Zhu Jiaji, Jiang Xin, Rong Yawen, Wei Wenya, Wu Shengde, Jiao Tianhui, Chen Quansheng
School of Electrical Engineering, Yancheng Institute of Technology, Yancheng 224051, PR China.
School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, PR China.
Food Chem. 2023 Jul 15;414:135705. doi: 10.1016/j.foodchem.2023.135705. Epub 2023 Feb 15.
Surface-enhanced Raman spectroscopy (SERS) and deep learning models were adopted for detecting zearalenone (ZEN) in corn oil. First, gold nanorods were synthesized as a SERS substrate. Second, the collected SERS spectra were augmented to improve the generalization ability of regression models. Third, five regression models, including partial least squares regression (PLSR), random forest regression (RFR), Gaussian progress regression (GPR), one-dimensional convolutional neural networks (1D CNN), and two-dimensional convolutional neural networks (2D CNN), were developed. The results showed that 1D CNN and 2D CNN models possessed the best prediction performance, i.e., determination of prediction set (R) = 0.9863 and 0.9872, root mean squared error of prediction set (RMSEP) = 0.2267 and 0.2341, ratio of performance to deviation (RPD) = 6.548 and 6.827, limit of detection (LOD) = 6.81 × 10 and 7.24 × 10 μg/mL. Therefore, the proposed method offers an ultrasensitive and effective strategy for detecting ZEN in corn oil.
采用表面增强拉曼光谱（SERS）和深度学习模型检测玉米油中的玉米赤霉烯酮（ZEN）。首先，合成金纳米棒作为SERS基底。其次，对收集到的SERS光谱进行增强，以提高回归模型的泛化能力。第三，开发了五个回归模型，包括偏最小二乘回归（PLSR）、随机森林回归（RFR）、高斯过程回归（GPR）、一维卷积神经网络（1D CNN）和二维卷积神经网络（2D CNN）。结果表明，1D CNN和2D CNN模型具有最佳的预测性能，即预测集的决定系数（R）分别为0.9863和0.9872，预测集的均方根误差（RMSEP）分别为0.2267和0.2341，性能与偏差比（RPD）分别为6.548和6.827，检测限（LOD）分别为6.81×10和7.24×10μg/mL。因此，该方法为检测玉米油中的ZEN提供了一种超灵敏且有效的策略。
