Determination of fatty acid of wheat by near-infrared spectroscopy with combined feature selection based on CARS and NSGA-III

Abstract

In this study, an innovative method was attempt to use the multi-optimization objective algorithm to select the characteristic wavelengths of wheat near infrared spectra and realize the high-precision analysis of fatty acid in wheat. First, near-infrared (NIR) spectra of wheat samples obtained were collected by a NIRQuest 512 and pre-treated appropriately. Secondly, the competitive adaptive reweighted sampling (CARS) algorithm was used as a rough selection method to eliminate redundant feature variables in the original spectra. Then, the remaining variables were selected by nondominated sorting genetic algorithm-III (NSGA-III), and support vector machine (SVM) models based on optimized features were established to detect fatty acid of wheat with high accuracy. The results obtained showed that the CARS method can effectively screen out the characteristic wavelengths that are closely related to the measured properties of the samples. NSGA-III algorithm can be used to further compress the number of selected feature wavelengths and build a high-performance prediction model. Comparison of different SVM models, the SVM model built on the characteristics obtained by the CARS with the NSGA-III algorithm has the best performance in the case of Case2, and there are only 6 characteristic variables involved in the model establishment. The root mean square error of prediction (RMSEP) was 1.2518 mg/100 g, and the correlation coefficient of prediction (RP) was 0.9897. The results reveal that CARS combined with NSGA-III multi-optimization target algorithm can achieve efficient mining of the spectral characteristics.