Summary
International Symposium on Nonlinear Theory and Its Applications
2016
Session Number:A2L-C
Session:
Number:A2L-C-1
Detecting Directional Couplings from Time Series: Joint Distribution of Distances
Yoshito Hirata, Jose Amigo, Kazuyuki Aihara,
pp.-
Publication Date:2016/11/27
Online ISSN:2188-5079
DOI:10.34385/proc.48.A2L-C-1
PDF download (199KB)
Summary:
When we investigate the dynamics underlying a complex system where we can observe time series of several different components, we want to identify directional couplings between each pair of those components. In such a circumstance, we should not want to assume that the dynamics is linear or that all the components can be observed. Thus, here we propose a method for identifying directional couplings based on a joint distribution of distances. The proposed method will be easily extended to the analysis of point processes.