Reflectance spectroscopy with operator difference for determination of behenic acid in edible vegetable oils by using convolutional neural network and polynomial correction

• Published in: Food chemistry Vol. 367; p. 130668
• Main Authors: Weng, Shizhuang, Chu, Zhaojie, Wang, Manqin, Han, Kaixuan, Zhu, Gongqin, Liu, Cunchuan, Li, Xinhua, Huang, Linsheng
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.01.2022
• Subjects: Behenic acid; Convolutional neural network; Edible vegetable oil; Polynomial correction; Reflectance spectroscopy; Reflectance spectroscopy; Behenic acid; Polynomial correction; Edible vegetable oil; Convolutional neural network
• ISSN: 0308-8146; 1873-7072
• DOI: 10.1016/j.foodchem.2021.130668

•Reflectance spectroscopy was used to predict behenic acid in edible oils.•OAPC was proposed to alleviate impact of operator differences.•CNN was introduced to develop analysis model for prediction of behenic acid.•Analysis model of effective wavelengths obtained smaller prediction errors. A novel polynomial correction method, order-adaptive polynomial correction (OAPC), was proposed to correct reflectance spectra with operator differences, and convolutional neural network (CNN) was used to develop analysis model to predict behenic acid in edible oils. With application of OAPC, CNN performed well with coefficient of determination of correction (R2cor) of 0.8843 and root mean square error of correction (RMSEcor) of 0.1182, outperforming partial least squares regression, support vector regression and random forest with OAPC, as well as the cases without OAPC. Based on 16 effective wavelengths selected by combination of bootstrapping soft shrinkage, random frog and Pearson’s correlation, CNN and OAPC exhibited excellent performance with R2cor of 0.9560 and RMSEcor of 0.0730. Meanwhile, only 5% correction samples were selected by Kennard–Stone for OAPC. Overall, the proposed method could alleviate the impact of operator differences on spectral analysis, thereby providing potential to correct differences from measurement instruments or environments.