• Suivez-nous

A new method to improve the accuracy of the near infrared models: noise addition partial least squares method


  • Dardenne, P. & Fernández Pierna, J.A. (2006). A new method to improve the accuracy of the near infrared models: noise addition partial least squares method. J. Near Infrared Spectrosc. 14: (6), 349-355.
Type Journal Article
Year 2006
Title A new method to improve the accuracy of the near infrared models: noise addition partial least squares method
Journal J. Near Infrared Spectrosc.
Label U15-0727
Edition Journal Article
Recnumber 255
Volume 14
Issue 6
Pages 349-355
Date 2006
Isbn 0967-0335
Endnote keywords Di-Chimiométrie
Endnote Keywords NiR spectroscopy|noise addition|PLS|b coefficients|
Abstract The accuracy of the y vectors estimated by the NIR models depends on the quality of the reference method. In this paper the reference data values are augmented with noise. The level of noise added ranged from 0 to 20% of the variability for the mean y values. PLS models are then calculated for each addition of noise resulting in many regression coefficient vectors that are used to produce the final calibration model. This final model is selected as the one with the highest R2 with the median of all these coefficient vectors. This model applied on unchanged independent test sets produced a RMSEP that leads to a clear improvement over the original value without noise. The ability of this technique is investigated on a simulated and on an industrial data set.
Author address Dardenne Pierre, Quality Department of Agro-food Products, Walloon Agricultural Research Centre (CRA-W), Chaussée de Namur, 24, B-5030 Gembloux, dardenne@cra.wallonie.be
Fichier A new method to improve the accuracy of the near infrared models: noise addition partial least squares method
Caption U15-0727-dardenne-2006.pdf
Lien http://www.impublications.com/nir/abstract/J14_0349
Authors Dardenne, P. & Fernández Pierna, J.A.