摘要：The Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) has a disadvantage that it reduced the accuracy of the arbitrary shape clustering algorithm clusters, to this end a split improved BIRCH algorithm (AS-Birch) was put forward. Through the analysis of the reconfigurable network and a detailed analysis of application scenarios and functional requirements of business clustering, according to the different characteristics of each clustering algorithm, we choose a hierarchical clustering algorithm BIRCH as a business solution to the clustering programs. On the basis of the drawbacks in BIRCH algorithm, we designed split improved BIRCH algorithm and the specific steps of the algorithm is given. Finally, Advanced Split BIRCH algorithm was applied to a detailed experimental simulation experiments show in reconfigurable network. The experiment suggests: AS-BIRCH algorithm has a greater improvement in terms of packet loss rate, delay and jitter than BIRCH algorithm, especially when dealing with irregular shape cluster, AS-BIRCH algorithm greatly improved the accuracy rate concerning to the business clustering.
关键词：Multidimensional Cognitive Synergy;Clustering Algorithm;Intrusion Detection;Artificial Data Sets
