• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies >Mining constrained inter-sequence patterns: a novel approach to cope with item constraints
【24h】

Mining constrained inter-sequence patterns: a novel approach to cope with item constraints

机译：挖掘约束序列间模式：一种应对项目限制的新方法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Data mining has become increasingly important in the Internet era. The problem of mining inter-sequence pattern is a sub-task in data mining with several algorithms in the recent years. However, these algorithms only focus on the transitional problem of mining frequent inter-sequence patterns and most frequent inter-sequence patterns are either redundant or insignificant. As such, it can confuse end users during decision-making and can require too much system resources. This led to the problem of mining inter-sequence patterns with item constraints, which addressed the problem when end-users only concerned the patterns contained a number of specific items. In this paper, we propose two novel algorithms for it. First is the ISP-IC (Inter-Sequence Pattern with Item Constraint mining) algorithm based on a theorem that quickly determines whether an inter-sequence pattern satisfies the constraints. Then, we propose a way to improve the strategy of ISP-IC, which is then applied to the i $i$ ISP-IC algorithm to enhance the performance of the process. Finally, pi ISP-IC, a parallel version of i $i$ ISP-IC, will be presented. Experimental results show that pi ISP-IC algorithm outperforms the post-processing of the-state-of-the-art method for mining inter-sequence patterns (EISP-Miner), ISP-IC, and i $i$ ISP-IC algorithms in most of the cases.
机译：数据挖掘在互联网时代变得越来越重要。挖掘序列间模式的问题是近年来具有多种算法的数据挖掘的子任务。然而，这些算法仅关注挖掘频繁序列间模式的过渡问题，并且大多数频繁的序列模式是冗余或微不足道的。因此，它可以在决策期间混淆最终用户，并且可能需要过多的系统资源。这导致挖掘序列间模式与项目约束的问题，这解决了问题时，当最终用户仅涉及模式包含许多特定项目。在本文中，我们提出了两种新颖的算法。首先是基于快速确定序列间模式是否满足约束的定理的isp-ic（序列间模式）算法。然后，我们提出了一种改进ISP-IC策略的方法，然后将其应用于I $ ISP-IC算法，以增强过程的性能。最后，将提出PI ISP-IC，我是I $ ISP-IC的并行版本。实验结果表明，PI ISP-IC算法优于挖掘序列间模式（EISP-MINER），ISP-IC和I $ ISP-IC算法的最先进方法的后处理在大多数情况下。

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