Intrusion Detection System using Ensemble Learning W-AODE and REPTree Algorithm Accuracy Graphs on WEKA

With the advancement in information and communication technology (ICT), it has become a vital component of humans life. But this technology has brought a lot of threats in cyber world. These threats increase the chances of network vulnerabilities to attack the system in the network. To avoid these attacks there are various methods in which one is Intrusion Detection System (IDS). In IDS, there are various methods used in data mining and existing technique is not strong enough to detect the attack proficiently. Weighted Average One-Dependence Estimator (WAODE) is an enhanced version of AODE and in this technique; we have to assign weights to each attribute. The dependent attributes having lesser weights by defining the degree of the dependencies. This paper deals with a novel ensemble classifier (WAODE+ RepTree) for intrusion detection system. Proposed ensemble classifier is built using two well-known algorithms WAODE and RepTree. This tree improves accuracy and reduces the error rate. The performance of proposed ensemble classifier (WAODE+ RepTree) is analyzed on Kyoto data set. Proposed ensemble classifier outperforms WAODE and RepTree algorithms and efficiently classifies the network traffic as normal or malicious.