Laboratório de Automação e Instrumentação em Química Analítica e Quimiometria (LAQA) Universidade Federal da Paraíba, CCEN, Departamento de Química, Caixa Postal 5093, CEP 58051-970, João Pessoa, PB, Brazil.
Faculdade de Química, Instituto de Ciências Exatas da Universidade Federal do Sul e Sudoeste do Pará, Folha 17, Quadra 04, Lote Especial, Nova Marabá, CEP: 68.505.080, Marabá, Pará, Brazil.
Talanta. 2018 May 1;181:38-43. doi: 10.1016/j.talanta.2017.12.064. Epub 2017 Dec 24.
This paper proposes a new variable selection method for nonlinear multivariate calibration, combining the Successive Projections Algorithm for interval selection (iSPA) with the Kernel Partial Least Squares (Kernel-PLS) modelling technique. The proposed iSPA-Kernel-PLS algorithm is employed in a case study involving a Vis-NIR spectrometric dataset with complex nonlinear features. The analytical problem consists of determining Brix and sucrose content in samples from a sugar production system, on the basis of transflectance spectra. As compared to full-spectrum Kernel-PLS, the iSPA-Kernel-PLS models involve a smaller number of variables and display statistically significant superiority in terms of accuracy and/or bias in the predictions.
本文提出了一种新的非线性多变量校准变量选择方法，将区间选择的连续投影算法（iSPA）与核偏最小二乘（Kernel-PLS）建模技术相结合。所提出的 iSPA-Kernel-PLS 算法应用于一个具有复杂非线性特征的 Vis-NIR 光谱数据集的案例研究中。分析问题是根据漫反射光谱，确定制糖系统中样品的 Brix 和蔗糖含量。与全谱 Kernel-PLS 相比，iSPA-Kernel-PLS 模型涉及的变量较少，并且在预测的准确性和/或偏差方面具有统计学上的显著优势。
