Summary

International Symposium on Nonlinear Theory and its Applications

2008

Session Number:A2L-B

Session:

Number:A2L-B4

Time series classification by complex network transformation

J. Zhang,  J. Sun,  X. Xu,  M. Small,  

pp.-

Publication Date:2008/9/7

Online ISSN:2188-5079

DOI:10.34385/proc.42.A2L-B4

PDF download (515.1KB)

Summary:
The nonlinear transformation from time domain to complex network domain recently introduced for pseudoperiodic time series has been shown to be a powerful tool in characterizing the complex dynamics of time series via the organization of the corresponding complex networks. In this paper, we test an extensive range of network topological statistics for time series from two archetypal systems and show that they are capable of providing a comprehensive statistical characterization of the dynamics from different aspects, and can be used to distinguish different dynamical regimes. Application of such network statistics to the human electrocardiograms reveals significant difference between the healthy individual and arrhythmia patients.