Record Details

Local partial least squares based on global PLS scores

CGSpace

View Archive Info
 
 
Field Value
 
Title Local partial least squares based on global PLS scores
 
Creator Shen, Guanghui
Lesnoff, Matthieu
Baeten, Vincent
Dardenne, Pierre
Davrieux, Fabrice
Ceballos, Hernán
Belalcázar, John Eiver
Dufour, Dominique
Yang, Zengling
Han, Lujia
Fernández Pierna, Juan Antonio
 
Description A local‐based method for near‐infrared spectroscopy predictions, the local partial least squares regression on global PLS scores (LPLS‐S), is proposed in this work and compared with the usual local PLS (LPLS) regression approach. LPLS‐S is based on the idea of replacing the original spectra with a global PLS score matrix before using the usual LPLS. This is done with the aim of increasing the speed of the calculations, which can be an important parameter for online applications in particular, especially when implemented on large databases. In this study, the performance of the two local approaches was compared in terms of efficiency and speed. It could be concluded that the root‐mean‐square error of prediction of LPLS and LPLS‐S were 1.1962 and 1.1602, respectively, but the calculation speed for LPLS‐S was more than 20 times faster than for the LPLS algorithm.
 
Date 2019-05
2019-04-09T14:33:12Z
2019-04-09T14:33:12Z
 
Type Journal Article
 
Identifier Shen, Guanghui; Lesnoff, Matthieu; Baeten, Vincent; Dardenne, Pierre; Davrieux, Fabrice; Ceballos, Hernan; Belalcazar, John; Dufour, Dominique; Yang, Zengling; Han, Lujia & Fernández Pierna, Juan Antonio (2019). Local partial least squares based on global PLS scores. Journal of Chemometrics, 1-12 P.
0886-9383
https://hdl.handle.net/10568/100718
https://doi.org/10.1002/cem.3117
 
Language en
 
Rights Copyrighted; all rights reserved
Open Access
 
Format 1-12 p.
 
Publisher Wiley
 
Source Journal of Chemometrics