A CALIBRATION METHOD, BASED ON RIDGE LS ESTIMATOR DESIGNED FOR DETERMINATION OF OLIVE OIL MIXTURES ON THE BASIS OF NIR SPECTRAL DATA

Andrzej Miekina, Roman Z. Morawski

Abstract

The spectrophotometric analysis of oil mixtures, containing olive oil, is the subject of this paper. Its objective is to propose and evaluate a new methodology for determination of a selected component of such a mixture. According to this methodology, the space of concentration values to be estimated is partitioned into subspaces and the calibration is performed separately for each subspace by means of a new <i>piecewise ridge least-squares estimator</i>. The estimation of concentrations is carried out, using the results of calibration, in two cycles: first, rough estimates of concentrations are found and a corresponding subspace is identified; next, the results of calibration, obtained for this subspace, are used for refining the estimates of concentrations. The performance of the proposed methodology is assessed using a criterion related to measurement uncertainty.

Keywords

least-squares estimators, NIR spectro-photometry, chemometrics, olive oil

Download

IMEKO-WC-2009-TC23-263.pdf

DOI

-

IMEKO TC

TC23 - Metrology in Food and Nutrition

Back to the proceedings