Generic models for rapid detection of vanillin and melamine adulterated in infant formulas from diverse brands based on near-infrared hyperspectral imaging,

Abstract Research has shown that near-infrared hyperspectral imaging (NIR HSI) is an effective rapid-detection tool for milk powder adulteration, but model generality under different adulteration conditions requires further study. Therefore, this study focused on developing generic models for the detection of vanillin and melamine in infant formulas from diverse brands. Three pretreatment algorithms were applied successively to spectrum of each pixel in hyperspectral images. Minimum noise fraction was applied to eliminate interference from brand diversity and extract adulterant information. Partial least squares discriminant analysis (PLSDA) was used to develop a classification model to identify vanillin-rich pixels. The PLSDA model, developed with three optimal wavelengths selected by the successive projections algorithm (SPA), detected vanillin at concentrations as low as 0.01%. Partial least squares regression (PLSR) was applied to establish a quantitative model for melamine. The PLSR model, established with six optimal wavelengths selected by the competitive adaptive reweighting algorithm (CARS), showed excellent predictive capabilities, with a limit of detection of 0.5%. A visual prediction map clearly showed the location of vanillin-rich pixels and melamine content variations spatially. The proposed generic practical method would greatly facilitate the application and promotion of NIR HSI technology in quality inspection for the milk powder market and manufacturers.

[1]  D. Britti,et al.  Detection of buffalo milk adulteration with cow milk by capillary electrophoresis analysis. , 2019, Journal of dairy science.

[2]  Santosh Lohumi,et al.  Detection of melamine in milk powder using MCT-based short-wave infrared hyperspectral imaging system , 2018, Food additives & contaminants. Part A, Chemistry, analysis, control, exposure & risk assessment.

[3]  M. Samadi,et al.  Homogenous liquid–liquid extraction followed by dispersive liquid–liquid microextraction for the extraction of some antibiotics from milk samples before their determination by HPLC , 2020 .

[4]  Hongdong Li,et al.  Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. , 2009, Analytica chimica acta.

[5]  Min Huang,et al.  Quantitative analysis of melamine in milk powders using near-infrared hyperspectral imaging and band ratio , 2016 .

[6]  Wei Yu,et al.  An evaluation of hyperspectral imaging for characterising milk powders , 2018 .

[7]  Jun-Hu Cheng,et al.  Non-destructive Detection and Screening of Non-uniformity in Microwave Sterilization Using Hyperspectral Imaging Analysis , 2018, Food Analytical Methods.

[8]  D. Ballabio,et al.  Classification tools in chemistry. Part 1: linear models. PLS-DA , 2013 .

[9]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[10]  R. Poppi,et al.  Use of NIR hyperspectral imaging and multivariate curve resolution (MCR) for detection and quantification of adulterants in milk powder , 2017 .

[11]  Lei Zhu,et al.  A new MNF-BM4D denoising algorithm based on guided filtering for hyperspectral images. , 2019, ISA transactions.

[12]  Yong He,et al.  Application of Near-Infrared Hyperspectral Imaging with Machine Learning Methods to Identify Geographical Origins of Dry Narrow-Leaved Oleaster (Elaeagnus angustifolia) Fruits , 2019, Foods.

[13]  Xufeng Wang,et al.  Feasibility of NIR spectroscopy detection of moisture content in coco-peat substrate based on the optimization characteristic variables. , 2020, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[14]  H. Karimi-Maleh,et al.  Voltammetric food analytical sensor for determining vanillin based on amplified NiFe2O4 nanoparticle/ionic liquid sensor , 2020, Journal of Food Measurement and Characterization.

[15]  M. M. Reis,et al.  Identification of Cold Spots Using Non-Destructive Hyperspectral Imaging Technology in Model Food Processed by Coaxially Induced Microwave Pasteurization and Sterilization , 2020, Foods.

[16]  K. Kannan,et al.  Melamine and its derivatives in dog and cat urine: An exposure assessment study. , 2018, Environmental pollution.

[17]  Bingcong Xing,et al.  Rapid detection of saffron (Crocus sativus L.) Adulterated with lotus stamens and corn stigmas by near-infrared spectroscopy and chemometrics , 2020 .

[18]  M. Barker,et al.  Partial least squares for discrimination , 2003 .

[19]  X. Ni,et al.  Utilising near-infrared hyperspectral imaging to detect low-level peanut powder contamination of whole wheat flour , 2019, Biosystems Engineering.

[20]  Ji Ma,et al.  Prediction of monounsaturated and polyunsaturated fatty acids of various processed pork meats using improved hyperspectral imaging technique. , 2020, Food chemistry.

[21]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[22]  Xiaping Fu,et al.  Detection of melamine in milk powders using near-infrared hyperspectral imaging combined with regression coefficient of partial least square regression model. , 2016, Talanta.

[23]  Ming Li,et al.  Evaluation of an ELISA-based visualization microarray chip technique for the detection of veterinary antibiotics in milk , 2019 .

[24]  Rijun Gui,et al.  Ketjen black/ferrocene dual-doped MOFs and aptamer-coupling gold nanoparticles used as a novel ratiometric electrochemical aptasensor for vanillin detection. , 2019, Analytica chimica acta.

[25]  Lianru Gao,et al.  Optimized Kernel Minimum Noise Fraction Transformation for Hyperspectral Image Classification , 2017, Remote. Sens..

[26]  M. Ghaedi,et al.  Column packing elimination in matrix solid phase dispersion by using water compatible magnetic molecularly imprinted polymer for recognition of melamine from milk samples. , 2019, Journal of chromatography. A.

[27]  Moon S. Kim,et al.  Detection of melamine in milk powders based on NIR hyperspectral imaging and spectral similarity analyses , 2014 .

[28]  Liguang Xu,et al.  Analytical methods and recent developments in the detection of melamine , 2010 .

[29]  Maria Luisa Amodio,et al.  Feasibility study for the surface prediction and mapping of phytonutrients in minimally processed rocket leaves (Diplotaxis tenuifolia) during storage by hyperspectral imaging , 2020, Comput. Electron. Agric..