• Dr. M.Manimekalai
• G. Anupriya

Intrusion detection systems (IDS) in MANET have to system blocks of packets with many features, which suspend the detecting of anomalies. Sampling and Feature Selection may be employed to depreciate computing time and hence diminishing the time of intrusion detection. A Novel Hybrid Feature Selection method mounts on Particle Swarm Optimization (PSO) and Information Gain analysis. The execution of the proposed Hybrid Feature Selection Method on KDD CUP dataset to decrease the volume of primary features and accurate by implementing better detection performance in the classification methods relating with other feature selectors. The relevant features and removing redundant features of KDD CUP dataset is Optimal Dataset. ANN with Multi-Layered Perceptron classification method was used to classify the nodes of MANET.

Intrusion Detection System, Mobile Ad Hoc Network, Data Mining Technique, Artificial Neural Network, Naïve Bayes classification.

"A Novel Intrusion Detection System using Data Mining Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.58-62, June 2019, Available :http://www.jetir.org/papers/JETIRDB06009.pdf

"A Novel Intrusion Detection System using Data Mining Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp58-62, June 2019, Available at : http://www.jetir.org/papers/JETIRDB06009.pdf