Distributed Web usage clustering based on multi-mirror image sites

The general algorithms of local Web usage clustering (LUC) and global Web usage clustering (GUC) in a distributed data mining system based on multi-mirror sites were proposed, which better solved the troubles made by distributed Web access information and communication number. Java language was used to implement the algorithms and its performance was studied. The results showed that the algorithms were valid and could be effectively and accurately identified by Web user group patterns.