Determination of corn protein content using near-infrared spectroscopy combined with A-CARS-PLS

Xiaohong Wu; Shupeng Zeng; Haijun Fu; Bin Wu; Haoxiang Zhou; Chunxia Dai

doi:10.1016/j.fochx.2023.100666

Determination of corn protein content using near-infrared spectroscopy combined with A-CARS-PLS

Food Chem X. 2023 Mar 30:18:100666. doi: 10.1016/j.fochx.2023.100666. eCollection 2023 Jun 30.

Authors

Xiaohong Wu^{1

2}, Shupeng Zeng¹, Haijun Fu¹, Bin Wu³, Haoxiang Zhou⁴, Chunxia Dai¹

Affiliations

¹ School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China.
² High-Tech Key Laboratory of Agricultural Equipment and Intelligence of Jiangsu Province, Jiangsu University, Zhenjiang 212013, China.
³ Department of Information Engineering, Chuzhou Polytechnic, Chuzhou 239000, China.
⁴ Department of Electrical and Control Engineering, Research Institute of Zhejiang University-Taizhou, Taizhou 318000, China.

Abstract

In order to quickly and accurately determine the protein content of corn, a new characteristic wavelength selection algorithm called anchor competitive adaptive reweighted sampling (A-CARS) was proposed in this paper. This method first lets Monte Carlo synergy interval PLS (MC-siPLS) to select the sub-intervals where the characteristic variables exist and then uses CARS to screen the variables further. A-CARS-PLS was compared with 6 methods, including 3 feature variable selection methods (GA-PLS, random frog PLS, and CARS-PLS) and 2 interval partial least squares methods (siPLS and MWPLS). The results showed that A-CARS-PLS was significantly better than other methods with the results: RMSECV = 0.0336, R² _c = 0.9951 in the calibration set; RMSEP = 0.0688, R² _p = 0.9820 in the prediction set. Furthermore, A-CARS reduced the original 700-dimensional variable to 23 variables. The results showed that A-CARS-PLS was better than some wavelength selection methods, and it has great application potential in the non-destructive detection of protein content in corn.

Keywords: Corn protein; Monte Carlo method; Near-infrared Spectroscopy; Partial least-squares; Wavelength selection.