Cross-validation for the selection of spectral variables using the successive projections algorithm

Journal of the Brazilian Chemical Society

Empresa Brasileira de Aeronáutica, São José dos Campos, Brazil¹  Araújo, Mário César Ugulino¹  José, Gledson Emidio¹  Silva, Edvan Cirino¹  Galvão, Roberto Kawakami Harrop¹  Instituto Tecnológico de Aeronáutica, São José dos Campos, Brazil¹  Soares, Sófacles Figueredo Carreiro¹  Paiva, Henrique Mohallem¹  Universidade Federal da Paraíba, João Pessoa, Brazil¹ 

关键词: multiple linear regression;    variable selection;    successive projections algorithm;    cross-validation;    near-infrared spectrometry;   

DOI  :  10.1590/S0103-50532007000800021

学科分类：化学（综合）

来源: SciELO

【 摘 要 】

This work compares the use of a separate validation set and leave-one-out cross-validation to guide the selection of variables in the Successive Projections Algorithm (SPA) for multivariate calibration. Two case studies involving diesel and corn analysis by NIR spectrometry are presented. A graphical interface for SPA is available at www.ele.ita.br/~kawakami/spa/

【 授权许可】

Unknown