| 基于哈达玛变换的多元时间序列聚类研究 |
| |
| 引用本文： | 韩娜,滕少华,房小兆. 基于哈达玛变换的多元时间序列聚类研究[J]. 计算机工程与设计, 2012, 33(3): 983-986,1021 |
| |
| 作者姓名： | 韩娜 滕少华 房小兆 |
| |
| 作者单位： | 广东工业大学计算机学院,广东广州,510006 |
| |
| 基金项目： | 广东省自然科学基金项目(9151009001000007、9451009001002777);广东省科技计划基金项目(2008A060201011);广州市越秀区科技计划基金项目(2007-GX-075) |
| |
| 摘 要： | 对当前聚类算法进行研究的基础上,提出了有效地实现多元时间序列聚类的方法.用离散哈达玛变换对多元数据进行降维,求出多元变量相关系数矩阵的特征值作为权值.采用带权值的矩阵相似性度量方法,利用改进的K-means算法对多元时间序列进行聚类分析.实验结果表明,该方法能够有效地实现多元时间序列聚类,把具有相似趋势变化的多元时间序列对象划分到同一类中.
|
| 关 键 词： | 多元时间序列 离散哈达玛变换 降维 矩阵相似性度量 聚类 |
Multivariate time series clustering research based on Hadamard transform |
| |
| HAN Na , TENG Shao-hua , FANG Xiao-zhao. Multivariate time series clustering research based on Hadamard transform[J]. Computer Engineering and Design, 2012, 33(3): 983-986,1021 |
| |
| Authors: | HAN Na TENG Shao-hua FANG Xiao-zhao |
| |
| Affiliation: | (College of Computer,Guangdong University of Technology,Guangzhou 510006,China) |
| |
| Abstract: | A effective clustering method is presented based on researching the present clustering algorithm.Firstly,a multivariate time sequence is reduced-order by discrete Hadamard transform.Then,the eigenvalue of multiple variables related coefficient matrix are the weights of multiple time series transformation matrix.Finally,Using the matrix similarity measure with weights,improved K-means algorithm is used to cluster the multivariate time series.Experimental results show this method can achieve multivariate time series clustering effectively. |
| |
| Keywords: | multivariate time series discrete Hadamard transform reduced-order matrix similarity clustering |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
