Grey variable dual precision rough set model and its application

PurposeThe purpose of this paper is to advance a novel grey variable dual precision rough set model for grey concept.Design/methodology/approachTo obtain the approximation of a grey object, the authors first define the concepts of grey rough membership degree and grey degree of approximation on the basic thinking logic of variable precision rough set. Based on grey rough membership degree and grey degree of approximation, the authors proposed a grey variable dual precision rough set model. It uses a clear knowledge concept to approximate a grey concept, and the output result is also a clear concept.FindingsThe result demonstrates that the proposed model may be closer to the actual decision-making situation, can effectively improve the rationality and scientificity of the approximation and reduce the risk of decision-making. It can effectively achieve the whitenization of grey objects. The model can be degenerated to traditional variable precision rough fuzzy set model, variable precision rough set model and classic Pawlak rough set, when some specific conditions are met.Practical implicationsThe method exposed in the paper can be used to solve multi-criteria decision problems with grey decision objects and provide a decision rule. It can also help us better realize knowledge discovery and attribute reduction. It can effectively achieve the whitenization of grey object.Originality/valueThis method proposed in this paper implements a rough approximation of grey decision object and obtains low-risk probabilistic decision rule. It can effectively achieve a certain degree of whitenization of some grey objects.

A Discretization Algorithm Based on Forest Optimization Network and Variable Precision Rough Set

Discretization of multidimensional attributes can improve the training speed and accuracy of machine learning algorithm. At present, the discretization algorithms perform at a lower level, and most of them are single attribute discretization algorithm, ignoring the potential association between attributes. Based on this, we proposed a discretization algorithm based on forest optimization and rough set (FORDA) in this paper. To solve the problem of discretization of multi-dimensional attributes, the algorithm designs the appropriate value function according to the variable precision rough set theory, and then constructs the forest optimization network and iteratively searches for the optimal subset of breakpoints. The experimental results on the UCI datasets show that:compared with the current mainstream discretization algorithms, the algorithm can avoid local optimization, significantly improve the classification accuracy of the SVM classifier, and its discretization performance is better, which verifies the effectiveness of the algorithm.