This item still needs to be validated !
Title: Effect of biological variability on the robustness of NIR models for soluble solids content of apples
Authors: Peirs, Ann
Tirry, J
Verlinden, Bert
Darius, Paul
Nicolai, Bart #
Issue Date: May-2003
Publisher: Elsevier science bv
Series Title: Postharvest biology and technology vol:28 issue:2 pages:269-280
Abstract: A statistical analysis was performed I on a large spectral data set to analyse the effect of orchard, season and cultivar. Season and cultivar were responsible for a major amount of the spectral variability, whereas the influence of the orchard was low and only appeared for certain cultivars during specific seasons. The robustness of the calibration models for soluble solids content with respect to the three factors was tested based on external validations. It was found that the accuracy of the models increased considerably when including more variability in the calibration set. Further, overfitting of the calibration model was avoided. On the other hand, adding more data to the calibration set increased the chance of adding atypical data, which resulted in reduced model accuracy. It is, therefore, important to construct the calibration data set in such a way that it is representative for future measurements. When the effect of a certain factor is known a priori, e.g. cultivar, it is recommended to use specific calibration models. (C) 2002 Elsevier Science B.V. All rights reserved.
ISSN: 0925-5214
Publication status: published
KU Leuven publication type: IT
Appears in Collections:Leuven Statistics Research Centre (LStat)
Division of Mechatronics, Biostatistics and Sensors (MeBioS)
# (joint) last author

Files in This Item:

There are no files associated with this item.

Request a copy


All items in Lirias are protected by copyright, with all rights reserved.

© Web of science