Application of Kernel Orthogonal Projection to Latent Structure Discriminant Analysis in the Discrimination of Adulterated Milk
LIU Rong1, YANG Ren-jie1, 2, MIAO Jing1, XU Ke-xin1
1. State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China 2. Department of Electromechanical Engineering, Tianjin Agricultural University, Tianjin 300384, China
摘要： 运用核隐变量正交投影(kernel orthogonal projection to latent structure, KOPLS)方法，建立掺杂牛奶与纯牛奶的判别模型。分别配置含有三聚氰胺牛奶(0.01～3 g·L-1)和尿素牛奶(1～20 g·L-1)样品各40个，采集纯牛奶及掺杂牛奶样品的近红外光谱。选择4 200～4 800 cm-1为建模区间，采用KOPLS分别建立掺杂三聚氰胺、掺杂尿素、两种掺杂牛奶与纯牛奶的判别模型，并利用这些模型对未知样品进行判别。研究结果表明：与偏最小二乘判别(partial least squares discriminant analysis, PLS-DA)和隐变量正交投影判别(orthogonal projections to latent structures discriminant analysis, OPLS-DA)建模方法相比，KOPLS-DA具有更强的掺杂判别能力，对掺杂三聚氰胺、掺杂尿素牛奶和两种掺杂牛奶的判别正确率分别为95%，100%和97.5%。
关键词：核隐变量正交投影;掺杂牛奶;三聚氰胺;尿素;近红外光谱
Abstract：Based on the method of kernet Orthogonal Projection to Latent Structure Discriminant Analysis, discrimination models for adulterated milk were established in the present paper. Forty adulterated milk samples with melamine(0.01～3 g·L-1)and 40 adulterated milk samples with urea (1～20 g·L-1)were prepared, respectively. Then the near-infrared absorption spectra of all samples were measured. The spectra in the range of 4 200～4 800 cm-1 were selected to construct the KOPLS-DA models for milk adulterated with melamine, milk adulterated with urea and milk adulterated with both melamine and urea. The results showed that, compared with PLS-DA and OPLS-DA models, KOPLS-DA model had better discriminant ability for the adulterated milk, and its classification accuracy rate (CAR) for milk adulterated with melamine, milk adulterated with urea and milk adulterated with both melamine and urea were 95%, 100% and 97.5%, respectively.
[1] Yang Renjie, Liu Rong, Xu Kexin. Proc. of SPIE, 2012, 8229: 822918. [2] Cassoli L D, Sartori B, MachadoA P F. R. Bras. Zootec, 2011, 40(11): 2591. [3] Lu Chenghui, Xing Bingren, Hao Gang, et al. Near Infrared Spectroscopy, 2009, 17: 59. [4] YANG Ren-jie, LIU Rong, XU Ke-xin(杨仁杰，刘 蓉，徐可欣). Food Science(食品科学), 2012, 31(9): 2383;33(16): 120. [5] Mauer L J, Chernyshova A A, Hiatt A, et al. J. Agric. Food Chem., 2009, 57: 3974. [6] YANG Ren-jie, LIU Rong, XU Ke-xin(杨仁杰，刘 蓉，徐可欣). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2012, 28(6): 259. [7] Trygg J, Wold S. Journal of Chemometrics, 2002, 16: 119. [8] Bylesj M, Rantalainen M, Cloarec O, et al. Journal of Chemometrics, 2006, 20: 341. [9] Rantalainen M, Bylesj M, Cloarec O, et al. Journal of Chemometrics, 2007, 21(7): 376. [10] CHEN Min, HE Yi-jun, WANG Jing-dai, et al(陈 敏，贺益君，王靖岱, 等). CIESC Journal(化工学报), 2010, 61(6): 1349. [11] Bylesj M, Rantalainen M, Jeremy K N, et al. BMC Bioinformatics, 2008, 9: 106. [12] Westman E, Wahlund L O, Foy C, et al. Journal of Alzheimer’s Disease, 2012, 22(1): 171. [13] Mehdi J H, Heshmatollah E N, Akram K. QSAR Comb. Sci, 2009, 28(111-112): 1432.
