pedometrics (version 0.4-1)

spJitterFinite: Random perturbation of spatial points

Description

This function perturbs the coordinates of spatial points. This is also known as jittering.

Usage

spJitterFinite(points, candidates, x.max, x.min, y.max, y.min, which.point)

Arguments

points

data.frame or matrix with three columns: 1) the identification of each point, 2) the x coordinates of the set of points, and 3) the y coordinates of the set of points. The coordinates must be projected. This is the set of points to be optimized. poi

candidates

data.frame or matrix with the candidate locations for the sample points. See Details for more information.

x.max,x.min,y.max,y.min

The minimum and maximum quantity of random noise to be added to the x and y coordinates. The minimum quantity should be equal to, at least, the minimum distance between two neighboring candidate locations. The units are the same as of the coordinates. See

which.point

Integer values defining which point should be perturbed. The current version accepts only one point to be perturbed at a time. See Details for more information.

Value

• A matrix with the jittered coordinates of the points.

concept

jitter perturb

Details

This function perturbs the coordinates of spatial points adding random noise, a process also known as jittering. There are two ways of jittering the coordinates. They differ on how the the set of candidate locations is defined.

Finite set of candidate locations{ The first method uses a finite set of candidate locations for the perturbed points. This method usually is the fastest because it does not require the use of complex routines to check if the perturbed point falls inside the spatial domain. Since the candidate locations is a finite set, any perturbed point will inexorably fall inside the spatial domain. This is a very important feature in optimization exercises with complex objective functions such as simulated annealing when repetitive perturbation is required.

The arguments x.min, y.min, x.max, and y.max are used to define a rectangular window containing the set of effective candidate locations for the point defined with the argument which.point. The new location is then randomly sampled from the set of effective candidate locations and checked against existing points to avoid duplicates. The current implementation does not enable to define the direction of the perturbation, nor to perturb more than one point at a time. } Infinite set of candidate locations{ The current version does not accept using an infinite set of candidate locations. }

References

Edzer Pebesma, Jon Skoien with contributions from Olivier Baume, A. Chorti, D.T. Hristopulos, S.J. Melles and G. Spiliopoulos (2013). intamapInteractive: procedures for automated interpolation - methods only to be used interactively, not included in intamap package. R package version 1.1-10. http://CRAN.R-project.org/package=intamapInteractive

Van Groenigen, J.-W. Constrained optimization of spatial sampling: a geostatistical approach. Wageningen: Wageningen University, p. 148, 1999.

See Also

ssaOptim, zerodist, jitter, jitter2d, gContains.

Examples

require(sp)
data(meuse.grid)
meuse.grid <- as.matrix(meuse.grid[, 1:2])
meuse.grid <- matrix(cbind(1:dim(meuse.grid)[1], meuse.grid), ncol = 3)
pts1 <- sample(c(1:dim(meuse.grid)[1]), 155)
pts2 <- meuse.grid[pts1, ]
pts3 <- spJitterFinite(points = pts2, candidates = meuse.grid, x.min = 40,
                      x.max = 100, y.min = 40, y.max = 100, which.point = 10)
plot(meuse.grid[, 2:3], asp = 1, pch = 15, col = "gray")
points(pts2[, 2:3], col = "red", cex = 0.5)
points(pts3[, 2:3], pch = 19, col = "blue", cex = 0.5)