1. School of Science，Jiangnan University，Wuxi 214122，China 2. Jiangsu Provincial Research Center of Light Industrial Optoelectronic Engineering and Technology，Wuxi 214000，China
Abstract：The feature compression algorithm which was reformed from the original Moment method was used for the pre-processing of the fluorescence spectral data, then combined the data and the Weighted Least Squares Support Vector Machine(WLS-SVM) algorithm to establish a robust regression model, which is used for forecasting the purity of edible pigment powder. In this paper, brilliant blue and ponceau 4R served as an example to discuss the method of forecasting effect of edible pigment powder purity. The emission fluorescence spectra of two edible pigment at the optimal excitation wavelength were measured by FLS920 fluorescence spectrometer. The compression and transformation of the fluorescence spectral data was acquired by the feature compression algorithm reformed from the Original Moment method. On the one hand the feature compression algorithm shortened the operation time, on the other hand it improved the prediction accuracy of the model. Then, the concentration prediction model was established after inputting the fluorescence spectral data pre-processed into the Weighted Least Squares Support Vector Machine. The model gave anastomotic predicted spectral data with the actual experiments of the brilliant blue and ponceau 4R, and the average coefficient of determination in the half peak width was 0.700 and 0.930 respectively. There was a good linear relationship between the predicted and the nominal concentration of the brilliant blue and ponceau 4R, and the correlation coefficients were 0.997 and 0.992 respectively. It can be concluded that, the predicted concentration of the brilliant blue and ponceau 4R powder were got the results of 61.0% and 72.3% respectively.
Key words：Spectroscopy;Synthetic edible pigment;Soft measurement of purity;Weighted least squares support vector machine
[1] CHEN Guo-qing(陈国庆). Jiangnan University Doctoral Dissertation(江南大学博士论文), 2010：23. [2] LI Run, CHEN Guo-qing, et al(李 润，陈国庆，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014，34(1)：111. [3] Li W J, Zhou X, Tong S S, et al. Talanta, 2013，(105)：386. [4] NING Shang-yong，GAO-Jie, et al(宁尚勇, 高 洁，等). Chinese Journal of Analysis Laboratory(分析试验室), 2008，(4)：72. [5] ZHANG Yu-lin, MA Jing-yuan, et al(张予林, 马静远，等). Journal of Northwest A & F University·Natural Science Edition(西北农林科技大学学报·自然科学版), 2011，(1)：186. [6] ZHANG Wan, WANG Tan, et al(张 婉, 王 覃，等). Food Science(食品科学), 2011，(4)：177. [7] Del Giovine L, Bocca A P. Food Control, 2003，14(3)：131. [8] WANG Yu-tian, XU Jing, et al(王玉田, 徐 婧，等). Chinese Journal of Lasers(中国激光), 2014，41(12): 1215002. [9] LIU Jing, LIU Wen-qing, et al(刘 晶, 刘文清，等). Acta Optica Sinica(光学学报), 2013，33(9): 0930001. [10] SONG Xin, JI Shuang-li, et al(宋 新, 纪双利, 等). Chinese Journal of Food Hygiene(中国食品卫生杂志), 2009，(5)：422. [11] CHEN Guo-qing(陈国庆). Jiangnan University Doctoral Dissertation(江南大学博士论文), 2010: 32. [12] Pell R J. Chemometrics and Intelligent Laboratory Systems, 2000，(52)：87. [13] Daszykowski M, Kaczmarek K, Vander Heyden Y, et al. Chemometrics and Intelligent Laboratory Systems, 2007，85(2)：203. [14] Mller S F, von Frese J, Bro R. Journal of Chemometrics, 2005，19(10)：549. [15] Kruger U, Zhou Y, Wang X, et al. Journal of Chemometrics, 2008，22(1)：1. [16] Suykens J A K, Van Gestel T, De Brabanter J, et al. Least Squares Support Vector Machines. Singapore：World Scientific, 2002. 149. [17] Suykens J A K, De Brabanter J, Lukas L, et al. Neurocomputing, 2002，48(1)：85. [18] Suykens J A K, Vandewalle J. Neural Processing Letters, 1999，9(3)：293. [19] Shim J, Hwang C, Nau S. Advances in Natural Computation, 2006. 157. [20] De Brabanter K, Karsmakers P, Ojeda F, et al. LS-SVMlab Toolbox User’s Guide. ESAT-SISTA Technical Report 10-146, 2010: 33. [21] SHANG Li-ping, YANG Ren-jie(尚丽平, 杨仁杰). Site Fluorescence Spectrum Technology and Application(现场荧光光谱技术及其应用). Beijing：Science Press(北京：科学出版社), 2009，1(5)：217.
