Non-destructive detection of dicyandiamide in infant formula powder using multi-spectral imaging coupled with chemometrics

作者：Liu, Changhong; Liu, Wei; Yang, Jianbo; Chen, Ying^*; Zheng, Lei^*

来源：Journal of the Science of Food and Agriculture, 2017, 97(7): 2094-2099.

DOI：10.1002/jsfa.8014

• dicyandiamide
• infant formula
• multi-spectral imaging
• non-destructive detection
• chemometrics

BACKGROUNDDicyandiamide (DCD) contamination of milk and milk products has become an urgent and broadly recognised topic as a result of several food safety scares. This study investigated the potential of using multi-spectral imaging (405-970nm) coupled with chemometrics for detection of DCD in infant formula powder. Partial least squares (PLS), least squares-support vector machines (LS-SVM), and back-propagation neural network (BPNN) were applied to develop quantitative models. @@@ RESULTSCompared with PLS and LS-SVM, BPNN considerably improved the prediction performance with coefficient of determination in prediction (RP2)=0.935 and 0.873, residual predictive deviation (RPD)=3.777 and 3.060 for brand 1 and brand 2 of infant formula powders, respectively. Besides, multi-spectral imaging was able to differentiate unadulterated infant formula powder from samples containing 0.01% DCD with no misclassification using BPNN model. @@@ CONCLUSIONThe study demonstrated that multi-spectral imaging combined with chemometrics enables rapid and non-destructive detection of DCD in infant formula powder.

• 出版日期2017-5
• 单位合肥学院; 合肥工业大学; 安徽省农业科学院; 中国检验检疫科学研究院