Fast for Feature Subset Selection Over Dataset

Feature selection is the process of identifying the most suitable features that is compatible with the target set features and thereby reducing feature space to an optimal minimum. The feature selection algorithm can be evaluated on the basis of two criteria: efficiency and effectiveness. Efficiency is measured on the basis of time required to find the feature set and effectiveness measures the quality of the feature. In fact feature selection, as a preprocessing step which is effective in reducing dimensionality, removing irrelevant data, removing redundant data etc. . However, the recent increase of dimensionality of data poses a severe challenge to many existing feature selection methods with respect to efficiency and effectiveness. In this paper various feature selection methods are depicted and proposes a new clustering based feature subset selection algorithm for feature selection.