Classification of adulterated milk by two-dimensional correlation near-infrared spectroscopy and multi-way principal component analysis

YANG Ren-jie; LIU Rong; YANG Yan-rong; ZHANG Wei-yu

doi:10.3788/OPE.20142209.2352

您当前的位置：

首页 >

文章列表页 >

Classification of adulterated milk by two-dimensional correlation near-infrared spectroscopy and multi-way principal component analysis

更新时间：2020-08-13

- Classification of adulterated milk by two-dimensional correlation near-infrared spectroscopy and multi-way principal component analysis
- Optics and Precision Engineering Vol. 22, Issue 9, Pages: 2352-2358(2014)
- 作者机构：
  
  1. 天津大学精密测试技术及仪器国家重点实验室天津,300072
  2. 天津农学院工程技术系天津,300384
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20142209.2352
  CLC： O657.33
- Received：05 November 2013，
  
  Revised：31 December 2013，
  
  Published：25 September 2014
- 稿件说明：
移动端阅览
杨仁杰, 刘蓉, 杨延荣等. 用二维相关近红外谱和多维主成分分析判别掺杂牛奶[J]. 光学精密工程, 2014,22(9): 2352-2358

YANG Ren-jie, LIU Rong, YANG Yan-rong etc. Classification of adulterated milk by two-dimensional correlation near-infrared spectroscopy and multi-way principal component analysis[J]. Editorial Office of Optics and Precision Engineering, 2014,22(9): 2352-2358
杨仁杰, 刘蓉, 杨延荣等. 用二维相关近红外谱和多维主成分分析判别掺杂牛奶[J]. 光学精密工程, 2014,22(9): 2352-2358 DOI： 10.3788/OPE.20142209.2352.

YANG Ren-jie, LIU Rong, YANG Yan-rong etc. Classification of adulterated milk by two-dimensional correlation near-infrared spectroscopy and multi-way principal component analysis[J]. Editorial Office of Optics and Precision Engineering, 2014,22(9): 2352-2358 DOI： 10.3788/OPE.20142209.2352.

摘要

为了有效地提取牛奶中微量的掺杂物特征信息，提出了基于二维相关近红外光谱多维主成分分析（MPCA）和最小二乘支持向量机（LS-SVM）判别牛奶掺杂物的方法。首先，采集纯牛奶、掺杂尿素牛奶和掺杂三聚氰胺牛奶的一维近红外谱，并对其进行相关计算，构建各样品的二维相关近红外谱。然后，采用多维主成分分析法分析二维相关谱矩阵，压缩数据，提取相关谱的得分矩阵。最后，将提取的得分矩阵输入最小二乘支持向量机，分别建立掺杂尿素牛奶、掺杂三聚氰胺牛奶及两种掺杂牛奶与纯牛奶的LS-SVM判别模型。用所建模型对测试集未知样品进行了判别，结果显示其判别正确率分别为92.3%，96.2%，92.3%。研究结果表明：所提出的方法不仅有效提取了牛奶中掺杂物的特征信息，而且缩短了建模所需时间，取得了较好的判别效果。

Abstract

To extract effectively characteristic information of adulterants in milk

the classification models for adulterated milk were established using two-dimensional(2D) correlation near-infrared spectra combining a Multi-way Principal Component Analysis(MPCA) with Least Square Support Vector Machines(LS-SVM). First

one-dimensional near-infrared spectra of pure milk and adulterated milk samples were collected and the synchronous 2D correlation spectra of all samples were calculated. Then

the MPCA was used to reduce dimension by extracting score matrix of 2D correlation data set. Finally

LS-SVM models for urea-tainted milk

melamine-tainted milk

and the above two kinds of adulterated milk were constructed by using score matrix extracted from 2D correlation spectra as the input variables. These models were used to discriminate the known samples in the test set and the results show that the classification accuracy rates of unknown samples are 92.3%

96.2%

92.3%

respectively. It demonstrates that the proposed method not only extracts effectively feature information of adulterants in milk

but also reduces the input dimension of LS-SVM and computational time. It realizes a better classification of adulterated milk and pure milk.

关键词

Keywords

references

杨延荣,杨仁杰,张志勇,等. 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):77-84. YANG Y R, YANG R J, ZHANG ZH Y, et al.. Discrimination of adulterated milk based on infrared spectroscopy and K-OPLS [J]. Opt.Precision Eng., 2013, 21(10):77-84. (in Chinese)

NODA I. Advances in two-dimensional correlation spectroscopy [J]. Vibrational Spectroscopy, 2004, 36(2):143-165.

杨仁杰. 基于二维相关谱掺杂牛奶检测方法研究[D]. 天津:天津大学,2013. YANG R J. Research on the detection of adulterated milk based on 2D correlation spectroscopy [D]. Tianjin:Tianjin University, 2013. (in Chinese)

SUN S Q, ZHOU Q, CHEN J B. Infrared Spectroscopy for Complex Mixtures:Applications in Food and Traditional Chinese Medicine [M]. Beijing: Chemical Industry Press, 2011.

WANG Y, XU C H, WANG P, et al.. Analysis and identification of different animal horns by a three-stage infrared spectroscopy [J]. Spectrochim Acta Part A:Molecular and Biomolecular Spectroscopy, 2011, 83(1):265-270.

ZHANG Y L, CHEN J B, LEI Y, et al.. Discrimination of different red wine by Fourier-transform infrared and two-dimensional infrared correlation spectroscopy [J]. Journal of Molecular Structure, 2010, 974(1-3):144-150.

YANG R J, LIU R, XU K X. Detection of adulterated milk using two-dimensional correlation spectroscopy combined with multi-way partial least squares[J]. Food Bioscience, 2013, 2:61-67.

杨仁杰, 刘蓉, 徐可欣, 等. 二维相关近红外谱结合NPLS-DA判别掺杂牛奶的研究[J]. 光子学报, 2013, 42(5):580-585. YANG R J, LIU R, XU K X, et al..Discrimination of adulterated milk using NPLS-DA combined with two-dimensional correlation near-infrared spectroscopy [J]. Acta Photonica Sinica, 2013, 42(5):580-585. (in Chinese)

YANG R J, LIU R, XU K X, et al.. Discrimination of adulterated milk based on two-dimensional correlation spectroscopy (2D-COS) combined with kernel orthogonal projection to latent structure (K-OPLS) [J]. Applied Spectroscopy. 67(12):1363-1367.

YANG R J, LIU R, XU K X, et al.. Classification of adulterated milk with the parameterization of 2D correlation spectroscopy and least squares support vector machines [J]. Anal. Methods, 2013, 5:5949-5953.

苗静,曹玉珍,杨仁杰,等. 基于二维相关近红外谱参数化及BP神经网络的掺杂牛奶鉴别[J]. 光谱学与光谱分析, 2013, 33(11):3032-3035. MIAO J, CAO Y ZH, YANG R J, et al.. Identification of adulterated milk based on two-dimensional correlation near-infrared spectra parameterization and BP neural network[J]. Spectroscopy and Spectral Analysis, 2013, 33(11):3032-3035. (in Chinese)

GELADI P, ISAKSSON H, LINDQVIST L, et al.. Principal component analysis of multivariate image [J]. Chemometrics and Intelligent Laboratory Systems, 1989, 5(3):209-220.

SMILDE A K, DOORNBOS D A. Three-way methods for the calibration of chromatographic systems:comparing PARAFAC and three-way PLS[J]. Journal of Chemometrics,1991, 5:345-360.

CHEN J B, ZHOU Q, NODA I, et al.. Quantitative classification of two-dimensional correlation spectra [J]. Applied Spectroscopy, 2009, 63(8):920-925.

VILLEZ K, RUIZ M, SIN G, et al.. Combining multiway principal component analysis (MPCA) and clustering for efficient data mining of historical data sets of SBR process [J]. Water Science and Technology, 2008, 57(10):1659-1666.

虞科, 程翼宇. 一种基于最小二乘支持向量机算法的近红外光谱判别分析方法[J]. 分析化学, 2006, 34(4):561-564. YU K, CHENG Y Y. Discriminating the genuineness of Chinese medicines with least squares support machines [J]. Chinese Journal of Anaytica Chemistry, 2006, 34(4):561-564. (in Chinese)

SUYKENS J A K, VANDEWALLE J. Least squares support vector machine classifiers [J]. Neural Process. Lett., 1999, 9(3):293-300.

LASKO T A. BHAGWAT J G, ZOU K H. The use of receiver operating characteristic curves in biomedical informatics [J]. Journal of Biomedical Informatics, 2005, 38(5):404-415.

Views

551

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Discrimination of Adulterated Milk Based on Infrared Spectroscopy and K-OPLS

Related Author

YANG Yan-rong1

YANG Ren-jie1

ZHANG Zhi-yong1

DONG Gui-mei1

YANG Shi-chun2

Related Institution

Department of Electromechanical Engineering, Tianjin Agricultural University

Laboratory of Agricultural Analysis, Tianjin Agricultural University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰