The Close-Degree of Concept Lattice and Attribute Reduction Algorithm Based on It

Concept lattice is a new mathematical tool for data analysis and knowledge processing. Attribute reduction is very important in the theory of concept lattice because it can make the discovery of implicit knowledge in data easier and the representation simpler. In this paper the reduction of the concept lattice was investigated. First, we present a close-degree of concept to measure the close-degree of two concepts with the attributes reduction. Based on the close-degree of two concepts, we propose the close-degree of concept lattice. Then we use the close-degree of concept lattice as heuristic information and design an attribute reduction algorithm. The reduction algorithm attempts to get one reduction of the attribute set of concept lattice. Last, we give an application example for proving the validity of the algorithm.