set theory.the discovery based on attribute reduction and method of acquiring knowledge of Rough Set has important sense:The covering rough sets is an improvement of Pawlak Rough Set to deal with complex practical problems which the latter one can not handle.so it is valuable to do research in the model of covering rough sets.This paper revolves around these two points and research the following three aspects in the model of Rough Set theory:(1)This paper brings out a method of rule fusion,which can form approximate decision-making rules and provide a new way of acquiring knowledge based on Rough Set,by means of analysing the process of Rough Set's attribute reduction and two reduction algorithm of decision-making system.(2)After analysing concepts of supportable subsets in Rough Set.the paper studies the acquiring process of minimal rule sets to put forward an algorithm of minimal induction of decision rules.And experimentation proves the effectiveness of this new algorithm in coordinated decision system.(3)Having investigated four types of covering rough set for dealing with the vagueness and granularity in information systems.this paper mainly improves the definition of upper approximation for covering rough set,and gains the fifth type of covering rough set to make it more reasonable. Thus a framework for the approximation operators of covering rough set.which is endowed with more properties than the existing ones and inter dependency between the lower and upper approximation operations,is set up after studying and describing the attributes of the new covering rough set.
Keywords/Search Tags:rough set, reduct, rule fusion, minimal rules sets, covering, covering based rough sets
PDF Full Text Request
Related items