ghkss {RTisean} | R Documentation |
Performs a noise reduction, through an orthogonal projection onto manifold using an euclidean or a special metric.
ghkss(series, l, x = 0, c = 1, m = 5, d = 1, q = 3, k = 30, r, i = 1, two = FALSE)
series |
a vector or a matrix. |
l |
number of data to use. |
x |
number of lines to be ignored. |
c |
column to be read. |
m |
embedding dimension. |
d |
delay for the embedding. |
q |
dimension of the manifold to project to. |
k |
minimal number of neighbours. |
r |
minimal size of the neighbourhood. |
i |
number of iterations. |
two |
use euclidean metric instead of the special one. |
A list of vectors with filtered time series, one per iteration.
P. Grassberger, R. Hegger, H. Kantz, C. Schaffrath, and T. Schreiber, On noise reduction methods for chaotic data, CHAOS 3, 127 (1993).
## Not run: #FIXME: find better example dat <- logistic(iter=10000,r=3.8, noisesd=0.01) filteredat <- ghkss(dat)[[1]] delayedfiltered <- embed(filteredat, d=2) delayed <- embed(dat,d=2) plot(delayed,cex=0.8,xlab="x(t)",ylab="x(t+1)",main="Delayed Logistic Chaotic Attractor",pch='.') points(delayedfiltered,col=2,cex=0.8,pch='.') legend(0.5,0.4, c("Noisy data","Filtered data"),fill=c(1,2), bty="n",cex=0.8) ## End(Not run)