|
|||||
|
|
| 基于语义相似的水文时间序列相似性挖掘——以太湖流域大浦口站水位数据为例 | |
| 引用本文： | 朱跃龙,王咏梅,万定生,李薇,梅青,余达征.基于语义相似的水文时间序列相似性挖掘——以太湖流域大浦口站水位数据为例[J].水文,2011,31(1):35-40. |
| 作者姓名： | 朱跃龙 王咏梅 万定生 李薇 梅青 余达征 |
| 作者单位： | 1. 河海大学计算机及信息工程学院,江苏,南京,210098 2. 水利部水文局,北京,100053 3. 水利部太湖流域管理局,上海,200434 |
| 基金项目： | 国家自然科学基金项目(51079040); 水利部948项目(201016); “十一五”国家科技支撑计划重大项目(2006BAB04A13) |
| 摘 要： | 利用数据挖掘技术从长期观测的数据序列中发现蕴藏的规律是当前研究热点之一。相似性挖掘是时间序列挖掘的基础,提出一种基于语义相似的水文时间序列相似性查询方法。首先利用小波变换将时间序列进行平滑处理,在此基础上进行极值点分段并符号化,每个符号代表一种语义模式,从而选取语义相似的子序列作为候选集,再将候选集中子序列通过动态时间弯曲距离进行精确匹配从而得到相似子序列(以太湖流域大浦口站水位数据为例),实验证明,该方法能够在大幅度降低时间复杂度的基础上较准确地查找出相似子序列。 |
| 关 键 词： | 水文时间序列 数据挖掘 语义相似 动态时间弯曲距离 小波变换 |
Similarity Mining of Hydrological Time Series Based on Semantic Similarity Measures |
|
| ZHU Yuelong,WANG Yongmei,WAN Dingsheng,LI Wei,MEI Qing,YU Dazheng.Similarity Mining of Hydrological Time Series Based on Semantic Similarity Measures[J].Hydrology,2011,31(1):35-40. | |
| Authors: | ZHU Yuelong WANG Yongmei WAN Dingsheng LI Wei MEI Qing YU Dazheng |
| Institution: | ZHU Yuelong1 WANG Yongmei1,WAN Dingsheng1,LI Wei2,MEI Qing3,YU Dazheng2(1. School of Computer & Information Engineering,Hohai University,Nanjing 210098,China,2. Bureau of Hydrology,MWR,Beijing 100053,3. Taihu Basin Authority,Shanghai 200434,China) |
| Abstract: | It is now one of the hot spots in scientific research to use data mining technology over long-term observations of time-series to find the regular pattern. Similarity mining is the basis for other tasks of time series data mining. This paper proposed a semantic similarity-based similarity search method over hydrological time-series data. Firstly, wavelet transform was employed to smooth the time-series data; then the extreme points were extracted and the segments were symbolized, each of which represents a ... |
| Keywords: | hydrological time series data mining semantic similarity dynamic time warping(DTW) wavelet transform |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |