delta_Bel {evclust}

Delta-Bel graph for Belief Peak Evidential Clustering (BPEC)

Description

delta_Bel computes the delta-Bel graph used to determine the proptotypes in the Belief Peak Evidential Clustering (BPEC) algorithm. The user must manually specify the rectangles containing the protytypes (which are typically in the upper-right corner of the graph is the clusters are well-seperated). These prototypes are then used by function bpec to compute a credal partition.

Usage

delta_Bel(x, K, q = 0.9)

Arguments

x

input matrix of size n x d, where n is the number of objects and d the number of attributes.

K

Number of neighbors to determine belief values

q

Parameter of the algorithm, between 0 and 1 (default: 0.9).

Value

A list with three elements:

BelC

The belief values.

delta

The delta values.

g0

A c*d matrix containing the prototypes.

ii

List of indices of the belief peaks.

Author(s)

Thierry Denoeux .

References

Z.-G. Su and T. Denoeux. BPEC: Belief-Peaks Evidential Clustering. IEEE Transactions on Fuzzy Systems, 27(1):111-123, 2019.

See Also

bpec

Examples

## Not run: 
data(fourclass)
x<-fourclass[,1:2]
y<-fourclass[,3]
DB<-delta_Bel(x,100,0.9)
plot(x,pch=".")
points(DB$g0,pch=3,col="red",cex=2)

## End(Not run)