Adulteration detection of multi-species vegetable oils in camellia oil using Raman spectroscopy: Comparison of chemometrics and deep learning methods

被引：3

作者：

Wang, Jiahua ^{[1
,2
,3
]}

Qian, Jiangjin ^{[1
]}

Xu, Mengting ^{[1
]}

Ding, Jianyu ^{[1
]}

Yue, Zhiheng ^{[1
]}

Zhang, Yanpeng ^{[1
]}

Dai, Huang ^{[1
,2
,3
]}

Liu, Xiaodan ^{[1
,2
,3
]}

Pi, Fuwei ^{[1
,4
]}

机构：

[1] Wuhan Polytech Univ, Coll Food Sci & Engn, Wuhan 430023, Hubei, Peoples R China

[2] Wuhan Polytech Univ, Key Lab Deep Proc Major Grain & Oil, Minist Educ, Wuhan 430023, Hubei, Peoples R China

[3] Wuhan Polytech Univ, Hubei Key Lab Proc & Transformat Agr Prod, Wuhan 430023, Peoples R China

[4] Jiangnan Univ, Sch Food Sci & Technol, Wuxi 214122, Jiangsu, Peoples R China

来源：

FOOD CHEMISTRY | 2025年 / 463卷

关键词：

Machine learning; Convolutional neural networks; Partial least squares; Classification; Quantitative calculation; MODELS;

D O I：

10.1016/j.foodchem.2024.141314

中图分类号：

O69 [应用化学];

学科分类号：

081704 ;

摘要：

Oil adulteration is a global challenge in the production of high value-added natural oils. Raman spectroscopy combined with mathematical modeling can be used for adulteration detection of camellia oil (CAO). In this study, the advantages of traditional chemometrics and deep learning methods in identifying and quantifying adulterated CAO were compared from a statistical perspective, and no significant difference were founded in the identification of CAO at different levels of adulteration. The recognition rate of pure and adulterated CAO was 100 %, but there were misclassifications among different adulterated CAOs. The deep learning models outperformed chemometrics methods in quantitative prediction of adulteration level, with R2P, RMSEP, and RPD of the optimal ConvLSTM model achieved 0.999, 0.9 % and 31.5, respectively. The classifiers and models developed in this study based on deep learning have wide applicability and reliability, and provide a fast and accurate method for adulteration detection in CAO.

引用

页数：8