International Journal of Applied Information Systems |
Foundation of Computer Science (FCS), NY, USA |
Volume 3 - Number 6 |
Year of Publication: 2012 |
Authors: S. Vijayasankari, K. Ramar |
10.5120/ijais12-450550 |
S. Vijayasankari, K. Ramar . Common Hybrid Feature Selection for Modeling Intrusion Detection System and Cyber Attack Detection System. International Journal of Applied Information Systems. 3, 6 ( July 2012), 16-22. DOI=10.5120/ijais12-450550
Intrusion Detection Systems (IDS) and Cyber Attack Detection System (CADS) have to be provided in a Generalised Discriminant Analysis Algorithm. It is an important approach to nonlinear features and extensively used tool for ensuring network security. Complex relationships exist between the features, which are difficult for humans to discover. The conventional Linear Discriminant Analysis feature reduction technique is not suitable for nonlinear data set. Artificial Neural Network and C4. 5 classifiers to result in supervisory algorithm are used. If real-time detection is desired IDS must reduce the amount of data to be processed. Currently IDS examine all data features to detect intrusion or misuse patterns. Some of the features may be redundant or contribute little to the detection process. The purpose of this research work is to identify important input features in building IDS that is computationally efficient and effective. The performance of two feature selection algorithms involving Bayesian Networks (BN) and Classification and Regression Trees (CART) and an ensemble of BN and CART were investigated. Empirical results indicate that significant input feature selection is important to design IDS with efficient, effective and lightweight for real world detection systems. Finally, hybrid architecture for combining different feature selection algorithms for real world intrusion detection was proposed.