Data Reduction Through Combining Lattice with Rough Sets

In this paper, we propose a new efficient data reduction algorithm through combining lattice with rough set. On the basis of lattice learning, the algorithm applies the concept of attribute reduction in the theory of rough sets and calculates the importance degree of attributes automatically by a density based approach. Under acceptable classification precision and complexity, it reduces row and column together and generates concise classification rules. The algorithm represents a solution to the problem of attribute generalization on the basis of lattice learning and automatic estimation of attribute weights independently of domain experts. Attributes in the classification rules are ordered by the importance degree of attribute. So in the classification and by the sequence of importance degree of attribute, from one attribute to another, we can exclude the objects which dissatisfy the constraint from the attribute. And then it can, to a large extent, reduce the size of data set of object classified by scanning attribute of the rules, and thereby the efficiency of classification is improved greatly