期刊名称：International Journal of Engineering and Computer Science
印刷版ISSN：2319-7242
出版年度：2014
卷号：3
期号：2
页码：3873-3876
出版社：IJECS
摘要：During the last decade the analysis of intrusion detection has become very significant, the researcher focuses on various dataset toimprove system accuracy and to reduce false positive rate based on DAPRA 98 and later the updated version as KDD cup 99 dataset whichshows some statistical issues, it degrades the evaluation of anomaly detection that affects the performance of the security analysis which leads tothe replacement of KDD cup 99 to NSL-KDD dataset. This paper focus on detailed analysis on NSL- KDD dataset and proposed a newtechnique of combining swarm intelligence (Simplified Swarm Optimization) and data mining algorithm (Random Forest) for feature selectionand reduction. SSO is used to find more appropriate set of attributes for classifying network intrusions, and Random Forest is used as aclassifier. In the preprocessing step, we optimize the dimension of the dataset by the proposed SSO-RF approach and finds an optimal set offeatures. SSO is an optimization method that has a strong global search capability and is used here for dimension optimization. Theexperimental results shows that the proposed approach performs better than the other approaches for the detection of all kinds of attackspresent in the dataset
关键词：NSL-KDD; Simplified Swarm Optimization; PSO; Random Forest
