An Effective IDS for MANET using Forward Feature Selection and Classification algorithms

The security plays an important role in current technology with the threat detection and prevention for networks which are challenging problems. The Intrusion Detection System (IDS) is considered as the first line of defense for security in MANET. The existing techniques are not effective to improve the detection accuracy and to reduce false alarm rate. Therefore, it is essential to develop new techniques for intrusion detection because of the application of MANET. In this paper, an efficient Forward Feature Selection (FFS) algorithms and Enhanced Decision Tree Support Vector Machine (EDTSVM) classifier which uses experiments on KDD '99 cup data set and addresses. Our proposed method results in detecting intrusion when tested over the existing methodologies. (c) 2012 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of Noorul Islam Centre for Higher Education