Discretization of Attributes Based on Relative Positive Region of Decision Attribute
Traditional rough set theory can hardly handle the real-life data which contains continuous attribute. In order to solve this problem, a new method for discretization of continuous attributes based on relative positive region of decision attribute is presented. The method which distinguishes from traditional discrete methods firstly gets the relative positive region of decision attribute, and then discrete continuous attributes with the theorem proved in this paper. Finally, the result of an example shows that our method is efficient and feasible.
C. J. Zhou et al., "Discretization of Attributes Based on Relative Positive Region of Decision Attribute", Advanced Materials Research, Vols. 271-273, pp. 253-257, 2011