PROJECT TITLE :

Experimental Analysis of Data Mining Application for Intrusion Detection with Feature Reduction - 2017

ABSTRACT:

As tremendous growth of data in the net, the importance of Network security conjointly dramatically will increase. Network and Host based mostly Intrusion Detection System (IDS) are two primary systems in Network Security infrastructure. When new intrusion varieties are appeared in Network or Host, some serious problems are also seemed to detect these new intrusions. Due to this reason, IDSs demanded better than Signature based mostly detection. The action of intrusion is represented by some options and collects the corresponding featured knowledge from these unsure feature characteristics. In last 2 decades, many techniques are developed to detect intrusion by using these data as human labeling that is terribly time consuming and expensive method. During this paper, we tend to proposed a data mining rule based algorithm referred to as Call Table (DT) to detect intrusion and a brand new feature choice method to get rid of irrelevant/correlated options simultaneously. An empirical analysis on KDD'ninety nine cup dataset was performed by using our proposed and some other existence feature selection techniques with DT and some others classification algorithms. The experimental results showed that proposed approach provides higher performance in accuracy and cost compared among Bayesian Network, Nai¨ve Bayes Classifier and other developed algorithms with data mining KDD'ninety nine cup challenge in all cases.