Attributes reduction method based on limited tolerance relation in incomplete information system
Ke Luo · Journal of Computer Applications · 2011
The confirmation of core attribute of a decision table is always the basis of information reduction.However,most of the previous reduction methods in core attribute are for complete information system.Extending the reduction algorithm in core attribute and attribute order to incomplete information system,which was used in complete information system,this paper presented an attribute reduction algorithm based on limited tolerance relation in incomplete information system.This method obtained core attribute by constructing an improved discernable matrix of decision table in incomplete information system,and sorted the attributes which did not belong to core attribute by ability of affecting classification quality intuitively.Thus,the reduction result was ensured to be a relatively minimized reduction.This method is proved to be feasible and more effective through comparison.