A Novel Intrusion Detection Method Based on Adaptive Resonance Theory and Principal Component Analysis
Junbi Xiao, Hao Song · 2009
A novel intrusion detection approach based on Adaptive Resonance Theory (ART) and Principal Component Analysis (PCA) is put forward according to analyzing now intrusion detection methods. In this model (PCA-MART2), it defines network behaviors relied upon the datagram. PCA is applied to feature selection about input samples and the multi-layered ART2 is designed to subdivide the imprecise clustering. The modified algorithm improved the speed and accuracy of detection. The experimental results show that the intrusion detection system based on PCA-MART2 can detect intrusion behavior in network efficiently.