Abstract: Aimed at the lack of global search capability of K-means algorithm, optimized K-means clustering algorithm based on artificial fish swarm(AFS-KM)was presented in this paper,which can overcome the problem of initial clustering center selection sensitivity of K-means and can obtain global optimized clustering partition. During clutering process, a weighted distance computation method based on information gain attribute weighting is used, so, the better clustering can be obtained for both spherical data and ellipsodal data. Simulation experiment is implemented over data set KDD-99, and the result shows that the satisfying detection rate and false acceptance rate can be obtained in network instraction detection.

Key words: Clustering, Artificial fish swarm, Information gain, Attribute weighting, Intrusion detection