A Novel Approach for Periodically Updating Rough Approximations Upon Multi-Dimension Variation

In present era, transformation of almost all fields of life toward digitalization, poses various challenges. One of them is effective data analysis of large datasets and its complexity multiplies when dataset evolves with time. Dominance based rough set theory is a mathematical based tool, which efficiently probes hidden patterns from preference ordered based datasets. But in case of large datasets, computation of DRSA approximations becomes crucial step. In conventional DRSA algorithm, approximation sets have to be re-calculated when some change occurs in data over time. Therefore, repetitive calculations further increase the computational cost of approximations in real-time domain. In this paper, we researched the execution cost of approximations and designed a periodic approach to efficiently update DRSA approximations when variations occur in an object set and value set of decision attribute. We tested and compared the proposed dynamic approach with conventional approach and another dynamic approach, using UCI datasets. The results have shown that the proposed approach marked 98% reduction in computational time in comparison with conventional approach and 25% reduction in comparison with dynamic approach while updating DRSA approximations upon multi-dimensional variations.