Scientific journal
Journal of Food and Nutrition Research
Summary No. 3 / 2017
Liu, Y. – Zhou, S. – Han, W. – Li, C. – Huang, K. – Liu, W.
Detection of adulteration by hydrolysed leather protein in infant formula based on least squares support vector machine and near-infrared spectroscopy
Journal of Food and Nutrition Research, 56, 2017, No. 3, s. 283-291
Songbin Zhou, Guangdong Key Laboratory of Modern Control Technology; Guangdong Public Laboratory of Modern Control and Manufacturing Technology; Guangdong Institute of Intelligent Manufacturing; Xianliezhong Road No. 100, 510070 Gangzhou, China. E-mail: zhousongbin728@126.com, tel.: +8620 87685580
Received 29 December 2016; 1st revised 13 June 2017; 2nd revised 12 July 2017; accepted 31 July 2017; published online 16 September 2017
Summary: Near-infrared (NIR) spectroscopy and least squares support vector machine (LS-SVM) were applied to detect hydrolysed leather protein (HLP) adulteration in infant formula. In the classification approach, principal components (PCs) extracted by principal component analysis (PCA) were used as the inputs of the LS-SVM class model. The correct classification rates of authentic samples and adulterated samples in validation set were 96.7 % and 95.6 %, respectively. In the regression approach, PCs extracted by PCA were also utilized as inputs of LS-SVM to develop PCs-LS-SVM regression models. The optimal PCs-LS-SVM model was obtained with 4 PCs and the root mean squared error of calibration and prediction were 1.02 g·kg-1 and 1.46 g·kg-1, respectively. Moreover, sensitive wavelengths (SWs) were selected according to the regression coefficients obtained by partial least squares regression model, and utilized as the input data of LS-SVM to develop SWs-LS-SVM regression models. The optimal SWs-LS-SVM model was obtained with 19 SWs and the root mean squared error of calibration and prediction were 0.64 g·kg-1 and 1.18 g·kg-1, respectively. The results demonstrated that NIR spectroscopy combined with LS-SVM could be applied as a fast, simple and non-destructive way to detect HLP adulteration in infant formula.
Keywords: hydrolyzed leather protein; infant formula adulteration; least-squares support vector machine; near-infrared spectroscopy
Download:
(pdf, 645.21 Kb, 2315x)