Genetic Algorithm to Solve the Problem of Small Disjunct In the Decision Tree Based Intrusion Detection System

• Published in: International journal of computer network and information security Vol. 7; no. 8; pp. 56 - 71
• Main Authors: Azad, Chandrashekhar, Kumar Jha, Vijay
• Format: Journal Article
• Language: English
• Published: Hong Kong Modern Education and Computer Science Press 08.07.2015
• ISSN: 2074-9090; 2074-9104
• DOI: 10.5815/ijcnis.2015.08.07

Intrusion detection system is the most important part of the network security system because the volume of unauthorized access to the network resources and services increase day by day. In this paper a genetic algorithm based intrusion detection system is proposed to solve the problem of the small disjunct in the decision tree. In this paper genetic algorithm is used to improve the coverage of those rules which are cope with the problem of the small disjunct. The proposed system consists of two modules rule generation phase, and the second module is rule optimization module. We tested the effectiveness of the system with the help of the KDD CUP dataset and the result is compared with the REP Tree, Random Tree, Random Forest, Na?ve Bayes, and the DTLW IDS (decision tree based light weight intrusion detection system). The result shows that the proposed system provide the best result in comparison to the above mentioned classifiers.