基于近、中红外光谱数据融合掺假牛奶的判定

天津农学院学报 ›› 2017, Vol. 24 ›› Issue (4): 52-56.

基于近、中红外光谱数据融合掺假牛奶的判定

张海洋, 廖彩淇, 杨仁杰^通信作者, 鲍秀君, 王威, 靳皓, 张伟玉

天津农学院工程技术学院,天津 300384

收稿日期:2017-05-02 出版日期:2017-12-31 发布日期:2019-10-15
通讯作者: 杨仁杰（1978-）,男,山西运城人,副教授,博士,主要研究方向：光谱检测技术与应用。E-mail：rjyang1978@163.com。
作者简介:张海洋（1994-）,女,甘肃庆阳人,学士,研究方向：食品安全检测。E-mail：1754695019@qq.com。
基金资助:
天津农学院大学生创新创业训练计划项目“不同品牌牛奶对红外光谱判别模型影响及优化方法研究”（201610061011）; 天津市科技特派员项目“复杂掺伪食品体系特征光谱信息提取与检测方法研究”（16JCTPJC47500）; 国家自然科学青年基金“基于二维相关谱掺伪牛奶检测方法研究”（31201359）

Classification of Adulterated Milk Based on the Fused Near and Mid Infrared Spectroscopy

ZHANG Hai-yang, LIAO Cai-qi, YANG Ren-jie^{Corresponding Author}, BAO Xiu-jun, WANG Wei, JIN Hao, ZHANG Wei-yu

College of Engineering and Technology, Tianjin Agricultural University, Tianjin 300384,China

Received:2017-05-02 Online:2017-12-31 Published:2019-10-15

摘要/Abstract

摘要： 将近、中红外光谱数据进行融合,并结合偏最小二乘法建立了两个品牌掺杂牛奶的判别模型。分别准备伊利和蒙牛纯牛奶样品各40个、掺杂三聚氰胺牛奶样品各40个。室温下,采集所有样品的近红外透射光谱和中红外衰减全反射光谱。在融合近、中红外光谱数据的基础上,分别建立了伊利、蒙牛以及两品牌牛奶的判别模型,3个模型对预测集未知样品的判别正确率分别为96.2%、96.2%和94.2%。为了比较,分别建立了单一近红外光谱和中红外光谱的伊利、蒙牛以及两品牌牛奶的判别模型。研究结果表明：相对于单一的近红外光谱和中红外光谱,融合近、中红外光谱能减小不同牛奶品牌对模型预测性能的影响,可提供更好的分析结果。

关键词: 近红外光谱, 中红外光谱, 数据融合, 不同品牌牛奶, 判别分析, 三聚氰胺

Abstract: The models of two brands of adulterated milk were constructed based on the information fusion of near and mid infrared spectroscopy combined with partial least squares discriminant analysis（PLS-DA）. 40 Yili pure milk samples, 40 Mengniu pure milk samples, 40 Yili milk adulterated with melamine samples, and 40 Mengniu milk adulterated with melamine samples, were prepared respectively. Then, near infrared transmittance spectra and mid infrared attenuated total reflectance spectra of all samples were obtained under room temperature. Based on the fused data of near and mid infrared spectra, the discrimination models of Yili, Mengniu and both brands milk were established. The classification accuracies of three discrimination models for prediction set were 96.2%, 96.2% and 94.2%, respectively. For comparing, the discriminant models of Yili, Mengniu and two brands milk were established using near infrared spectra and mid infrared spectra individually. The results show that the fusion of near and mid infrared spectra not only can reduce the effect of different brands milk on the model, but also can provide better results compared with near infrared spectra and mid infrared spectra individually.

Key words: near infrared spectroscopy, mid infrared correlation spectroscopy, data fusion, different brands milk, discriminant analysis, melamine

中图分类号:

O657.33

张海洋, 廖彩淇, 杨仁杰, 鲍秀君, 王威, 靳皓, 张伟玉. 基于近、中红外光谱数据融合掺假牛奶的判定[J]. 天津农学院学报, 2017, 24(4): 52-56.

ZHANG Hai-yang, LIAO Cai-qi, YANG Ren-jie, BAO Xiu-jun, WANG Wei, JIN Hao, ZHANG Wei-yu. Classification of Adulterated Milk Based on the Fused Near and Mid Infrared Spectroscopy[J]. Journal of Tianjin Agricultural University, 2017, 24(4): 52-56.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://xuebao.tjau.edu.cn/CN/

http://xuebao.tjau.edu.cn/CN/Y2017/V24/I4/52

参考文献

[1] 崔彩路,杨仁杰,朱文碧,等. 二维相关红外谱结合PARAFAC-MLR判别掺杂牛奶[J]. 天津农学院学报,2015,22(1):19-23.
[2] Lu C H,Xiang B R,Hao G,et al.Rapid detection of melamine in milk powder by near infrared spectroscopy[J]. J Near Infrared Spectroscopy,2009,17(2):59-67.
[3] Lisa J M,Alona A,Chernyshova A H,et al.Melamine detection in infant formula powder using near- and mid-infrared spectroscopy[J]. Journal of Agricultural and Food Chemistry,2009,57(10):3974-3980.
[4] 李亮,丁武. 掺有植物性填充物牛奶的近红外光谱判别分析[J]. 光谱学与光谱分析,2010,30(5):1238-1242.
[5] 金垚,杜斌,智秀娟. NIR技术快速鉴定牛奶品牌与掺假识别[J]. 食品研究与开发,2016,37(3):178-181.
[6] 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.
[7] Yang R J,Liu R,Dong G M,et al.Two-dimensional hetero-spectral mid-infrared and near-infrared correlation spectroscopy for discrimination adulterated milk[J]. Spectrochimica Acta Part A,2016,157:50-54.
[8] Yang R J,Dong G M,Sun X S,et al.Synchronous- asynchronous two-dimensional correlation spectroscopy for the discrimination of adulterated milk[J]. Analytical Methods,2015,7(10):4302-4307.
[9] 杨仁杰,刘蓉,杨延荣,等. 二维相关近红外谱多维主成分分析掺杂牛奶判别方法研究[J]. 光学精密工程,2014,22(9):2352-2358.
[10] 杨仁杰,杨延荣,刘海学,等. 二维相关谱在食品品质检测中的研究进展[J]. 光谱学与光谱分析,2015,35(8):2124-2129.
[11] Casale M,Oliveri P,Casolino C,et al.Characterisation of PDO olive oil Chianti Classico by non-selective(UV-visible, NIR and MIR spectroscopy)and selective (fatty acid composition)analytical techniques[J]. Analytica Chimica Acta,2012,712:56-63.
[12] Bras L P,Bernardino S A,Lopes J A,et al.Multiblock PLS as an approach to compare and combine NIR and MIR spectra in calibrations of soybean[J]. Chemometrics and Intelligent Laboratory Systems,2005,75(1):91-99.
[13] Casale M,Sinelli N,Oliveri P,et al.Chemometrical strategies for feature selection and data compression applied to NIR and MIR spectra of extra virgin olive oils for cultivar identification[J]. Talanta,2010,80(5):1832-1837.
[14] Harrington P B,Kister J,Artaud J,et al.Automated principal component-based orthogonal signal correction applied to fused near infrared-mid-infrared spectra of French olive oils[J]. Analytical Chemistry,2009,81(17):7160-7169.