PLS_Toolbox Documentation: normaliz	< nippls	npls >

normaliz

Purpose

Normalizes rows of matrix to unit vectors.

Synopsis

[ndat,norms] = normaliz(dat)

[ndat,norms] = normaliz(dat,out,normtype)

Description

NORMALIZ can be used for pattern normalization, which is useful for preprocessing in some pattern recognition applications and also for correction of pathlength effects for some quantification applications.

The input is the data matrix dat. Optional input out suppresses warnings when set to 0 (zero) {default = 1} (warnings are given if the norm of a vector is zero). Optional input normtype can be used to specify the type of norm {default = 2}. If normtype is specified then out must be included, out can be empty [].

The output is the matrix of normalized data ndat where the rows have been normalized, and the vector of norms used in the normalization norms. Warnings are given for any vectors with zero norm.

Algorithm

For a 1 by N vector x, the norm n_x is given by  where p is normtype. The normalized 1 by N vector x_n is given by x/n_x.

See Also

auto, baseline, mncn, mscorr, snv