Adaptive Jaya Optimization Technique for Feature Selection in NSL-KDD Data Set of Intrusion Detection System
7 Pages Posted: 18 Jul 2019 Last revised: 30 Sep 2019
Date Written: July 17, 2019
Now a days, network traffic is increasing due to the exploding usage of smart devices and the Internet. The intrusion detection work centered on feature selection or decrease because few of the features are irrelevant and excess which results prolonged detection procedure and reduces the performance of an intrusion detection system (IDS). The NSL-KDD data set is a refined variant of its predecessor KDD‟99 data set. The intent of this work is to determine essential selected input features in building IDS that is computationally efficient and amazing. For this standard feature selection jaya optimization method is used. In this paper the NSL-KDD data set is analysed and applied Adaptive Jaya Technique for selecting best features to minimize low false alarm rate & maximize detection rate.
Keywords: Intrusion Detection System, NSL-KDD Dataset, Feature Selection, Machine Learning
JEL Classification: Y60
Suggested Citation: Suggested Citation