A PLS model for prediction of somatic cell count (SCC) based on near-infrar
ed (NIR) spectra of unhomogenized milk is presented in the study. Samples o
f raw mills were collected from cows in the early lactation period (from 7t
h to 29th day after parturition). The NIR spectra were measured in the regi
on 400-1100 nm. As reference method a fluoro-opto-electronic method was app
lied. Different preprocessing methods were investigated. The robust version
of PLS regression was applied to handle outliers present in the dataset an
d the uninformative variable elimination-partial least squares (UVE-PLS) me
thod was used to eliminate uninformative variables. The final model is acce
ptable for prediction of SCC in raw milk. (C) 2001 Elsevier Science B.V. Al
l rights reserved.