开展了基于中红外光谱的化学计量学模型对食用植物油掺伪的研究.通过获得市售食用油和以不同质量浓度掺伪食用油的中红外光谱,采用光谱预处理结合模式识别方法进行综合解析,使样本类间距最大化,类内距最小化,结果发现:无监督聚类包括主成分分析、非负矩阵分解均无法准确鉴别;有监督偏最小二乘判别分析的鉴别准确度较高;而二阶导数-非相关线性判别分析(SD-ULDA)对掺伪样本识别的灵敏度和特异度均达到100%.提出依据变量“负荷量”筛选特征波长(变量)新策略,考察了SD-ULDA模型识别准确率随保留波长的变化,同时准确地预测出掺伪比例,为构建高效中红外光谱食用油掺伪判别模型提供理论基础,为提高油脂品质的检测技术提供方法借鉴.
A chemometric model based on mid-infrared spectroscopy was developed to study the adulteration of edible vegetable oil. The mid-infrared spectra of commercial edible oil and adulterated edible oil with different mass concentrations were obtained and analyzed by spectral preprocessing combined with pattern recognition.The results show that unsupervised methods including principal component analysis and nonnegative matrix factorization do not perform accurately; supervised partial least squares discriminant analysis has high discrimination accuracy; the second derivative-uncorrelated linear discriminant analysis(SD-ULDA)maximizes the sample class spacing and minimizes the class spacing as much as possible, and the sensitivity and specificity for the identification of adulterated samples are 100%.A new strategy of characteristic wavelength(variables)screening according to ‘load capacity’ of variables is proposed, and the change of recognition accuracy of SD-ULDA model with reserved wavelength was investigated. Simultaneously, the adulteration proportion was accurately predicted. It provides a theoretical basis for constructing a high-efficiency mid-infrared spectrum edible oil adulteration- DOI:10.3969/j.issn.1000-1565.2022.06.007基于中红外光谱模型对食用植物油掺伪的判别李艳坤,许东情(华北电力大学(保定)环境科学与工程系,河北省燃煤电站烟气多污染物协同控制重点实验室,河北 保定 071003)摘 要:开展了基于中红外光谱的化学计量学模型对食用植物油掺伪的研究.通过获得市售食用油和以不同质量浓度掺伪食用油的中红外光谱,采用光谱预处理结合模式识别方法进行综合解析,使样本类间距最大化,类内距最小化,结果发现:无监督聚类包括主成分分析、非负矩阵分解均无法准确鉴别;有监督偏最小二乘判别分析的鉴别准确度较高;而二阶导数-非相关线性判别分析(SD-ULDA)对掺伪样本识别的灵敏度和特异度均达到100%.提出依据变量“负荷量”筛选特征波长(变量)新策略,考察了SD-ULDA模型识别准确率随保留波长的变化,同时准确地预测出掺伪比例,为构建高效中红外光谱食用油掺伪判别模型提供理论基础,为提高油脂品质的检测技术提供方法借鉴.关键词:中红外光谱;食用油;掺伪鉴别;非相关线性判别分析;波长筛选中图分类号:O433.4 文献标志码:A 文章编号:1000-1565(2022)06-0605-06Discrimination of adulteration of edible vegetable oil based on mid-infrared spectroscopy modelLI Yankun, XU Dongqing(Key Laboratory for Collaborative Control of Multi Pollutants in Flue Gas of Coal-fired Power Plants, Department of Environment Science and Engineering, North China Electric Power University, Baoding 071003, China)Abstract: A chemometric model based on mid-infrared spectroscopy was developed to study the adulteration of edible vegetable oil. The mid-infrared spectra of commercial edible oil and adulterated edible oil with different mass concentrations were obtained and analyzed by spectral preprocessing combined with pattern recognition.The results show that unsupervised methods including principal component analysis and nonnegative matrix factorization do not perform accurately; supervised partial least squares discriminant analysis has high discrimination accuracy; the second derivative-uncorrelated linear discriminant analysis(SD-ULDA)maximizes the sample class spacing and minimizes the class spacing as much as possible, and the sensitivity and specificity for the identification of adulterated samples are 100%.A new strategy of characteristic wavelength(variables)screening according to ‘load capacity’ of variables is proposed, and the change of recognition accuracy of SD-ULDA model with reserved wavelength was investigated. Simultaneously, the adulteration proportion was accurately predicted. It provides a theoretical basis for constructing a high-efficiency mid-infrared spectrum edible oil adulteration- 收稿日期:2022-03-03 基金项目:中央高校基本科研业务费资助项目(2017MS135) 第一作者:李艳坤(1977—),女,河北邯郸人,华北电力大学副教授,博士,主要从事分析化学、化学信息学的研究.E-mail:liyankun_ncepu@foxmail.com第6期李艳坤等:基于中红外光谱模型对食用植物油掺伪的判别discrimination model and provides a reference method for improving the detection technology of oil quality.
[1] 何文绚,方润,李艳霞,等.快速测定植物油胆固醇含量在地沟油筛查中的应用[J].分析化学, 2015, 43(3): 394-398. DOI:10.11895/j.issn.0253-3820.140902.
[2] 孔德明,李雨蒙,崔耀耀,等.结合小波压缩和APTLD的三维荧光光谱技术在掺伪芝麻油鉴别中的应用[J].光学学报, 2019, 39(3): 412-422.DOI:10.3788/AOS201939.0330004.
[3] 沈伟健,王红,陆慧媛,等.气相色谱-质谱法测定植物油中8种维生素E及其在芝麻油真伪鉴别方面的应用[J].色谱, 2020, 38(5): 595-599.DOI:10.3724/SP.J.1123.2019.09011.
[4] MA X P, PANG J F, DONG R N, et al. Rapid prediction of multiple wine quality parameters using infrared spectroscopy coupling with chemometric methods[J]. J Food Compos Anal, 2020, 91: 103509.DOI:10.1016/j.jfca.2020.103509.
[5] GU H W, YIN X L, PENG T Q, et al. Geographical origin identification and chemical markers screening of Chinese green tea using two-dimensional fingerprints technique coupled with multivariate chemometric methods[J]. Food Control, 2022, 135: 108795. DOI:10.1016/j.foodcont.2021.108795.
[6] 李艳坤,贾明静,王涵.中红外光谱法结合化学计量学对柏子养心丸和牛黄解毒丸的分析[J].河北大学学报(自然科学版), 2018, 38(3): 262-267. DOI:10.3969/j.issn.1000-1565.2018.03.006.
[7] GRIS E F, MATTIVI F, FERREIRA E A, et al. Stilbenes and tyrosol as target compounds in the assessment of antioxidant and hypolipidemic activity of vitis vinifera red wines from southern brazil[J]. J Agric Food Chem, 2011, 59(14):7954-7961. DOI: 10.1021/jf2008056.
[8] 周玲玲,姚志湘,粟晖,等.ATR/FTIR法检测植物油的品质指标[J].中国油脂,2016,41(4):96-99. DOI:10.3969/j.issn.1003-7969.2016.04.022.
[9] 李艳坤,董汝南,张进,等.光谱数据解析中的变量筛选方法[J].光谱学与光谱分析, 2021, 41(11): 3331-3338. DOI:10.3964/j.issn.1000-0593(2021)11-3331-08.
[10] CHU D L, GOH S T, HUNG Y S. Characterization of all solutions for undersampled uncorrelated linear discriminant analysis problems[J]. SIAM Journal on Matrix Analysis and Applications, 2011, 32(3): 820-844. DOI: 10.1137/100792007.
[11] LI Y K, ZENG X C. Serum SELDI-TOF MS analysis model applied to benign and malignant ovarian tumor identification[J]. Anal Methods, 2016, 8:183-188. DOI:10.1039/C5AY02517F.
[12] TURK M, PENTLAND A. Eigenfaces for recognition[J]. J Cogn Neurosci, 1991, 3(1): 71-86. DOI: 10.1162/jocn.1991.3.1.71.
[13] LEE D D, SEUNG H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401(6755): 788-791. DOI:10.1038/44565.
[14] 高乾坤,刘文清,张玉钧.针对湍流噪声的傅里叶光谱数据处理方法[J].光学学报, 2021, 41(17): 189-196. DOI:10.3788/AOS202141.1730001.
[15] 梁逸曾,许青松.复杂体系仪器分析—白、灰、黑分析体系及其多变量解析方法[M].北京: 化学工业出版社, 2012.
[16] ROUSSEAU R, GOVAERTS B, VERLEYSEN M, et al. Comparison of some chemometric tools for metabonomics biomarker identification[J]. Chemom Intell Lab Syst, 2008, 91: 54-66. DOI:10.1016/j.chemolab.2007.06.008. (
