Jump to main content
Jump to site search


mRMR-based wavelength selection for NIRS quantitative detection of Chinese yellow wine

Abstract

Wavelength selection plays an important role in the analysis of near-infrared(NIR) spectroscopy.This paper introduces the minimal-redundancy-maximal-relevance(mRMR) algorithm into NIR analysis for wavelength selection, by which relevance between spectrum and target component is maximized while redundancy among selected wavelengths is minimized. The wavelength selection method is applied in Chinese yellow wine to make prediction for concentration of ethanol. Prediction performance of mRMR algorithm is compared with another two widely used wavelength selection methods (correlation coefficient method and successive projections algorithm). Meanwhile, the adaptability of mRMR is verified by combining with partial least square regression model and support vector regression. A total of 30 wavelengths were selected as the optimal set. The correlation coefficient, root mean square errors of prediction and residual predictive deviation are employed to evaluate model performance, and the three indices reach 0.9848, 0.8159 and 3.6875 by mRMR based support vector regression. The results indicate that mRMR algorithm can be applied to NIR analysis as an effective wavelength selection tool and has a stable prediction performance no matter which kind of regression method is used.

Back to tab navigation

Publication details

The article was received on 23 Oct 2017, accepted on 28 Dec 2017 and first published on 02 Jan 2018


Article type: Paper
DOI: 10.1039/C7AY02488F
Citation: Anal. Methods, 2018, Accepted Manuscript
  •   Request permissions

    mRMR-based wavelength selection for NIRS quantitative detection of Chinese yellow wine

    L. Chen, Z. Zhao and F. Liu, Anal. Methods, 2018, Accepted Manuscript , DOI: 10.1039/C7AY02488F

Search articles by author

Spotlight

Advertisements