《计算机应用研究》|Application Research of Computers

基于符号化的时间序列复杂网络构造及其拓扑结构研究

Research on building complex network based on symbolization of time series and its topological properties

免费全文下载 (已被下载 次)  
获取PDF全文
作者 袁铭
机构 天津财经大学 理工学院,天津 300222
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2015)04-1044-04
DOI 10.3969/j.issn.1001-3695.2015.04.020
摘要 复杂网络理论是时间序列分析中一种有力的工具,但在面对高频数据时,现有建网方法是低效的。因此,提出利用时间序列符号化技术压缩原始序列,并构造网络的方法。该方法使用最小二乘估计时序分段斜率,提取序列的局部特征,并构造字典判断节点是否邻接。模拟实验表明,所建网络的标度指数、集群系数与过程的Hurst指数高度相关,可以精确地捕捉原过程的复杂性特征。
关键词 复杂网络;时间序列符号化;Hurst指数;网络拓扑结构
基金项目 国家自然科学基金青年基金项目(71103126)
天津市社科规划项目(TJTJ13-002)
本文URL http://www.arocmag.com/article/01-2015-04-020.html
英文标题 Research on building complex network based on symbolization of time series and its topological properties
作者英文名 YUAN Ming
机构英文名 School of Technology, Tianjin University of Finance & Economic, Tianjin 300222, China
英文摘要 Complex network theories may be a powerful tool in time series analysis. But when facing high frequency data, current method of building network is highly inefficient. Thus, this paper proposed a symbolic method for time series compression and built network. This method used least square to estimate the slope of each segments and then extracted local features from time series. Then it determined node’s adjacency through a dictionary. Simulation studies show the scaling exponent, cluster coefficient of the network are highly correlated with Hurst exponent and can exactly capture complex properties of original series.
英文关键词 complex network; time series symbolization; Hurst exponent; network topology
参考文献 查看稿件参考文献
  [1] WATTS D J, STROGATZ S H. Collective dynamics of “small-world” networks[J] . Nature, 1998, 393(6684):440-442.
[2] BARABSI A L, ALBERT R. Emergence of scaling in random networks[J] . Science, 1999, 286(5439):508-512.
[3] BONANNO G, CALDARELLI G, LILLO F, et al. Networks of equities in financial markets[J] . European Physical Journal B, 2004, 38(2):363-371.
[4] ZHANG J, SMALL M. Complex network from pseudoperiodic time series:topology versus dynamics[J] . Physical Review Letters, 2006, 96(23):238701.
[5] TANG Jin-yun, WANG Yin-hai, LIU Fang. Characterizing traffic time series based on complex network theory[J] . Physica A:Statistical Mechanics and its Applications, 2013, 392(18):4192-4201.
[6] AN Hai-zhong, GAO Xiang-yun, FANG Wei, et al. The role of fluctuating modes of autocorrelation in crude oil prices[J] . Physica A:Statistical Mechanics and its Applications, 2014, 393(C):382-390.
[7] GAO Zhong-ke, JIN Ning-de. Characterization of chaotic dynamic behavior in the gas-liquid slug flow using directed weighted complex network analysis[J] . Physica A:Statistical Mechanics and its Applications, 2012, 391(10):3005-3016.
[8] WANG Na, LI Dong, WANG Qi-wen. Visibility graph analysis on quarterly macroeconomic series of China based on complex network theory[J] . Physica A:Statistical Mechanics and its Applications, 2012, 391(24):6543-6555.
[9] YANG Yue, YANG Hui-jie. Complex network-based time series ana-lysis[J] . Physica A:Statistical Mechanics and its Applications, 2008, 387(5-6):1381-1386.
[10] KARIMI S, DAROONEH A H. Measuring persistence in a stationary time series using the complex network theory[J] . Physica A:Statistical Mechanics and its Applications, 2013, 392(1):287-293.
[11] LIN J, KEOGHE, LONARDIS, et al. A symbolic representation of time series, with implications for streaming algorithms[C] //Proc of the 8th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery. New York:ACM Press, 2003:2-11.
[12] 谭宏强, 牛强. 基于滑动窗口及局部特征的时间序列符号化方法[J] . 计算机应用研究, 2013, 30(3):796-798.
[13] 何大韧, 刘宗华, 汪秉宏. 复杂系统与复杂网络[M] . 北京:高等教育出版社, 2009.
收稿日期 2014/3/3
修回日期 2014/4/8
页码 1044-1047
中图分类号 TPP393;TP301.5
文献标志码 A