Characterizing time series: when Granger causality triggers complex networks
Characterizing time series: when Granger causality triggers complex networks
复制标题
表征时间序列：当格兰杰因果关系触发复杂网络时
DOI：
10.1088/1367-2630/14/8/083028
复制
发表时间：
2012-08-22
影响因子：
3.3
通讯作者：
Liu, Chong
中科院分区：
文献类型：
--
作者：
Ge, Tian;Cui, Yindong;Liu, Chong
在本文中，我们提出了一种通过结合格兰杰因果关系和复杂网络来表征时域和频域中具有噪声扰动的时间序列的新方法。我们从时间序列构建有向和加权的复杂网络，并使用代表性网络度量来描述它们的物理和拓扑特性。通过分析一些物理模型和 MIT-BIH7 人体心电图数据集的典型动态行为，我们表明所提出的方法能够捕获和表征各种动态，并且在分析长度相当短的现实世界时间序列方面具有很大潜力。
In this paper, we propose a new approach to characterize time series with noise perturbations in both the time and frequency domains by combining Granger causality and complex networks. We construct directed and weighted complex networks from time series and use representative network measures to describe their physical and topological properties. Through analyzing the typical dynamical behaviors of some physical models and the MIT-BIH7 human electrocardiogram data sets, we show that the proposed approach is able to capture and characterize various dynamics and has much potential for analyzing real-world time series of rather short length.