A New Method for Knowledge Acquisition from Incomplete Information System Based on Rough Set

Abstract

Knowledge acquisition is an important research area of knowledge discovery database and machine leaning, which includs knowledge reduction and knowledge extraction from large number of original data. Researchers in these fields are very interested in this new research topic since it offers opportunities to discover useful knowledge in information systems.Many algorithms demand information system must be complete. To deal with the problem in an incomplete information system, this paper proposed a method based on rough set theory. Based on tolerance relationship, the concept of tolerance relationship similar matrix via using an extension of equivalence relationship of rough set theory are defined in incomplete information systems. It calculates the core attributes of incomplete information systems via the tolerance relationship similar matrix. To overcome its drawback of NP-hard time complexity,It applies attribute significance, which this paper puts forward based on attribute frequency in the tolerance relationship similar matrix, as the heuristic knowledge, makes use of binsearch heuristic algorithm to calculate the candidate attribute expansion so that it can reduce the expansion times to speed up reduction. Experiment results show that the algorithm is simple and effective.