Incremental updating approximations in dominance-based rough sets approach under the variation of the attribute set

Dominance-based Rough Sets Approach (DRSA) is a generalized model of the classical Rough Sets Theory (RST) which may handle information with preference-ordered attribute domain. The attribute set in the information system may evolve over time. Approximations of DRSA used to induce decision rules need updating for knowledge discovery and other related tasks. We firstly introduce a kind of dominance matrix to calculate P-dominating sets and P-dominated sets in DRSA. Then we discuss the principles of updating P-dominating sets and P-dominated sets when some attributes are added into or deleted from the attribute set P. Furthermore, we propose incremental approaches and algorithms for updating approximations in DRSA. The proposed incremental approaches effectively reduce the computational time in comparison with the non-incremental approach are validated by experimental evaluations on different data sets from UCI.