首页> 外文会议>International conference on computer and network technology >A New Mining Method of Moving Sequential Pattern using Pseudo-Bitmap Representation
【24h】

A New Mining Method of Moving Sequential Pattern using Pseudo-Bitmap Representation

机译:一种使用伪位图表示的连续序列模式挖掘新方法

获取原文

摘要

Sequential pattern mining plays a more and more important role in data mining research area. With rapid growth of wireless networks and mobile applications, a special sequential pattern called moving sequential pattern has attracted many researchers' attention. Moving sequential pattern mining can be viewed as a conventional sequential pattern mining with some constrains |1|, which is significant for effective and efficient mobile user location and reduction of mobile user paging cost in wireless environment |2, 5|. In this paper, a new effective approach for getting moving sequential patterns is introduced, which has inherent characteristics of a mobile sequential pattern. In order to get more efficient results, a new data structure named pseudo bitmap is proposed. Finally, an efficient algorithm called MSP is presented to mine the moving sequences. A thorough experimental comparison shows that our algorithm outperforms Revised PrefixSpan which is revised to mine moving sequential patterns, in mining large moving sequences databases.
机译:顺序模式挖掘在数据挖掘研究领域中起着越来越重要的作用。随着无线网络和移动应用程序的快速发展,一种称为移动顺序模式的特殊顺序模式引起了许多研究人员的关注。移动顺序模式挖掘可以看作是具有一些约束| 1 |的常规顺序模式挖掘,这对于有效和高效地移动用户定位以及降低无线环境| 2,5 |中的移动用户寻呼成本具有重要意义。本文介绍了一种获得移动顺序模式的新有效方法,该方法具有移动顺序模式的固有特性。为了获得更有效的结果,提出了一种新的数据结构,称为伪位图。最后,提出了一种称为MSP的有效算法来挖掘运动序列。彻底的实验比较表明,在挖掘大型移动序列数据库中,我们的算法优于修订后的PrefixSpan,该修订版可对移动序列模式进行挖掘。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号