论文信息 - Correntropy based Granger causality

Correntropy based Granger causality

We propose a novel nonlinear extension to Granger causality. It is derived from a nonlinear mapping of a stochastic process using the recently introduced generalized correlation measure called correntropy. The method is demonstrated by detecting the direction of coupling in a chaotic system where the original Granger causality failed.

José Carlos Príncipe | Il Park

[1] K. Hlavácková-Schindler,et al. Causality detection based on information-theoretic approaches in time series analysis , 2007 .

[2] Jian-Wu Xu,et al. Nonlinear Signal Processing Based on Reproducing Kernel Hilbert Space , 2010 .

[3] E. Parzen. Time Series Analysis Papers , 1967 .

[4] Deniz Erdogmus,et al. A Closed Form Solution for a Nonlinear Wiener Filter , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[5] Nicola Ancona,et al. An Invariance Property of Predictors in Kernel-Induced Hypothesis Spaces , 2006, Neural Computation.

[6] S. Haykin,et al. Adaptive Filter Theory , 1986 .

[7] José Carlos Príncipe,et al. Generalized correlation function: definition, properties, and application to blind equalization , 2006, IEEE Transactions on Signal Processing.

[8] G. Rangarajan,et al. Multiple Nonlinear Time Series with Extended Granger Causality , 2004 .