Learn R Programming

crqa (version 2.0.6)

crqa-package: Unidimensional and Multidimensional Methods for Recurrence Quantification Analysis

Description

Auto, Cross and Multi-dimensional recurrence quantification analysis. Different methods for computing recurrence, cross vs. multidimensional or profile iti.e., only looking at the diagonal recurrent points, as well as functions for optimization and plotting are proposed. in-depth measures of the whole cross-recurrence plot, Please refer to by Coco and Dale (2014) <doi:10.3389/fpsyg.2014.00510> and Wallot (2018) <doi: 10.1080/00273171.2018.1512846> for further details about the method.

Arguments

Author

Moreno I. Coco moreno.cocoi@gmail.com Dan Monster danm@econ.au.dk Giuseppe Leonardi g.leonardi@vizja.pl Rick Dale rdale@ucla.edu Sebastian Wallot sebastian.wallot@ae.mpg.de

Details

crqa: Core recurrence function, which examines recurrent structures of a single rqa, two crqa, or multidimensional time-series mdcrqa, which are time-delayed and embedded in higher dimensional space. The approach compares the phase space trajectories of the time-series in the same phase-space when delays are introduced. A distance matrix between the time-series, delayed and embedded is calculated. Several measures representative of the underlying dynamics of the system are extracted.

drpfromts: Method to explore the diagonal profile of the recurrence plot (Auto, Cross, or Multi-dimensional). It returns the recurrence for different delays, the maximal recurrence observed and the delay at which it occurred.

lorenzattractor: An implementation of the Lorenz dynamical system, which describes the motion of a possible particle, which will neither converge to a steady state, nor diverge to infinity; but rather stay in a bounded but 'chaotically' defined region, i.e., an attractor.

mdDelay:Estimates time delay for embedding of a multi-dimensional dataset.

mdFnn: Computes the percentage of false nearest neighbors for multidimensional time series as a function of embedding dimension.

optimizeParam: Iterative procedure to examine the values of delay, embedding dimension and radius to compute recurrence plots of one, two, or more time-series.

piecewiseRQA: This is a convenience function which breaks down the computation of large recurrence plots into a collection of smaller recurrence plots. It can ease speed and memory issues if an appropriate size for the block is found.

plotRP: A convenience function to plot the RP matrix returned by the crqa.

simts: A simple algorithm for producing a time-series that drives a second time-series using parameters, which change independent and conditional probability of an event to occur.

wincrqa: A recurrence plot is computed in overlapping windows of a certain size for a number of delays smaller than the size of the window; and measures of it extracted.

windowdrp: A recurrence plot is computed in overlapping windows of a specified size for a number of delays smaller than the size of the window. In every window, the recurrence value for the different delays is calculated. A mean is then taken across the delays to obtain a recurrence value in that particular window.

References

Webber Jr, C. L., and Zbilut, J. P. (2005). Recurrence quantification analysis of nonlinear dynamical systems. Tutorials in contemporary nonlinear methods for the behavioral sciences, 26-94.

Marwan, N., and Kurths, J. Nonlinear analysis of bivariate data with cross recurrence plots. Physics Letters A 302.5 (2002): 299-307.

Coco, M. I., Monster, D., Leonardi, G., Dale, R., & Wallot, S. (2021). Unidimensional and Multidimensional Methods for Recurrence Quantification Analysis with crqa. R Journal, 13(1).

Examples

Run this code

# use the available data
data(crqa) 

listener = eyemovement$listener
narrator = eyemovement$narrator

delay = 1; embed = 1; rescale = 0; radius = .1;
normalize = 0; mindiagline = 2; minvertline = 2;
tw = 0; whiteline = FALSE; recpt = FALSE; side = "both"
method = 'crqa'; metric = 'euclidean';  
datatype = "categorical"

ans = crqa(narrator, listener, delay, embed, rescale, radius, normalize, 
           mindiagline, minvertline, tw, whiteline, recpt, side, method, metric, 
           datatype)

print(ans[1:10]) ## last argument of list is the recurrence plot


Run the code above in your browser using DataLab