PCA_DD Principal Component data description
W = PCA_DD(A,FRACREJ,N) W = PCA_DD(A,FRACREJ,VAR)
Fit a Principal Component Analysis data description by estimating first a PCA on the target class, and mapping the training data onto the PCA subspace. The distance between the original objects and the mapped objects is used to detect outliers. The number of dimensions of the PCA can be supplied by N. Alternatively the fraction of explained variance can be given (in VAR).
Default: FRACRE=0.05, VAR=0.9 Copyright: D.M.J. Tax, D.M.J.Tax@prtools.org Faculty EWI, Delft University of Technology P.O. Box 5031, 2600 GA Delft, The Netherlands