Jump to main content
Jump to site search

Issue 8, 2014
Previous Article Next Article

Determination of the contents of magnesium and potassium in rapeseeds using FTIR-PAS combined with least squares support vector machines and uninformative variable elimination

Author affiliations

Abstract

Fourier transform mid-infrared photoacoustic spectroscopy (FTIR-PAS) was employed to determine the contents of magnesium and potassium in rapeseeds. A total of 180 samples were collected for this purpose. A Savitzky–Golay filter was used for the spectral pretreatment. The whole sample set was divided into calibration and prediction sets composed of 135 and 45 samples, respectively. To build calibration models, partial least squares (PLS), least squares support vector machines (LS-SVM) and least squares support vector machines combined with uninformative variable elimination (UVE-LS-SVM) were used. The best results for quantification of both magnesium and potassium were achieved by UVE-LS-SVM models compared to the PLS models. The highest values of RPD (ratio of percentage deviation) were 2.5 and 2.25 for the prediction of magnesium and potassium, respectively. This work verified the good promise of FTIR-PAS combined with LS-SVM to quantify mineral nutrients of rapeseeds.

Graphical abstract: Determination of the contents of magnesium and potassium in rapeseeds using FTIR-PAS combined with least squares support vector machines and uninformative variable elimination

Back to tab navigation

Publication details

The article was received on 26 Aug 2013, accepted on 01 Feb 2014 and first published on 03 Feb 2014


Article type: Paper
DOI: 10.1039/C3AY41460D
Author version available: Download Author version (PDF)
Citation: Anal. Methods, 2014,6, 2586-2591
  •   Request permissions

    Determination of the contents of magnesium and potassium in rapeseeds using FTIR-PAS combined with least squares support vector machines and uninformative variable elimination

    Y. Lu, C. Du, C. Yu and J. Zhou, Anal. Methods, 2014, 6, 2586
    DOI: 10.1039/C3AY41460D

Search articles by author

Spotlight

Advertisements