开展了独立成分分析(independent component analysis,ICA)联合支持向量机(support vector machine,SVM)模型对食品掺伪的判别.通过傅里叶变换红外光谱仪获得食用植物油(正品油、掺伪油和炸货油)以及奶粉(纯奶粉和掺三聚氰胺奶粉)的中红外光谱,首先,探究不同的光谱预处理方法对所建立模型的影响,经考察选取归一化结合移动平滑对光谱进行预处理;然后采用特征矩阵联合近似对角化(joint approximate diagonalization of eigenmatrices,JADE)方法提取光谱特征信息,其结果优于主成分分析对特征信息的提取效果;通过Kennard-Stone算法划分训练集和测试集,利用贝叶斯优化(Bayesian optimization,BO)对SVM模型参数进行优化.经考察,所构建的JADE-BO-SVM模型对掺伪食品的识别准确度达到100%,该法可为食品掺伪的高效、准确鉴别提供新的途径和思路.
Independent component analysis(ICA)combined with support vector machine(SVM)model was carried out to identify food adulteration. Mid-infrared spectra of edible vegetable oil(certified oil, adulterate oil and fried oil)as well as milk powder(pure milk powder and melamine-containing milk powder)were obtained by Fourier transform infrared spectroscopy(FTIR). Firstly, the effects of different spectral preprocessing methods on the established model were investigated, and the normalization combined with the moving smoothing method was selected for the preprocessing of the spectra. Then the joint approximate diagonalization of eigenmatrices(JADE)method was used to extract the spectral feature- DOI:10.3969/j.issn.1000-1565.2024.02.004基于贝叶斯优化的JADE-SVM中红外食品掺伪判别模型张孟莎1,田璐1,李艳坤1,沈晓芳2(1.华北电力大学 环境科学与工程系,河北 保定 071003;2.江南大学 食品学院,江苏 无锡 214122)摘 要:开展了独立成分分析(independent component analysis,ICA)联合支持向量机(support vector machine,SVM)模型对食品掺伪的判别.通过傅里叶变换红外光谱仪获得食用植物油(正品油、掺伪油和炸货油)以及奶粉(纯奶粉和掺三聚氰胺奶粉)的中红外光谱,首先,探究不同的光谱预处理方法对所建立模型的影响,经考察选取归一化结合移动平滑对光谱进行预处理;然后采用特征矩阵联合近似对角化(joint approximate diagonalization of eigenmatrices,JADE)方法提取光谱特征信息,其结果优于主成分分析对特征信息的提取效果;通过Kennard-Stone算法划分训练集和测试集,利用贝叶斯优化(Bayesian optimization,BO)对SVM模型参数进行优化.经考察,所构建的JADE-BO-SVM模型对掺伪食品的识别准确度达到100%,该法可为食品掺伪的高效、准确鉴别提供新的途径和思路.关键词:光谱学;中红外光谱;模式识别;参数优化;掺伪判别中图分类号:TB96 文献标志码:A 文章编号:1000-1565(2024)02-0139-07JADE-SVM mid-infrared food adulteration discrimination model based on Bayesian optimizationZHANG Mengsha1, TIAN Lu1, LI Yankun1, SHEN Xiaofang2(1. Department of Environmental Science and Engineering, North China Electric Power University, Baoding 071003, China;2. College of Food Science and Technology, Jiangnan University, Wuxi 214122, China)Abstract: Independent component analysis(ICA)combined with support vector machine(SVM)model was carried out to identify food adulteration. Mid-infrared spectra of edible vegetable oil(certified oil, adulterate oil and fried oil)as well as milk powder(pure milk powder and melamine-containing milk powder)were obtained by Fourier transform infrared spectroscopy(FTIR). Firstly, the effects of different spectral preprocessing methods on the established model were investigated, and the normalization combined with the moving smoothing method was selected for the preprocessing of the spectra. Then the joint approximate diagonalization of eigenmatrices(JADE)method was used to extract the spectral feature- 收稿日期:2023-09-22;修回日期:2023-10-27 基金项目:国创计划资助项目(S202310079127); 中央高校基本科研业务费资助项目(2017MS135) 第一作者:张孟莎(1998—),女,华北电力大学在读硕士研究生,主要从事基于盲源分离模型展开光谱的定性和定量分析.E-mail:zhangmengsha125@126.com 通信作者:李艳坤(1977—),女,华北电力大学副教授,主要从事化学计量学、环境分析化学方面的研究.E-mail:liyankun_ncepu@foxmail.com第2期张孟莎等:基于贝叶斯优化的JADE-SVM中红外食品掺伪判别模型information, and the results were better than those of the principal component analysis for feature information extraction. The training and testing sets were divided by the Kennard-Stone algorithm, and Bayesian optimization(BO)was used to optimize the SVM model parameters. Upon examination, the constructed JADE-BO-SVM model achieved 100% accuracy in identifying adulterated food. The proposed method can provide new way and new idea for the efficient and accurate identification of food adulteration.
[1] WANG S, LAI G, LIN J, et al. Rapid detection of adulteration in extra virgin olive oil by low-field nuclear magnetic resonance combined with pattern recognition[J]. Food Analytical Methods, 2021, 14(7): 1322-1355.DOI:10.11895/j.issn.0253-3820.140902.
[2] NU 'ÑEZ N, SAURINA J, NU 'ÑEZ O. Non-targeted HPLC-FLD fingerprinting for the detection and quantitation of adulterated coffee samples by chemometrics[J]. Food Control, 2021, 124: 107912.DOI: 10.1016/j.foodcont.2021.107912.
[3] ALI H, RAFIQUE K, ULLAH R, et al. Classification of Sidr honey and detection of sugar adulteration using right angle fluorescence spectroscopy and chemometrics[J]. European Food Research and Technology, 2022, 248(7): 1823-1829.DOI: 10.1007/S00217-022-04008-9.
[4] 陈燕,张笑,邱思慧,等.茶油掺伪检测技术研究进展[J].中国粮油学报, 2023, 38(4): 159-169.DOI: 10.20048/j.cnki.issn.1003-0174.000291.
[5] 侯颖烨,王志元,谢建军,等.元素分析-稳定同位素质谱法结合化学计量学鉴别橄榄油掺假[J].中国油脂, 2023, 48(6): 73-78.DOI: 10.19902/j.cnki.zgyz.1003.7969.220232.
[6] 李艳坤,许东情.基于中红外光谱模型对食用植物油掺伪的判别[J].河北大学学报(自然科学版), 2022, 42(6): 605-610.DOI: 10.3969/j.issn.1000-1565.2022.06.007.
[7] 庞佳烽,汤谌,李艳坤,等. 中红外光谱联合模式识别鉴别奶粉中三聚氰胺[J].光谱学与光谱分析, 2020, 40(10): 3235-3240.DOI:10.3964/j.issn.1000-0593(2020)10-3235-06.
[8] COMON P. Independent component analysis, A new concept[J]. Signal Processing, 1994, 36(3): 287-314.DOI: 10.1016/0165-1684(94)90029-9.
[9] MONAKHOVA Y B, RUTLEDGE D N. Independent components analysis(ICA)at the “cocktail-party” in analytical chemistry[J]. Talanta, 2020, 208(1): 120451.DOI: 10.1016/j.talanta.2019.120451.
[10] 黄秀,康嘉诚,王淇,等.基于盲源分离的有机物混合信号特征提取与解析[J].计量学报, 2023, 44(4): 645-652.DOI: 10.3969/j.issn.1000-1158.2023.04.23.
[11] CARDOSO J F. High-order contrasts for independent component analysis[J]. Neural computation, 1999, 11(1): 157-192.DOI: 10.1162/089976699300016863.
[12] LIU F, HUANG H, LIU Y, et al. Performance degradation assessment for coaxial bearings using kernel JADE and two-class model[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-12.DOI: 10.1109/tim.2020.3014033.
[13] CORTES C, VAPNIK V. Support-Vector Networks [J]. Machine Learning, 1995, 20(3): 273-297.DOI: 10.1007/bf00994018.
[14] 闪霁芳,刘琨,江俊峰,等.支持向量机在混合气体定量分析中的应用[J].光学学报, 2023, 43(12): 81-91.DOI: 10.3788/AOS221681.
[15] MOHAMMADI M, RASHID T A, KARIM S H T, et al. A comprehensive survey and taxonomy of the SVM-based intrusion detection systems[J]. Journal of Network and Computer Applications, 2021, 178: 102983. DOI: 10.1016/j.jnca.2021.102983.
[16] 冯瑞杰,陈争光,衣淑娟.基于贝叶斯优化的SVM玉米品种鉴别研究[J].光谱学与光谱分析, 2022, 42(6): 1698-1703.DOI: 10.3964/j.issn.1000-0593(2022)06-1698-06.
[17] WANG X, JIN Y, SCHMITT S, et al. Recent advances in Bayesian optimization[J]. ACM Computing Surveys, 2023, 55(13s): 1-36.DOI: 10.1145/3582078.
[18] 孙嘉豪,张伟,施鉴芩,等.光谱数据预处理策略选择及应用 [J].计量学报, 2023, 44(8): 11284-1292.DOI: 10.3969/j.issn.1000-1158.2003.08.20.
[19] CHERKASSKY V, MA Y. Practical selection of SVM parameters and noise estimation for SVM regression[J]. Neural networks, 2004, 17(1): 113-126.DOI: 10.1016/s0893-6080(03)00169-2. (
