同步荧光光谱技术结合支持向量机对掺杂牛奶智能判别研究

doi:10.3964/j.issn.1000-0593(2024)09-2428-06

Abstract
References
Related Citation (15)

Download: PDF (4653 KB)
Export: BibTeX | EndNote (RIS)

Abstract Milk is favored due to its high nutritional value and consumption rate. Authenticity is a common concern for value assessment. Recently, non-invasive and rapid identification methods have been preferred for the dairy industry. This work proposed a quick method using synchronous fluorescence (SF) spectroscopy and a support vector machine (SVM) for the identification of raw milk. With this aim, SF spectra of milk were recorded between 220 and 600 nm excitation range with Δλ of 10 to 180 nm, in steps of 10 nm. All the milk showed the same fluorescence excitation at band position 280 nm, which corresponded to tryptophan. However, the fluorescence intensity of pure milk at this location was significantly higher than that of the two types of milk powder, and skimmed milk powder was stronger than whole milk powder. It indicated that the same main components were in milk. However, there were differences in their concentrations by different treatment methods. Two types of reconstituted formula milk were differentiated based on intensity variations at wavelengths 350~400 and 450~500 nm. The excitation at these wavelength positions corresponds to vitamin A and carotenoids. At these bands, the skimmed milk powder had a stronger fluorescence intensity in the corresponding region than whole milk powder, mainly due to the scattering of fatty substances, which enhanced the fluorescence intensity. Parallel factor analysis (PARAFAC) was found to reduce three-dimensional SF spectroscopy to two-dimensional data, resulting in a better understanding of the characteristics of dairy products. When the suitable components were6, the maximum load value was at Δλ with 40 nm, where the difference in sample information was more significant. Then, the Δλ with 40 nm and the value of contaminated dairy products as input data were used to classify and identify adulterated milk for the support vector machine (SVM) classifier. The three SVM methods were the genetic algorithm for support vector machine (Ga-SVM), particle swarm optimization support vector machine (Pso-SVM), and grid search algorithm (Grid-SVM). The results showed that the optimal classification accuracy for the Grid-SVM mode training set, test set, and cross-validation (CV) accuracy were 100.00%, 100%, and 98.91%, respectively, with a model running time of only 6.724 seconds. The study demonstrated that SF spectroscopy with PARAFAC and SVM methods is a promising tool and can potentially become a rapid and nondestructive analytical technique for identification of adulteration milk.

Key words：Fluorescence spectroscopy; PARAFAC algorithm; Adulteration milk; Support vector machine

Received: 2023-05-31 Accepted: 2024-01-17

ZTFLH:

O433.4

Corresponding Authors: SUN Yan-hui E-mail: 1647608982@qq.com

Cite this article:

ZHANG Wei-wei,QU Yi,WANG Qiang, et al. Research on the Synchronous Fluorescence Spectroscopy Combined With Support Vector Machines for Intelligent Discrimination of Milk Adulteration[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(09): 2428-2433.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2024)09-2428-06 OR https://www.gpxygpfx.com/EN/Y2024/V44/I09/2428

[1] Handford C E, Campbell K, Elliott C T. Comprehensive Reviews in Food Science and Food Safety, 2016，(15): 130.
[2] Moncayo S, Manzoor S, Rosales J D, et al. Food Chemistry, 2017，(232): 322.
[3] Mayer H K. International Dairy Journal, 2005, 15(6): 595.
[4] Choopan R, Thanakiatkrai P, Kitpipit T. Forensic Science International: Genetics Supplement Series, 2017，(6): 214.
[5] Gobbetti M, Morea M, Baruzzi F, et al. International Dairy Journal, 2002, 12(6)：511.
[6] Alvarado U, Zamora A, Arango O, et al. Journal of Food Engineering, 2022, 318: 110869.
[7] Barreto M, Braga R, Lemos S, et al. Food Chemistry, 2021，(364): 130407.
[8] Fragkoulis N, Samartzis P C, Velegrakis M. International Dairy Journal, 2021(123): 105181.
[9] Patra D, Mishra A K. Trends in Analytical Chemistry, 2002, 21(12): 787.
[10] Velioglu S D, Ercioglu E, Boyaci I H. Journal of Dairy Research, 2017, 84(2): 214.
[11] Genis D O, Sezer B, Bilge G, et al. Food Control, 2020，(108): 1.
[12] Birlouez-AragonI, Sabat P, Gouti N. International Dairy Journal, 2002, 12(1): 59.
[13] Bro R. Chemometrics and Intelligent Laboratory Systems, 1997, 38(2): 149.
[14] LI Xiang-yu, LI Liang-xing, WANG Wen-jie, et al（李翔宇, 李良星, 王闻婕, 等）. Journal of Engineering Thermophysics（工程热物理学报）, 2022, 43(11): 2957.
[15] Hou Dongyan, Hui Ruihua. Analytical Laboratory, 2001, 20(5): 88.
[16] Purna G S, Prow L, Metzger L. Journal of Dairy Science, 2005, 88(2): 470.
[17] GU Chun-feng, LAN Xiu-feng, YU Yin-shan, et al（顾春峰, 兰秀风, 于银山, 等）. Acta Photonica Sinica（光子学报）, 2012, 41(1): 107.
[18] Ullah R, Khan S, Ali H, et al. PLOS ONE, 2017, 12(5): e0178055.
[19] Skjervold O P, Taylor G R, Wold P J, et al. Journal of Food Science, 2003, 68(4): 1161.
[20] Daniel T, Jessica S, Nicolas D, et al. The American Journal of Clinical Nutrition, 2009, 90(3): 838.
[21] GU Chun-feng, LAN Xiu-feng, YU Yin-shan, et al（顾春峰，兰秀风，于银山，等）. Laser & Optoelectronics Progress（激光与光电子学进展）, 2012, 49(3): 130.
[22] YIN Wen-zhi, WANG Ting-yu, ZHU Tuo, et al（殷文志, 王婷钰, 朱拓, 等）. Spectroscopy and Spectral Analysis （光谱学与光谱分析）, 2021, 41(2): 535.
[23] Lv B, Xing M, Zhao C, et al. Chemosphere, 2014, 117(1): 216.
[24] Stedmon C A, Bro R. Limnology and Oceanography: Methods, 2008, 6(11): 572.