A decision-theoretic rough set approach for dynamic data mining
Abstract— Uncertainty and fuzziness generally exist in real-life data. Approximations are employed to describe the uncertain information approximately in rough set theory. Certain and uncertain rules are induced directly from different regions partitioned by approximations. Approximation can further be applied to data mining related task, e.g., attribute reduction. Nowadays, different types of data collected from different applications evolve with time, especially new attributes may appear while new objects are added. This paper presents an approach for dynamic maintenance of approximations w.r.t. objects and attributes added simultaneously under the framework of Decision Theoretic Rough Set < Final Year Projects 2016 > DTRS. Equivalence feature vector and matrix are deﬁned ﬁrstly to update approximations of DTRS in different levels of granularity.