Please use this identifier to cite or link to this item:
Files in This Item:
File SizeFormat 
Ge et al 2012, Characterizing time series.pdf1.01 MBAdobe PDFView/Open
Title: Characterizing time series: When Granger causality triggers complex networks
Authors: Ge, T.Cui, Y.Lin, W.Kurths, J.Liu, C.
Publishers Version:
Issue Date: 2012
Published in: New Journal of Physics Vol. 14 (2012)
Publisher: Bristol : Institute of Physics Publishing
Abstract: 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-BIH 7 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.
Keywords: Complex networks; Data sets; Dynamical behaviors; Granger Causality; Network measures; Noise perturbation; Physical model; Time and frequency domains; Topological properties; Weighted complex networks; Models; Topology; Time series
DDC: 530
License: CC BY-NC-SA 3.0 Unported
Link to License:
Appears in Collections:Physik

This item is licensed under a Creative Commons License Creative Commons