基于STM的三维荧光导数光谱法检测食品中黄曲霉素  

Utilizing 3-D first-order derivative fluorescence spectrometry to detect aflatoxin in foods based on STM

作　　者：杜树新[1] 蒋丹红[1] 

机构地区：[1]浙江大学宁波理工学院信息科学与工程分院,浙江宁波315100

出　　处：《光电子．激光》2014年第3期545-550,共6页Journal of Optoelectronics·Laser

基　　金：国家自然科学基金(60974111);国家"863计划"(2009AA04Z123)资助项目

摘　　要：基于支持张量机(STM)的三维荧光导数光谱定量分析方法,检测了食品中黄曲霉素。在计算三维荧光导数光谱时,将常规的、只适用于向量光谱数据的Savitzky-Golay方法扩展到由二阶张量描述的三维荧光光谱中。同时,应用了STM方法建立校正模型,对白酒和牛奶中的黄曲霉素进行了检测。在对白酒中的黄曲霉素检测中,复相关系数(CC)和预测误差均方根(RMSEP)分别为0.952 3和14.847 5,与常规的偏最小二乘(PLS)和支持向量机(SVM)方法相比,CC分别提高了2.40%和2.34%,RMSEP分别降低了8.92%和4.36%。在对牛奶中的黄曲霉素检测中,CC和RMSEP分别为0.996 5和5.448 9,与PLS和SVM的方法相比,RMSEP分别提高了0.40%和0.30%,RMSEP分别降低了18.31%和17.18%。检测结果表明,基于STM方法建立的校正模型要优于传统的SVM方法和PLS方法。Spectral quantitative analysis for three-dimensional first-order derivative fluorescence based on support tensor machine （STM） is proposed and applied to detect aflatoxin in foods in this paper. The conventional Savitzky-Golay polynomial smoothing and differentiation methods, only used for vector- based spectral analysis, are extended to three-dimensional fluorescence spectrometry represented by 2-or- der tensors. Because the three-dimensional first-order derivative spectrometry is represented as a 3-order tenor, support tensor machines （STMs） are used to build calibration model in order to improve the mod- el prediction accuracy. In the experiments for detecting aflatoxin in liquor, the correlation coefficient （CC） and root mean square error of prediction （RMSEP） are 0, 952 3 and 14. 847 5 ,respectively,and compared with partial least squares （ PLS ） and support vector machine （ SVM ） method , the CC is increased by 2.34% and 2.40% while RMSEP is reduced by 4.36% and 8. 92%,respectively. And in the experi- ments for detecting aflatoxin in rffllk,CC and RMSEP are 0. 996 5 and 5. 448 9 ,and the CC is increased by 2.34% and 2.40% while RMSEP is reduced by 4. 36% and 8.92% ,respectively with comparison to PLS and SVM. These experimental results show that the performance of calibration model used by STM is superior to that by SVM and PLS.

关 键 词：检测 导数光谱 三维荧光 支持张量机(STM) 黄曲霉素 

分 类 号：O657.37[理学—分析化学]