Learn R Programming

evclust (version 2.0.3)

Evidential Clustering

Description

Various clustering algorithms that produce a credal partition, i.e., a set of Dempster-Shafer mass functions representing the membership of objects to clusters. The mass functions quantify the cluster-membership uncertainty of the objects. The algorithms are: Evidential c-Means, Relational Evidential c-Means, Constrained Evidential c-Means, Evidential Clustering, Constrained Evidential Clustering, Evidential K-nearest-neighbor-based Clustering, Bootstrap Model-Based Evidential Clustering, Belief Peak Evidential Clustering, Neural-Network-based Evidential Clustering.

Copy Link

Version

Install

install.packages('evclust')

Monthly Downloads

345

Version

2.0.3

License

GPL-3

Maintainer

Thierry Denoeux

Last Published

November 9th, 2023

Functions in evclust (2.0.3)

pairwise_mass

Computes the relational representation
kpcca

Kernel Pairwise Constrained Component Analysis (KPCCA)
summary.credpart

Summary of a credal partition
pcca

Pairwise Constrained Component Analysis (PCCA)
s2

S2 dataset
normalize.credpart

Normalization of a credal partition
nonspecificity

Nonspecificity of the relational representation of a credal partition
kcevclus

k-CEVCLUS algorithm
nnevclus

NN-EVCLUS algorithm
nnevclus_mb

NN-EVCLUS algorithm (minibatch version)
protein

Protein dataset
makeF

Creation of a matrix of focal sets
recm

Relational Evidential c-means algorithm
plot.credpart

Plotting a credal partition
kevclus

k-EVCLUS algorithm
knn_dist

K nearest neighbors in a dissimilarity matrix
predict.credpart

Computation of a credal partition for new data
bootclus

Generating a credal partition by bootstraping Gaussian Mixture Models
create_MLCL

Random generation of Must-Link and Cannot-Link constraints
EkNNclus

EkNNclus algorithm
bpec

Belief Peak Evidential Clustering (BPEC)
create_fuzzy_credpart

Creation of a "credpart" object from a from a fuzzy or possibilistic partition matrix
butterfly

Butterfly dataset
createPairs

Finding overlapping pairs of clusters
bananas

Generation of "bananas" datasets
cecm

Constrained Evidential c-means algorithm
createD

Computation of a Euclidean distance matrix
harris

Harris gradient-based optimization algorithm
create_hard_credpart

Creation of a "credpart" object from a vector of class labels
extractMass

Creates an object of class "credpart"
evclust

evclust: A package for evidential clustering
credal_RI

Credal Rand indices
delta_Bel

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

Evidential c-means algorithm
fourclass

Synthetic four-class dataset
expandlink

Expansion of must-link and cannot-link constraints