红外光谱结合核隐变量正交投影法判别掺杂牛奶

杨延荣1; 杨仁杰1; 张志勇1; 董桂梅1; 杨士春2

doi:10.3788/OPE.20132110.2549

您当前的位置：

首页 >

文章列表页 >

红外光谱结合核隐变量正交投影法判别掺杂牛奶

现代应用光学 | 更新时间：2020-08-12

- 红外光谱结合核隐变量正交投影法判别掺杂牛奶
- Discrimination of Adulterated Milk Based on Infrared Spectroscopy and K-OPLS
- 光学精密工程 2013年21卷第10期页码：2549-2556
- 作者机构：
  
  1. 天津农学院农业分析测试中心天津,300384
  2. 天津农学院机电工程系天津,300384
- 作者简介：
- 基金信息：
  
  国家自然科学青年基金()
- DOI：10.3788/OPE.20132110.2549
  中图分类号： O657.33
- 收稿日期：2013-04-22，
  
  修回日期：2013-06-08，
  
  网络出版日期：2012-10-19，
  
  纸质出版日期：2013-10-15
- 稿件说明：
移动端阅览
杨延荣杨仁杰张志勇董桂梅杨士春. 红外光谱结合核隐变量正交投影法判别掺杂牛奶[J]. 光学精密工程, 2013,21(10): 2549-2556

YANG Yan-rong YANG Ren-jie ZHANG Zhi-yong DONG Gui-mei YANG Shi-chun. Discrimination of Adulterated Milk Based on Infrared Spectroscopy and K-OPLS[J]. Editorial Office of Optics and Precision Engineering, 2013,21(10): 2549-2556
杨延荣杨仁杰张志勇董桂梅杨士春. 红外光谱结合核隐变量正交投影法判别掺杂牛奶[J]. 光学精密工程, 2013,21(10): 2549-2556 DOI： 10.3788/OPE.20132110.2549.

YANG Yan-rong YANG Ren-jie ZHANG Zhi-yong DONG Gui-mei YANG Shi-chun. Discrimination of Adulterated Milk Based on Infrared Spectroscopy and K-OPLS[J]. Editorial Office of Optics and Precision Engineering, 2013,21(10): 2549-2556 DOI： 10.3788/OPE.20132110.2549.

摘要

为了快速、准确地检测掺杂牛奶，采用基于核隐变量正交投影（K-OPLS）法分析了掺杂牛奶的光谱。选用高斯函数作为核函数，内部交叉验证均方根（RMSECV）最小值作为评价指标，优选了核函数中的核宽度以及Y正交成分数。配置含四环素牛奶（0.01~0.3 gL-1）、三聚氰胺牛奶（0.01~0.3 gL-1）和葡萄糖牛奶（0.01~0.3 gL-1）各36个，采集纯牛奶及掺杂牛奶样品的红外光谱，采用K-OPLS建立各掺杂牛奶与纯牛奶的判别模型。利用这些模型对未知样品进行判别，结果显示对掺杂四环素、三聚氰胺、葡萄糖牛奶的判别正确率分别为100%、100%、95.8%。建立了同时判别3种掺杂牛奶与纯牛奶的K-OPLS模型，该模型对未知样品的判别正确率为93.1%；同时，与偏最小二乘判别PLS-DA方法的预测结果进行了比较，结果表明：K-OPLS建模方法对于复杂的牛奶体系具有较好的预测能力。

Abstract

To detect adulterated milk rapidly and accurately

the discrimination models for adulterated milk were established based on the method of Kernel Orthogonal Projection to Latent Structure (K-OPLS). By using the Gaussian radial basis function as the kernel function and the minimum value of Root Mean Square Errors of Cross-validation (RMSECV)as an evaluation index

the width of the Gaussian kernel

the minimum value of the RMSECV

and the number of Y-orthogonal components (scalar) were selected in a optimization. 36 samples with different concentrations of tetracycline (0.01-0.3 gL-1)

melamine (0.01-0.3 gL-1) and glucose (0.01-0.3 gL-1) in milk were prepared

respectively. Then the infrared absorption spectra of all samples were measured. K-OPLS models for tetracycline-tainted milk

melamine-tainted milk and glucose-tainted milk were constructed. The results show that its classification accuracy for tetracycline-tainted milk

melamine-tainted milk and glucose-tainted milk are 100%

100%

95.8%

respectively. The K-OPLS model was used to classify the above three kinds of adulterated milk and pure milk and its classification accuracy for unknown samples is 93.1%. Compared with Partial Least Square Discriminant Analysis (PLS-DA)

K-OPLS methods show higher accuracy. The results indicate that the K-OPLS model has good prediction ability for complex milk systems.

关键词

Keywords

references

LISA J M, ALONA A, CHERNYSHOVA A H, et al.. Melamine detection in infant formula powder using near- and mid-infrared spectroscopy [J]. Agric. Food Chem., 2009, 57:3974-3980.[2]唐玉莲.近红外光谱在乳制品成分快速检测方面的应用研究[J]. 乳业科学与技术, 2009, 32(4):190-194.TANG Y L. Study on near infrared spectroscopy technique for composition detection of dairy production [J]. Journal of Dairy Science and Technology, 2009, 32(4):190-194. (in Chinese )[3]杨仁杰,刘蓉,徐可欣.二维相关光谱结合偏最小二乘法测定牛奶中的掺杂尿素[J]. 农业工程学报, 2012, 28(6):259-263.YANG R J, LIU R, XU K X. Detection of urea in milk using two-dimensional (2D) correlation spectroscopy and partial least square method [J].Transactions of the CSAE, 2012, 28(6):259-263. (in Chinese)[4]KASEMSUMARAN S, THANAPASE W, KIATSOONTHON A. Feasibility of near infrared spectroscopy to detect and to quantify adulterants in cow milk [J]. Analytical Sciences, 2007, 23(7):907-910.[5]杨仁杰,刘蓉,徐可欣.基于中红外光谱检测牛奶中掺杂尿素[J]. 光谱学与光谱分析, 2011, 31(9):2383-2385. YANG R J, LIU R, XU K X. Adulteration detection of urea in milk by mid-infrared spectroscopy [J]. Spectroscopy and Spectral Analysis, 2011, 31(9):2383-2385. (in Chinese)[6]LU C H, XING B R, HAO G, et al.. Rapid detection of melamine in milk powder by near infrared spectroscopy [J]. Near infrared Spectroscopy, 2009,17(2):59-67.[7]LEE S Y, ERDENE O G, JAEBUM C，et al.. Detection of melamine in powdered milk using surface-enhanced roman scattering with no pretreatment [J]. Analytical Letters, 2010, 43(14):2135-2141.[8]TRYGG J, WOLD S. Orthogonal projections to latent structures (O-PLS) [J]. Journal of Chemometrics，2002, 16(3):119-128. [9]BYLESJ M, RANTALAINEN M, CLOAREC O, et al.. OPLS discriminant analysis: combining the strengths of PLS-DA and SIMCA classification [J]. Journal of Chemometrics，2006, 20:341-351.[10]RANTALAINEN M, BYLESJ, CLOAREC O, et al.. Kernel-based orthogonal projections to latent structures (K-OPLS)[J]. Journal of Chemometrics, 2007, 21(7): 376-385.[11]陈敏，贺益君，王靖岱，等. 基于小波包分析和KOPLS集成方法在颗粒粒径分布检测中的应用[J].化工学报, 2010, 61(6):1349-1356.CHEN M, HE Y J, WANG J D, et al.. Integrated method of wavelet packet analysis and K-OPLS and its application in measurement of particle size distribution [J]. CIESC Journal, 2010, 61(6):1349-1356. (in Chinese)[12]BYLESJ M, RANTALAINEN M, NICHOLSON J K, et al.. K-OPLS package: kernel-based orthogonal projections to latent structures for prediction and interpretation in feature space [J]. BMC Bioinformatics, 2008, 9:106.[13]WESTAMAN E, WAHLUND L O, FOY C, et al.. Combining MRI and MRS to distinguish between Alzheimer's disease and healthy controls [J]. Journal of Alzheimer's Disease, 2012, 22(1):171-181. [14]MEHDI J H, HESHMATOLLAH E N, AKRAM K. Use of kernel orthogonal projection to latent structure in modeling of retention indices of pesticides[J]. QSAR Comb., 2009, 28(11-12):1432-1441.

浏览量

683

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

电域自适应中红外激光甲烷传感系统

用二维相关近红外谱和多维主成分分析判别掺杂牛奶

同步荧光光谱结合CARS变量优选预测猪肉中四环素残留含量

基于逆向蒙特卡洛的溶液葡萄糖浓度低相干测量