Introduction - If you have any usage issues, please Google them yourself
The problem of intrusion detection has been studied and received a lot of attention in
machine learning and data mining in the literature survey. The existing techniques are not
effective to improve the classification accuracy and to reduce high false alarm rate.
Therefore, it is necessary to propose new technique for IDS. In this work, we propose a
new K-means clustering method with a different Preprocessing and Genetic Algorithm
for identifying intrusion and classification for both anomaly and misuse.
The experiments of the proposed IDS are performed with KDD cup’99 data set. The
experiments will clearly results the proposed method provides better classification
accuracy over existing method.