School of Food and Biological Engineering, Hefei University of Technology, Hefei 230009, China; Intelligent Control and Compute Vision Lab, Hefei University, Hefei 230601, China.
School of Food and Biological Engineering, Hefei University of Technology, Hefei 230009, China.
Food Chem. 2019 Sep 30;293:213-219. doi: 10.1016/j.foodchem.2019.04.081. Epub 2019 Apr 24.
Soybean oil is often contaminated by aflatoxin B (AFB) which is regarded as a class I carcinogen. The feasibility of rapid determination of AFB in soybean oil with terahertz spectroscopy was examined. t-SNE, as the pre-treatment method was used to get the best features and combined with different chemometrics including least squares-support vector machines (LS-SVM), back propagation neural network (BPNN), random forest (RF) and partial least squares (PLS) to find the best determination model. The excellent prediction results could be obtained using BPNN combined with t-SNE with correlation the coefficient of prediction (R) was 0.9948 and the root-mean-square error of prediction (RMSEP) was 0.7124 µg/kg. Besides, THz spectroscopy was proved to be feasible to detect AFB at 1 µg/kg in soybean oil (over 90% accuracy). It was concluded that THz spectroscopy together with chemometrics would be a promising technique for rapid determination of the AFB concentration in soybean oil.
大豆油通常会受到黄曲霉毒素 B（AFB）的污染，而 AFB 被视为一类致癌物质。本研究旨在探讨太赫兹光谱技术快速测定大豆油中 AFB 的可行性。实验采用 t-SNE 作为预处理方法，以获取最佳特征，并结合不同的化学计量学方法，包括最小二乘支持向量机（LS-SVM）、反向传播神经网络（BPNN）、随机森林（RF）和偏最小二乘（PLS），以找到最佳的测定模型。结果表明，BPNN 与 t-SNE 结合可以得到优秀的预测结果，预测相关系数（R）为 0.9948，预测均方根误差（RMSEP）为 0.7124μg/kg。此外，太赫兹光谱技术可以检测大豆油中 1μg/kg 的 AFB（准确率超过 90%）。综上所述，太赫兹光谱技术结合化学计量学方法有望成为快速测定大豆油中 AFB 浓度的一种有前途的技术。
