Skip to Main Content
In recent years, intrusion detection has emerged as an important technique for network security. Machine learning techniques have been applied to the field of intrusion detection. They can learn normal and anomalous patterns from training data and via Feature selection improving classification by searching for the subset of features which best classifies the training data to detect attacks on computer system. The quality of features directly affects the performance of classification. Many feature selection methods introduced to remove redundant and irrelevant features, because raw features may reduce accuracy or robustness of classification. In this paper we compared three methods for feature selection based on Decision trees (DT), Flexible Neural Tree (FNT) and Particle Swarm Optimization (PSO). The results based on comparison of three methods on DARPA KDD99 benchmark dataset indicate that DT has almost better accuracy.