KFDA and clustering based multiclass SVM for intrusion detection

To improve the classification accuracy and reducethe training time, an intrusion detection technology is proposed,which combines feature extraction technology and multiclasssupport vector machine (SVM) classification algorithm. Theintrusion detection model setup has two phases. The first phaseis to project the original training data into kernel fisherdiscriminant analysis (KFDA) space. The second phase is to usefuzzy clustering technology to cluster the projected data andconstruct the decision tree, based on the clustering results. Theoverall detection model is set up based on the decision tree.Results of the experiment using knowledge discovery and datamining (KDD) from 99 datasets demonstrate that the proposedtechnology can be an an effective way for intrusion detection.