Predicting soluble solid content in intact jaboticaba [Myrciaria jaboticaba (Vell.) O. Berg] fruit using near-infrared spectroscopy and chemometrics

Food Chem. 2014 Sep 15:159:458-62. doi: 10.1016/j.foodchem.2014.03.066. Epub 2014 Mar 20.

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 (R(2)=0.71, RMSEP=1.33 °Brix, and RPD=1.65) while the BP-ANN model (R(2)=0.68, RMSEM=1.20 °Brix, and RPD=1.83) and LS-SVM models achieved lower performance metrics (R(2)=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.

Keywords: BP-ANN; LS-SVM; NIR spectroscopy; PLS; Variables selection.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Calibration
  • Fruit / chemistry*
  • Least-Squares Analysis
  • Multivariate Analysis
  • Myrtaceae / chemistry*
  • Neural Networks, Computer
  • Plant Extracts / chemistry*
  • Reproducibility of Results
  • Spectroscopy, Near-Infrared*
  • Support Vector Machine

Substances

  • Plant Extracts