Overview of feature subset selection algorithm for high dimensional data

Feature selection process involves identifying a subset of features that provides same results as the original entire set of features. Feature subset selection removes irrelevant and redundant features for reducing data dimensionality. Feature selection, also known as attribute subset selection. A feature selection algorithm can be measured from both the efficiency and effectiveness points. The efficiency composes of the time required to find a subset of features, whereas effectiveness is related to the accuracy of the subset of features finally selected. The objective of feature selections are increasing the prediction performance of the predictors, providing correct and fast result. This paper analyses some existing popular feature selection algorithms like CFS, FCBF, FAST, Relief etc., addresses the strengths and challenges of those algorithms.