CalculateCorrDim {RHRV}

Correlation sum, correlation dimension and generalized correlation dimension (order q >1)

Description

Functions for estimating the correlation sum and the correlation dimension of the RR time series using phase-space reconstruction

Usage

CalculateCorrDim(HRVData,
  indexNonLinearAnalysis = length(HRVData$NonLinearAnalysis),
  minEmbeddingDim = NULL, maxEmbeddingDim = NULL, timeLag = NULL,
  minRadius, maxRadius, pointsRadius = 20, theilerWindow = 100,
  corrOrder = 2, doPlot = TRUE)

EstimateCorrDim(HRVData,
  indexNonLinearAnalysis = length(HRVData$NonLinearAnalysis),
  regressionRange = NULL, useEmbeddings = NULL, doPlot = TRUE)

PlotCorrDim(HRVData,
  indexNonLinearAnalysis = length(HRVData$NonLinearAnalysis), ...)

Arguments

HRVData

Data structure that stores the beats register and information related to it

indexNonLinearAnalysis

Reference to the data structure that will contain the nonlinear analysis

minEmbeddingDim

Integer denoting the minimum dimension in which we shall embed the time series

maxEmbeddingDim

Integer denoting the maximum dimension in which we shall embed the time series. Thus, we shall estimate the correlation dimension between minEmbeddingDim and maxEmbeddingDim.

timeLag

Integer denoting the number of time steps that will be use to construct the Takens' vectors.

minRadius

Minimum distance used to compute the correlation sum C(r)

maxRadius

Maximum distance used to compute the correlation sum C(r)

pointsRadius

The number of different radius where we shall estimate C(r). Thus, we will estimate C(r) in pointsRadius between minRadius and maxRadius

theilerWindow

Integer denoting the Theiler window: Two Takens' vectors must be separated by more than theilerWindow time steps in order to be considered neighbours. By using a Theiler window, we exclude temporally correlated vectors from our estimations.

corrOrder

Order of the generalized correlation Dimension q. It must be greater than 1 (corrOrder>1). Default, corrOrder=2

doPlot

Logical value. If TRUE (default), a plot of the correlation sum is shown

regressionRange

Vector with 2 components denoting the range where the function will perform linear regression

useEmbeddings

A numeric vector specifying which embedding dimensions should the algorithm use to compute the correlation dimension

...

Additional plot parameters.

Details

The correlation dimension is the most common measure of the fractal dimensionality of a geometrical object embedded in a phase space. In order to estimate the correlation dimension, the correlation sum is defined over the points from the phase space:

C(r) = \{(number\;of\;points\;(x_i,x_j)\;verifying\;that\;distance\;(x_i,x_j)<r\})/N^2

However, this estimator is biased when the pairs in the sum are not statistically independent. For example, Taken's vectors that are close in time, are usually close in the phase space due to the non-zero autocorrelation of the original time series. This is solved by using the so-called Theiler window: two Takens' vectors must be separated by, at least, the time steps specified with this window in order to be considered neighbours. By using a Theiler window, we exclude temporally correlated vectors from our estimations.

The correlation dimension is estimated using the slope obtained by performing a linear regression of \log10(C(r))\;Vs.\;\log10(r). Since this dimension is supposed to be an invariant of the system, it should not depend on the dimension of the Taken's vectors used to estimate it. Thus, the user should plot \log10(C(r))\;Vs.\;\log10(r) for several embedding dimensions when looking for the correlation dimension and, if for some range \log10(C(r)) shows a similar linear behaviour in different embedding dimensions (i.e. parallel slopes), these slopes are an estimate of the correlation dimension. The estimate routine allows the user to get always an estimate of the correlation dimension, but the user must check that there is a linear region in the correlation sum over different dimensions. If such a region does not exist, the estimation should be discarded.

Note that the correlation sum C(r) may be interpreted as: C(r) = <p(r)>, that is: the mean probability of finding a neighbour in a ball of radius r surrounding a point in the phase space. Thus, it is possible to define a generalization of the correlation dimension by writing:

C_q(r) = <p(r)^{(q-1)}>

Note that the correlation sum

C(r) = C_2(r)

It is possible to determine generalized dimensions Dq using the slope obtained by performing a linear regression of log10(Cq(r))\;Vs.\;(q-1)log10(r). The case q=1 leads to the information dimension, that is treated separately in this package. The considerations discussed for the correlation dimension estimate are also valid for these generalized dimensions.

Value

The CalculateCorrDim returns the HRVData structure containing a corrDim object storing the results of the correlation sum (see corrDim) of the RR time series.

The EstimateCorrDim function estimates the correlation dimension of the RR time series by averaging the slopes of the embedding dimensions specified in the useEmbeddings parameter. The slopes are determined by performing a linear regression over the radius' range specified in regressionRange.If doPlot is TRUE, a graphic of the regression over the data is shown. The results are returned into the HRVData structure, under the NonLinearAnalysis list.

PlotCorrDim shows two graphics of the correlation integral: a log-log plot of the correlation sum Vs the radius and the local slopes of log10(C(r))\;Vs\;log10(C(r)).

Note

This function is based on the timeLag function from the nonlinearTseries package.

In order to run EstimateCorrDim, it is necessary to have performed the correlation sum before with ComputeCorrDim.

References

H. Kantz and T. Schreiber: Nonlinear Time series Analysis (Cambridge university press)

See Also

corrDim.

Examples

## Not run: 
 # ...
 hrv.data = CreateNonLinearAnalysis(hrv.data)
 hrv.data = CalculateCorrDim(hrv.data,indexNonLinearAnalysis=1, 
             minEmbeddingDim=2, maxEmbeddingDim=8,timeLag=1,minRadius=1,
             maxRadius=15, pointsRadius=20,theilerWindow=10,
             corrOrder=2,doPlot=FALSE)
 PlotCorrDim(hrv.data,indexNonLinearAnalysis=1)
 hrv.data = EstimateCorrDim(hrv.data,indexNonLinearAnalysis=1,
             useEmbeddings=6:8,regressionRange=c(1,10))

## End(Not run)