Fuzzy c-means and Gaussian mean shift

FuzzyCmeans: Bezdek (1981) iterations from given centres with the Xie-Beni index (Xie and Beni 1991) and partition coefficient. MeanShift: Gaussian-kernel mode seeking (Comaniciu and Meer 2002), modes within merge_tol merged.

Usage

FuzzyCmeans(X, centers, m = 2, tol = 1e-09, maxit = 1000L)

MeanShift(X, bandwidth, tol = 1e-10, maxit = 1000L, merge_tol = NULL)

Arguments

X

Data matrix.

centers

Initial centres.

m

Fuzzifier.

tol

Tolerance.

maxit

Maximum iterations.

bandwidth

Kernel bandwidth.

merge_tol

Mode merging distance (default bandwidth / 100).

Value

List.

References

Bezdek, J. C. (1981). Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum.

Comaniciu, D. and Meer, P. (2002). Mean shift: a robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 603-619.

Examples

FuzzyCmeans(matrix(c(0, 1, 9, 10)), matrix(c(0, 10)))$centers
#>           [,1]
#> [1,] 0.4997402
#> [2,] 9.5002598
MeanShift(matrix(c(0, 0.2, 5, 5.2)), 0.5)$cluster
#> [1] 1 1 2 2