A soft set approach for fast clustering attribute selection

Attribute-based data clustering has been proven as one of the efficient methods in data clustering. Set theory approaches for data clustering exist to handle attribute-based data clustering. The MDDS, a soft set based technique has proven its applicability in data clustering. However, in reviewing MDDS, where its calculations are based on comparing all constructed multi-soft sets, it still suffers from high computational time. This research presents a modification of the MDDS by generating an alternative technique to reduce its computational complexity. To provide alternative solutions from MDDS algorithm, we derive a new algorithm that can lesser response time. It is using theory of soft set by selecting and excluding the set having no effect domination on other sets. The experiments are implemented in MATLAB software thought to UCI benchmark datasets. The computation experiment illustrate that the time response can be speed up to 67.56 % by proposed algorithm compared with MDDS.