Investigating the Impact of Feature Reduction Through Information Gain and Correlation on the Performance of Error Back Propagation Based IDS

Research in the field of IDS has been going on since long time; however, there exists a number ways to further improve efficiency IDS. This paper investigates performance Intrusion detection system using feature reduction and EBPA. The first step involves features, based combination information gain correlation. In next step, error back propagation algorithm (EBPA) is used train network then analyze performance. EBPA commonly due its ease use, high accuracy efficiency. proposed model tested over KDD Cup 99 NSL-KDD datasets. Results show that with reduced set outperforms other models, both terms metrics processing time.