Disciminant analysis and data clustering methods for high dimensional data, based on the asumption that high-dimensional data live in different subspaces with low dimensionality, proposing a new parametrization of the Gaussian mixture model which combines the ideas of dimension reduction and constraints on the model.
Laurent Berge, Charles Bouveyron and Stephane Girard
Maintainer: Laurent Berge <laurent.berge at uni.lu>
| Package: | HDclassif |
| Type: | Package |
| Version: | 2.1.0 |
| Date: | 2018-05-11 |
| License: | GPL-2 |
| LazyLoad: | yes |
This package is used to make efficient supervised and unsupervised classification with high dimensional data. The supervised method uses the hdda function to get the data parameters and the predict function to realise the class prediction of a dataset. The unsupervised method is implemented in the hddc function, and once the parameters are estimated, the predict gives the class prediction of other datasets. The method used in the hddc is based on the Expectation - Maximisation algorithm.
Bouveyron, C. Girard, S. and Schmid, C. (2007) “High Dimensional Discriminant Analysis”, Communications in Statistics: Theory and Methods, vol. 36 (14), pp. 2607--2623
Bouveyron, C. Girard, S. and Schmid, C. (2007) “High-Dimensional Data Clustering”, Computational Statistics and Data Analysis, vol. 52 (1), pp. 502--519
Berge, L. Bouveyron, C. and Girard, S. (2012) “HDclassif: An R Package for Model-Based Clustering and Discriminant Analysis of High-Dimensional Data”, Journal of Statistical Software, 46(6), 1--29, url: http://www.jstatsoft.org/v46/i06/