| 时间序列的相似性的分层查询 |
| |
| 引用本文： | 喻高瞻,彭宏,胡劲松,郑启伦.时间序列的相似性的分层查询[J].计算机工程与应用,2006,42(23):152-153,185. |
| |
| 作者姓名： | 喻高瞻 彭宏 胡劲松 郑启伦 |
| |
| 作者单位： | 华南理工大学计算机工程与科学系,广州,510640 |
| |
| 基金项目： | 中国科学院资助项目;国家高性能计算基金;广东省广州市科技攻关项目 |
| |
| 摘 要： | 提出了一种新的基于重要点的分段方法,将时间序列数据转换为趋势序列。在进行相似性比较时先进行趋势相似的比较,然后对结果进行欧氏距离的比较。实验结果表明该算法是有效的。
|
| 关 键 词： | 时间序列 重要点 趋势序列 模式匹配 |
| 文章编号： | 1002-8330-（2006）23-0152-02 |
| 收稿时间： | 2006-02 |
| 修稿时间： | 2006-02 |
Hierarchical Algorithm to Match Similar Time Series Data |
| |
| Yu Gaozhan,Peng Hong,Hu Jingsong,Zheng Qilun.Hierarchical Algorithm to Match Similar Time Series Data[J].Computer Engineering and Applications,2006,42(23):152-153,185. |
| |
| Authors: | Yu Gaozhan Peng Hong Hu Jingsong Zheng Qilun |
| |
| Affiliation: | Computer Science and Engineering Department,South China University of Technology,Guangzhou 510640 |
| |
| Abstract: | The paper proposes a segmentation method based on important points,bywhich time series data can be transformed into trend sequence.When we perform time series similarity searching,trend similarity may be calculated first,then the results are compared based on Euclidean distance.Experiments show that this hierarchical approach is effective. |
| |
| Keywords: | time series important points trend sequence pattern matching |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
