Feature selection using closeness to centers for network intrusion detection
S Sethuramalingam, E. R. Naganathan · Transactions on Networks and Communications · 2014
Classification in intrusion detection data set becomes complex due to its high dimensionality. To reduce the complexity, significant attributes for classification called as features in the data set needs to be identified. Numbers of methods are available in the literature for feature selection. In this paper, a new algorithm based on closeness of points to its center is proposed. It is tested with NSL-KDD data set. The algorithm shows better result.