Abstract：Traditional analysis of food adulteration is more concentrated in the detection of specific known or suspected adulterants which may exist. However, due to the variety of adulteration and the emergence of new adulterants, the traditional detection methods have limitations. Currently，as an ideal substitute for fresh egg，the adulteration of egg powder is serious, but the problem is rarely studied both at home and abroad. In order to explore a rapid detection method of whole egg powder adulteration, this study attempted to use hyperspectral technology green and nondestructive in its advantages to detect the feasibility of whole egg powder with several adulterants. Different brands of egg powder were collected from different area and the common adulterants (starch, soy isolate protein, maltodextrin and mixture) were added in in proportion. After spectral acquisition, the region of interest (ROI) was extracted by ENVI and the mean spectra were extracted. Firstly, the support vector machines (SVM) models were founded to identify the adulteration and the Partial least squares (PLSR) model was used to establish the relationship between the full bands and adulteration concentration. The results showed that the correctness of the SVM model based on RBF kernel function was more than 90%, and the correlation coefficient between the actual value and the prediction value of the adulteration model based on PLSR was higher than 0.90. In order to simplify the model, the regression coefficient method (RC) and the successive projections algorithm (SPA) were used to extract the characteristic wavelengths, and the RC-PLSR model and SPA-PLSR were established according to the spectral data at the characteristic wavelength. The results showed that the simplified models still have good performance, indicating that the hyperspectral technique to detect adulteration of whole egg powder is feasible.
Key words：Whole egg powder adulteration; Hyperspectral technology; Support vector machine; Characteristic wavelength; Partial least square regression
[1] Caboni M F, Boselli E, Messia M C, et al. Food Chemistry, 2005, 92(2): 293.
[2] Li Y, Huang F, Xian R, et al. Food Analytical Methods, 2015, 8(8): 2150.
[3] Kamruzzaman M, Sun D W, Elmasry G, et al. Talanta, 2013, 103(2): 130.
[4] Wu D, Shi H, He Y, et al. Journal of Food Engineering, 2014, 119(3): 680.
[5] Xiong Z, Sun D W, Pu H, et al. LWT-Food Science and Technology, 2015, 60(2): 649.
[6] Xiong Z, Sun D W, Xie A, et al. Food Chemistry, 2015, 178: 339.
[7] Lohumi S, Lee S, Lee H, et al. Trends in Food Science & Technology, 2015, 46(1): 85.
[8] ZHANG Li-hua, HAO Li-hua, LI Shun-feng(张丽华, 郝莉花, 李顺峰). Science and Technology of Food Industry(食品工业科技), 2015, 36(23)：289.
[9] Elmasry G, Sun DW, Allen P. Food Research International, 2011, 44(9): 2624.
[10] Xiong Z, Sun DW, Dai Q, et al. Food Analytical Methods, 2015, 8(2): 380.
[11] Xiong Z, Sun D W, Zeng X A, et al. Journal of Food Engineering, 2014, 132(1): 1.
[12] LIN Sheng-liang, LIU Zhi(林升梁, 刘 志). Journal of Zhejiang University of Technology(浙江工业大学学报), 2007, 35(2): 163.
[13] Andersen C M, Bro R. Journal of Chemometrics, 2010, 24(11-12): 728.
