Network Anomaly Detection with TSK Fuzzy Inference System

In order to improve the detection rate for anomaly state and reduce the false positive rate for normal state in the network anomaly detection, a novel method of network anomaly detection based on TSK Fuzzy inference system(TSK-FIS) was proposed.The TSK-FIS was trained by the algorithm which is based on gradient descent(GD).The model makes full use of local accurate searching of GD.The well-known KDD Cup 1999 Intrusion Detection Data Set was used as the experimental data.Experimental result on KDD 99 intrusion detection datasets shows that this learning algorithm has better global convergence ability and the accuracy of anomaly detection is enhanced.