clues (version 0.3.2)

shrinking: Data Sharpening Based on K-nearest Neighbors

Description

Data sharpening based on K-nearest neighbors.

Usage

shrinking(y, K, disMethod = "Euclidean", eps = 1e-04, itmax = 20)

Arguments

y

data matrix with rows being the observations and columns being variables.

K

number of nearest neighbors.

disMethod

specification of the dissimilarity measure. The available measures are Euclidean and 1-corr.

eps

a small positive number. A value is regarded as zero if it is less than eps.

itmax

maximum number of iterations allowed.

Value

• Sharpened data set.

Details

Within each iteration, each data point is replaced by the vector of the coordinate-wise medians of its K nearest neighbors. Data points will move toward the locally most dense data point by this shrinking process.

See Also

clustering

Examples

# ruspini data
  data(Ruspini)
  # data matrix
  ruspini <- Ruspini$ruspini
  
  tt <- shrinking(ruspini, K = 25)
  tt2 <- clustering(tt)
  plotClusters(ruspini, tt2$mem)