Rapid quantification of grapeseed oil multiple adulterations using near-infrared spectroscopy coupled with a novel double ensemble modeling method
writer:Xihui Bian*, Yuxia Liu, Rongling Zhang, Hao Sun, Peng Liu, Xiaoyao Tan
keywords:Adulterated grapeseed oil, Spectral analysis, Multivariate calibration, Whale optimization algorithm, Monte Carlo sampling
source:期刊
specific source:Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2024, 311, 124016
Issue time:2024年
As a high-quality edible oil, grapeseed oil is often adulterated with low-price/quality vegetable oils, such as soybean oil. A novel ensemble modeling method named as MC-WOA-PLS is proposed for quantitative analysis of grapeseed oil adulterations combined with near-infrared (NIR) spectroscopy. The method combines Monte Carlo (MC) sampling and whale optimization algorithm (WOA) to build numerous partial least squares (PLS) sub-models. A total of 80 adulterated grapeseed oil samples were prepared by mixing grapeseed oil with soybean oil, palm oil, cottonseed oil and corn oil with the designed mass percentages. NIR spectra of the 80 samples were measured in a transmittance mode in the range of 12000-4000 cm-1. Parameters in MC-WOA-PLS including the number of LVs in PLS, iteration number of WOA, whale number, iteration number of the sub-model, and percentage of training subsets were optimized. To validate the prediction performance of the model, root mean squared error of prediction (RMSEP), correlation coefficient (R), residual predictive deviation (RPD) and standard deviation (S.D.) were used. Compared with PLS and WOA-PLS, MC-WOA-PLS can achieve the best prediction accuracy and stability for quantification of the five pure oils in adulterated grapeseed oil samples.