Projection to latent correlative structures, a dimension reduction strategy for spectral-based classification.

Autor:	Erny GL; LEPABE - Laboratory for Process Engineering, Environment, Biotechnology and Energy, Faculdade de Engenharia da Universidade do Porto Rua Dr Roberto Frias 4200-465 Porto Portugal guillaume@fe.up.pt., Brito E; ITQB NOVA, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa Avenida da República 2780-157 Oeiras Portugal., Pereira AB; iBET, Instituto de Biologia Experimental e Tecnológica Avenida da República, Quinta-do-Marquês, Estação Agronómica Nacional, Apartado 12 2780-901 Oeiras Portugal., Bento-Silva A; ITQB NOVA, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa Avenida da República 2780-157 Oeiras Portugal.; FCT NOVA, School of Science and Technology, New University of Lisbon Caparica Portugal.; FFULisboa, Faculdade de Farmácia da Universidade de Lisboa Av. das Forças Armadas 1649-019 Lisboa Portugal., Vaz Patto MC; ITQB NOVA, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa Avenida da República 2780-157 Oeiras Portugal., Bronze MR; ITQB NOVA, Instituto de Tecnologia Química e Biológica António Xavier, Universidade Nova de Lisboa Avenida da República 2780-157 Oeiras Portugal.; iBET, Instituto de Biologia Experimental e Tecnológica Avenida da República, Quinta-do-Marquês, Estação Agronómica Nacional, Apartado 12 2780-901 Oeiras Portugal.; FCT NOVA, School of Science and Technology, New University of Lisbon Caparica Portugal.
Jazyk:	angličtina
Zdroj:	RSC advances [RSC Adv] 2021 Sep 01; Vol. 11 (47), pp. 29124-29129. Date of Electronic Publication: 2021 Sep 01 (Print Publication: 2021).
DOI:	10.1039/d1ra03359j
Abstrakt:	Latent variables are used in chemometrics to reduce the dimension of the data. It is a crucial step with spectroscopic data where the number of explanatory variables can be very high. Principal component analysis (PCA) and partial least squares (PLS) are the most common. However, the resulting latent variables are mathematical constructs that do not always have a physicochemical interpretation. A new data reduction strategy, named projection to latent correlative structures (PLCS), is introduced in this manuscript. This approach requires a set of model spectra that will be used as references. Each latent variable is the relative similarity of a given spectrum to a pair of reference spectra. The latent structure is obtained using every possible combination of reference pairing. The approach has been validated using more than 500 FTIR-ATR spectra from cool-season culinary grain legumes assembled from germplasm banks and breeders' working collections. PLCS has been combined with soft discriminant analysis to detect outliers that could be particularly suitable for a deeper analysis. Competing Interests: There are no conflicts to declare. (This journal is © The Royal Society of Chemistry.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu