A clustering approach applicable to every projection method is proposed here [Thrun/Ultsch,2017] <doi:10.13140/RG.2.2.13124.53124>. The two-dimensional scatter plot of any projection method can construct a topographic map which displays unapparent data structures by using distance and density information of the data. The visualization of the topographic map is derived from the generalized U*-matrix. Thus, it can be used to define the clusters of high-dimensional data automatically. The whole system is a generalization of the book "Projection-Based Clustering through Self-Organization and Swarm Intelligence" <doi:10.1007/978-3-658-20540-9>. Choosing a correct projection method will result in a visualization where mountains surround each cluster. The number of clusters can be determined by counting valleys on the topographic map. Most projection methods are wrappers for already available methods in R. By contrast, the neighbor retrieval visualizer (NeRV) is based on C++ source code of the 'dredviz' software package, and the Curvilinear Component Analysis (CCA) is translated from 'MATLAB' ('SOM Toolbox' 2.0) to R.
Version: |
1.0.6 |
Depends: |
R (≥ 3.0) |
Imports: |
Rcpp, ggplot2, stats, graphics, vegan, deldir, geometry, GeneralizedUmatrix, shiny, shinyjs |
LinkingTo: |
Rcpp |
Suggests: |
DataVisualizations, fastICA, tsne, FastKNN, MASS, pcaPP, spdep, methods, pracma, grid, mgcv, fields, png, reshape2 |
Published: |
2018-01-31 |
Author: |
Michael Thrun [aut, cre, cph],
Florian Lerch [aut],
Felix Pape [aut],
Kristian Nybo [cph],
Jarkko Venna [cph] |
Maintainer: |
Michael Thrun <m.thrun at gmx.net> |
License: |
GPL-3 |
URL: |
https://www.uni-marburg.de/fb12/datenbionik/software-en |
NeedsCompilation: |
yes |
SystemRequirements: |
C++11 |
CRAN checks: |
ProjectionBasedClustering results |