Telecommunications Science ›› 2013, Vol. 29 ›› Issue (2): 51-57.doi: 10.3969/j.issn.1000-0801.2013.02.009

• research and development • Previous Articles     Next Articles

Internet Hosts Grouping Algorithm Based on Clustering and Bayesian Classifier and Evaluation Model

Jianhong Zhai1,Wei Li1,Ruihai Ge1,Ru Yang2   

  1. 1 Research Center of Computer Network and Information Security Technology,Harbin Institute of Technology,Harbin 150001,China
    2 Department of Computer Science and Technology,Heilongjiang Institute of Technology,Harbin 150001,China
  • Online:2013-02-15 Published:2017-02-22

Abstract:

The multi-group network application is one of the popular network service models,internet hosts grouping method and the evaluation mode1 were focused on. A new internet hosts grouping algorithm ca11ed Clustyes was presented. Also,based on the concept of group coupling degree,an evaluation mode1 of hosts grouping performance was constructed. RTT,hops,and packet 1oss rate in network communication were considered in this evaluation mode1. The experiment was simulated on the NS-3,and the results show that the new grouping algorithm Clustyes can generate groups,in which the hosts can communicate quickly,stably,and closely in physica1 distance.

Key words: grouping evaluation mode1, group coupling degree, cluster analysis, Bayesian classifier

No Suggested Reading articles found!