Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
7598307 | Food Chemistry | 2014 | 5 Pages |
Abstract
The aim of this study was to evaluate the potential of near-infrared reflectance spectroscopy (NIR) as a rapid and non-destructive method to determine soluble solid content (SSC) in intact jaboticaba [Myrciaria jaboticaba (Vell.) O. Berg] fruit. Multivariate calibration techniques were compared with pre-processed data and variable selection algorithms, such as partial least squares (PLS), interval partial least squares (iPLS), a genetic algorithm (GA), a successive projections algorithm (SPA) and nonlinear techniques (BP-ANN, back propagation of artificial neural networks; LS-SVM, least squares support vector machine) were applied to building the calibration models. The PLS model produced prediction accuracy (R2 = 0.71, RMSEP = 1.33 °Brix, and RPD = 1.65) while the BP-ANN model (R2 = 0.68, RMSEM = 1.20 °Brix, and RPD = 1.83) and LS-SVM models achieved lower performance metrics (R2 = 0.44, RMSEP = 1.89 °Brix, and RPD = 1.16). This study was the first attempt to use NIR spectroscopy as a non-destructive method to determine SSC jaboticaba fruit.
Related Topics
Physical Sciences and Engineering
Chemistry
Analytical Chemistry
Authors
Nathália Cristina Torres Mariani, Rosangela Câmara da Costa, Kássio Michell Gomes de Lima, Viviani Nardini, LuÃs Carlos Cunha Júnior, Gustavo Henrique de Almeida Teixeira,