Deng Jihong, Jiang Hui, Chen Quansheng
School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, PR China.
School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, PR China.
Spectrochim Acta A Mol Biomol Spectrosc. 2022 Jul 5;275:121148. doi: 10.1016/j.saa.2022.121148. Epub 2022 Mar 15.
Aflatoxin B (AFB) is the most widely distributed, most toxic, and most harmful, and it is widely present in moldy grains. This study proposes a new method for quantitative and rapid determination of the AFB content in maize based on Raman spectroscopy. The Raman spectra of maize samples with different mildew degrees were collected by a portable laser Raman spectroscopy system. Three different spectral selection methods, which were bootstrapping soft shrinkage (BOSS), variable combination population analysis (VCPA) and competitive adaptive reweighted sampling (CARS), were applied to optimize the characteristic wavelength variables of the pretreated Raman spectra. The support vector machine (SVM) detection models based on different optimized characteristic wavelength variables were established, and the results of each detection model were compared. The results obtained showed that the performance of the SVM models established by optimized features was significantly better than the performance of the SVM model built by full-spectrum data. Among them, the SVM model based on the characteristic wavelength variables optimized by the CARS method had the best performance, and its root mean square error of prediction (RMSEP) was 3.5377 μg∙kg, the determination coefficient of prediction (R) was 0.9715, and the relative prediction deviation (RPD) was 5.8258. The overall results reveal that the rapid quantitative detection of the AFB in maize by Raman spectroscopy has a promising application prospect. In addition, the implementation of the characteristic wavelength optimization of Raman spectra in the model calibration process can effectively improve the detection accuracy of chemometric models.
黄曲霉毒素B（AFB）分布最广、毒性最强且危害最大，广泛存在于霉变谷物中。本研究提出了一种基于拉曼光谱的玉米中AFB含量定量快速测定新方法。采用便携式激光拉曼光谱系统采集不同霉变程度玉米样品的拉曼光谱。应用三种不同的光谱选择方法，即自助软收缩（BOSS）、变量组合总体分析（VCPA）和竞争性自适应重加权采样（CARS），对预处理后的拉曼光谱特征波长变量进行优化。建立基于不同优化特征波长变量的支持向量机（SVM）检测模型，并比较各检测模型的结果。结果表明，由优化特征建立的SVM模型性能明显优于由全光谱数据构建的SVM模型。其中，基于CARS方法优化特征波长变量的SVM模型性能最佳，其预测均方根误差（RMSEP）为3.5377μg∙kg，预测决定系数（R）为0.9715，相对预测偏差（RPD）为5.8258。总体结果表明，拉曼光谱法快速定量检测玉米中的AFB具有广阔的应用前景。此外，在模型校准过程中对拉曼光谱进行特征波长优化，可有效提高化学计量学模型的检测精度。
