clusterISODATA: Cluster Clustering using the Isodata Approach

In FRESA.CAD: Feature Selection Algorithms for Computer Aided Diagnosis

Cluster Clustering using the Isodata Approach

Description

Returns the set of Gaussian Ellipsoids that best model the data

Usage

   clusterISODATA(dataset,
                 clusteringMethod=GMVECluster,
                 trainFraction=0.99,
                 randomTests=10,
                 jaccardThreshold=0.45,
                 isoDataThreshold=0.75,
                 plot=TRUE,
                 ...)

Arguments

dataset	The data set to be clustered
clusteringMethod	The clustering method.
trainFraction	The fraction of the data used to train the clusters
randomTests	The number of clustering sets that will be generated
jaccardThreshold	The minimum Jaccard index to be considered for data clustering
isoDataThreshold	The minimum distance (as p.value) between gaussian clusters
plot	If true it will plot the clustered points
...	Parameter list to be passed to the clustering method

Details

The data will be clustered N times as defined by a number of randomTests. After clustering, the Jaccard Index map will be generated and ordered from high to low. The mean clusters parameters (Covariance sets) associated with the point with the highest Jaccard index will define the first cluster. A cluster will be added if the Mahalanobis distance between clusters is greater than the given acceptance p.value (isoDataThreshold) Only clusters associated with points with a Jaccard index greater than jaccardThreshold will be considered.

Value

cluster	The numeric vector with the cluster label of each point
classification	The numeric vector with the cluster label of each point
robustCovariance	The list of robust covariances per cluster
pointjaccard	The mean of jaccard index per data point
centers	The list of cluster centers
covariances	The list of cluster covariance
features	The characer vector with the names of the features used

Author(s)

Jose G. Tamez-Pena

FRESA.CAD documentation built on Nov. 25, 2023, 1:07 a.m.