An Efficient Intrusion Detection Based on Decision Tree Classifier Using Feature Reduction

Large computational value has always been a restraint in processing huge network intrusion data. This problem can be extenuated through feature selection to abbreviate the size of the network data involved. In this paper, we first deal existing feature selection methods that are computationally executable for processing vast network intrusion datasets. In this paper, we study and analysis of four machine learning algorithms (J48, BayesNet, OneR, NB) of data mining for the task of detecting intrusions and compare their relative performances. Based on this study, it can be concluded that J48 decision tree is the most suitable associated algorithm than the other three algorithms with high true positive rate (TPR) and low false positive rate (FTR) and low computation time with high accuracy. Index TermsIntrusion Detection; Machine Learning; Decision Tree; Bayes Net; NB; KDD 99