Constructing Galios Lattice in Hybrid Datasets Based on Rough Set Theory

Existing constructing concept lattice methods cannot process continuous and hybrid attributes in formal concept analysis. This paper extended the existing definition of discretization based on cut-splitting and gave the definition of frequency weightiness function about cut-splitting firstly. Then, a new approach was proposed to constructing Galois lattice after discretizing continuous and hybrid attributes. The introduced approach emphasized on the weightiness of cut-splitting in the process of discretization of continuous attributes, so the approach helped to simplify the classing design and to remain data information in original data table. In order to explore the application of the proposed method, we perform the experiments on datasets from UCI repository. The results verified that the introduced approach is valid and feasible.