evclust (version 2.0.3)

predict.credpart: Computation of a credal partition for new data

Description

predict.credpart is the predict method for "credpart" objects generated by nnevclus or ecm.

Usage

# S3 method for credpart
predict(object, newdata, fhat = NULL, ...)

Value

A credal partition of the new data.

Arguments

object

An object of class "credpart", encoding a credal partition.

newdata

A matrix of size ntest*p containing the new data.

fhat

An optional vector of one-class SVM outputs (for method nn-evclus only)

...

Additional arguments (not used).

Details

This function computes a credal partial of newdata based on learnt information stored in a "credpart" objects created by ecm or nnevclus.

References

T. Denoeux and O. Kanjanatarakul. Beyond Fuzzy, Possibilistic and Rough: An Investigation of Belief Functions in Clustering. 8th International conference on soft methods in probability and statistics, Rome, 12-14 September, 2016.

M.-H. Masson and T. Denoeux. ECM: An evidential version of the fuzzy c-means algorithm. Pattern Recognition, Vol. 41, Issue 4, pages 1384--1397, 2008.

T. Denoeux, S. Sriboonchitta and O. Kanjanatarakul. Evidential clustering of large dissimilarity data. Knowledge-Based Systems, vol. 106, pages 179-195, 2016.

See Also

ecm, cecm, nnevclus.

Examples

if (FALSE) {
data(fourclass)
train<-sample(400,200)
x<-fourclass[train,1:2]
x.test<-x[-train,1:2]
clus<-ecm(x,c=4,type='pairs',delta=sqrt(10),epsi=1e-3,disp=TRUE)
clus.test<-predict(clus,x.test)
plot(clus.test,x.test,mfrow=c(2,2))
}