大型时态数据库中的Burst模式挖掘  

Mining Burst patterns in large temporal database

作　　者：曾德胜[1] 张师超[2] 王日凤[2] 谢冲[2] 

机构地区：[1]广东罗定职业技术学院电子工程系,广东罗定527200 [2]广西师范大学计算机系

出　　处：《计算机应用》2006年第10期2413-2416,2420,共5页journal of Computer Applications

基　　金：国家自然科学基金资助项目(60463003);澳大利亚ARC项目(DP0559536;DP0667060)

摘　　要：首先分析了挖掘整个大型时态数据库时可能存在的两个问题,提出了解决的一种新方法。该方法采用“先分后合”的思想:先将大型数据库划分成多个小型数据集,接着对这些数据集进行四次裁剪后再进行综合评价,最后挖掘出潜在的Burst模式。实验结果表明,该方法准确有效。挖掘出的Burst模式给公司决策者在制定决策的时候提供参考帮助和支持。How to effectively discover potentially useful knowledge from large databases is an important yet challenging issue. The paper firstly pointed out there would be two problems in mining very large temporal databases with experimental results, and then proposed a new method to solve the two problems. This approach first partitioned a database into several small datasets. And then the Burst patterns were dug up after four times pruning on the data. The experimental results show that the proposed method is accurate and efficient, and the Burst patterns are useful for decision-making in business.

关 键 词：数据挖掘 Burst模式 时态数据库 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]