Water Cycle Algorithm for Attribute Reduction Problems in Rough Set Theory

The attribute reduction is known as the procedure for decreasing the number of features in an information system and its action is a vital phase of data mining processing. In the attribute reduction process, the least subset of attributes is selected (according to rough set theory which is employed as a mathematical tool) from the initial set of attributes with very little loss in information. In this study, a new optimization approach, known as the water cycle algorithm (WCA), has been used for attribute reduction and the rough set theory is employed as a mathematical tool to assess quality of solutions that are produced. The idea of the WC as an optimization algorithm was derived from nature, after examining the whole water cycle process which involves the flow of streams and rivers into the sea in the natural world. The WC-RSAR has been employed in public datasets that are obtainable in UCI. From the findings of the experiments, it has been shown that the suggested method performs equally well or even better than other methods of attribute selection.