Distributed Web usage clustering based on multi-mirror image sites
-
摘要: 提出了一種適用于多鏡像站點環境下的分布式Web使用聚類局部挖掘算法LUC和全局挖掘算法GUC,較好地解決了Web訪問信息的異地存儲、分布式算法通訊量等因素給模式分析過程帶來的困難.將給出的算法用Java語言加以實現,并對算法性能進行了研究.結果證明,該算法是有效的,可以用來高效、準確地在多鏡像站點環境下發現Web用戶群體模式.Abstract: 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.
-
Key words:
- mirror image sites /
- Web /
- clustering /
- user transactions clustering /
- distributed data mining
-
點擊查看大圖
計量
- 文章訪問數: 161
- HTML全文瀏覽量: 27
- PDF下載量: 6
- 被引次數: 0
下載:
