Knowledge acquisition in vague objective information systems based on rough sets

The growing volume of vague information poses interesting challenges and calls for new theories, techniques and tools for analysis of vague data sets. In this paper, we study how to extract knowledge from vague objective information systems (VOISs) based on rough sets theory. We first introduce the basic notion termed rough vague sets by combining rough sets theory and vague sets theory. By using the rough vague lower approximation distribution in the VOIS, the concept of attribute reduction is introduced. Then, we develop an algorithm based on a discernibility matrix to compute all the attribute reductions. Finally, a viable approach for extracting decision rules from the VOIS is proposed. An example is also presented to illustrate the application of the proposed theories and approaches in handling medical diagnosis problems.