RefDoc
Haut

Faire une nouvelle recherche
Make a new search
Lancer la recherche


Titre du document / Document title

A Backward Variable Selection method for PLS regression (BVSPLS)

Auteur(s) / Author(s)

FERNANDEZ PIERNA Juan Antonio (1) ; ABBAS Ouissam (1) ; BAETEN Vincent (1) ; DARDENNE Pierre (1) ;

Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)

(1) Walloon Agricultural Research Centre (CRA-W), Quality of Agricultural Products Department, Chaussée de Namurn 24, 5030 Gembloux, BELGIQUE

Résumé / Abstract

Variable selection has been discussed in many papers and it became an important topic in areas as chemometrics and science in general. Here a backward iterative step-by-step wrapper method is proposed using PLS. The root-mean-square error of prediction (RMSEP) for an independent test set is used as selection criterion to quantify the gain obtained using the selected range of variables. The method has been applied to different data sets and the results obtained revealed that one can improve or at least keep constant the prediction performances of the PLS models compared to the full-spectrum models. Moreover with the advantage that the number of variables is reduced driving to an easier interpretation of the relationship between model and sample composition and/or properties. The aim is not to compare to other variable selection methods but to show that a simple one can improve or at least keep constant the prediction performances of the PLS models by using only a limited number of variables.

Revue / Journal Title

Analytica chimica acta    ISSN  0003-2670   CODEN ACACAM 

Source / Source

Congrès
International Conference on Chemometrics in Analytical Chemistry No11, Montpellier , FRANCE (30/06/2008)
2009, vol. 642, no 1-2 (294 p.)  [Document : 5 p.] (17 ref.), pp. 89-93 [5 page(s) (article)]

Langue / Language

Anglais

Editeur / Publisher

Elsevier, Amsterdam, PAYS-BAS  (1947) (Revue)

Mots-clés anglais / English Keywords

Near infrared spectrometry

;

Performance evaluation

;

Selection criterion

;

Mean square error

;

Step by step method

;

Chemometrics

;

PLS regression

;

Mots-clés français / French Keywords

Spectrométrie IR proche

;

Evaluation performance

;

Critère sélection

;

Erreur quadratique moyenne

;

Méthode pas à pas

;

Chimiométrie

;

Régression PLS

;

Mots-clés espagnols / Spanish Keywords

Espectrometría IR próximo

;

Evaluación prestación

;

Criterio selección

;

Error medio cuadrático

;

Método paso a paso

;

Quimiometría

;

Regresión PLS

;

Mots-clés d'auteur / Author Keywords

Variable selection

;

Partial least squares

;

Regression

;

Near infrared spectroscopy

;

Localisation / Location

INIST-CNRS, Cote INIST : 3950, 35400018823923.0110

Nº notice refdoc (ud4) : 21709036



Faire une nouvelle recherche
Make a new search
Lancer la recherche
Bas