Combination of heuristic optimal partner bands for variable selection in near‐infrared spectral analysis. (29th November 2017)

• Record Type: Journal Article
• Authors: Zhang, Jin; Cui, Xiaoyu; Cai, Wensheng; Shao, Xueguang
• Other Names: Yu Ru–Qin guestEditor.
• Is Part Of: Journal of chemometrics. Volume 32:Number 11(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2017-11-29
• Subjects: near‐infrared spectroscopy -- optimal partner wavelength combination -- spectral band selection -- successive projection algorithm -- variable selection; Chemistry -- Mathematics -- Periodicals; Chemistry -- Statistical methods -- Periodicals; 542.85
• DOI: 10.1002/cem.2971
• Languages: English
• ISSNs: 0886-9383

Abstract

Abstract: Variable selection plays a critical role in the analysis of near‐infrared (NIR) spectra. A method for variable selection based on the principle of the successive projection algorithm (SPA) and optimal partner wavelength combination (OPWC) was proposed for NIR spectral analysis. The method determines a number of knot variables with sufficient independence by SPA, and candidate variable bands with a definite width are defined. The cooperative effect of the bands is then evaluated with the partial least squares regression model by using the method of OPWC. The performance of the proposed method was compared with those of SPA, OPWC, randomization test, competitive adaptive reweighted sampling, and Monte Carlo uninformative variable elimination by using NIR datasets for pharmaceutical tablets, corn, and soil. The results show that the proposed method can select informative variable bands with a cooperative effect and improves the model for quantitative analysis. Abstract : A number of knot variables with independency are determined, and candidate variable bands with a definite width are adaptively defined on the basis of the knot variables. The cooperative effect of the bands is then evaluated by using partial least squares regression models, and the variables in the optimal combinations of the spectral bands are used in building the quantitative model.