WANG Yi-miao, ZHU Jin-lin, ZHANG Hui etc. Optimization of Near Infrared Quantitative Model for Wine Alcohol Content Based on MC-UVE, GA Algorithm and Factor Analysis[J]. Chinese Journal of Luminescence, 2018,39(9): 1310-1316
WANG Yi-miao, ZHU Jin-lin, ZHANG Hui etc. Optimization of Near Infrared Quantitative Model for Wine Alcohol Content Based on MC-UVE, GA Algorithm and Factor Analysis[J]. Chinese Journal of Luminescence, 2018,39(9): 1310-1316 DOI: 10.3788/fgxb20183909.1310.
Optimization of Near Infrared Quantitative Model for Wine Alcohol Content Based on MC-UVE, GA Algorithm and Factor Analysis
对葡萄酒酒精度偏最小二乘(Partial least squares,PLS)回归模型进行优化研究。使用近红外光谱仪采集葡萄酒样本的光谱数据,用于建立酒精度定量模型,实现在线快速检测。通过蒙特卡罗无信息变量消除(Monte Carlo uninformative variable elimination,MC-UVE)和遗传算法(Genetic algorithm,GA)进行变量选择,基于被选择的变量分别进行PLS和因子分析(Factor analysis,FA),建立回归模型。结果表明,MC-UVE-GA-FAR模型预测集相关系数(
R
2
)为0.946,预测均方根误差(Root mean square error of prediction,RMSEP)为0.215,效果优于MC-UVE-GA-PLS模型。与基于全范围光谱所建PLS回归模型相比,模型效果有所提升,而且模型所选变量个数仅为6,极大地简化了模型。MC-UVE和GA算法与FA分析结合可以实现模型的优化。
Abstract
The optimization of the PLS regression model of wine alcohol content was studied. The near-infrared spectroscopy was used to collect the spectral data of the wine samples and the data were used to establish the quantitative model of alcohol to achieve rapid on-line detection. PLS regression model and FA model were established based on the selected variables
chosen by MC-UVE and GA. The results show that the MC-UVE-GA-FAR model
which yielded
R
2
of 0.946 and RMSEP of 0.215
is superior to the MV-UVE-GA-PLS model. In comparison of the performance of the full-spectra PLS regression model
the model based on the selected wave numbers is much better
and 6 variables in total are selected
which greatly simplifies the model. The study indicates the MC-UVE
GA and FA can optimize the model.
关键词
Keywords
references
FRANKEL E N, GERMAN J B, KINSELLA J E, et al.. Inhibition of oxidation of human low-density lipoprotein by phenolic substances in red wine[J]. The Lancet, 1993, 341(8843):454-457.
BIANCA F, ALEXANDRA L, MICHAEL A. Consumption of red wine with meals reduces the susceptibility of human plasma and low-density lipoprotein to lipid peroxidation[J]. Am. J. Clinic.Nutrit., 1995, 61(3):549-554.
FERRARI E, FOCA G, VIGNALI M, et al.. Adulteration of the anthocyanin content of red wines:perspectives for authentication by Fourier transform-near infrared and 1H NMR spectroscopies[J]. Anal. Chim. Acta, 2011, 701(2):139-151.
URBANO C M, LUQUE D C M, PEREZ J P, et al.. Comparison and joint use of near infrared spectroscopy and Fourier transform mid infrared spectroscopy for the determination of wine parameters[J]. Talanta, 2005, 66(1):218-224.
GEANA E, POPESCU R, COSTINEL D, et al.. Verifying the red wines adulteration through isotopic and chromatographic investigations coupled with multivariate statistic interpretation of the data[J]. Food Control, 2016, 62:1-9.
陈士恒, 章晴, 史晓梅, 等. DSPE-GC/MS快速检测葡萄酒中52种农药残留[J]. 食品科学技术学报, 2014, 32(3):14-22. CHEN S H, ZHANG Q, SHI X M, et al.. Fast determination of 52 pesticide residues in grape wine by DSPEGC/MS[J]. J. Food Sci. Technol., 2014, 32(3):14-22. (in Chinese)
吴正宗, 王芳, 徐恩波, 等. 傅立叶红外光谱技术快速检测黄酒中的氨基酸质量浓度[J]. 食品与生物技术学报, 2017, 36(1):34-40. WU Z Z, WANG F, XU E B, et al.. Rapid determination of amino acids in chinese rice wine by fourier transform infrared spectroscopy[J]. J. Food Sci. Biotechnol., 2017, 36(1):34-40. (in Chinese)
BASALEKOU M, PAPPAS C, KOTSERIDIS Y, et al.. Red wine age estimation by the alteration of its color parameters:Fourier transform infrared spectroscopy as a tool to monitor wine maturation time[J]. J. Anal. Methods Chem., 2017, 2017:1-9.
URBANO-CUARDRADO M, LUQUE D C M, PEREZ J P, et al.. Near infrared reflectance spectroscopy and multivariate analysis in enology[J]. Anal. Chim. Acta, 2004, 527(1):81-88.
COZZOLINO D, KWIATOWSKI M, PARKER M, et al.. Prediction of phenolic compounds in red wine fermentations by visible and near infrared spectroscopy[J]. Anal. Chim. Acta, 2004, 513(1):73-80.
SWIERENGA H, WULFERT F, NOORD O, et al.. Development of robust calibration models in near infrared spectrometric applications[J]. Anal. Chim. Acta, 2000, 411(1):121-135.
LEARDI R, LUPIANEZ G A. Genetic algorithms applied to feature selection in PLS regression:how and when to use them[J]. Chemometrics Intellig. Lab. Syst., 1998, 41(2):195-207.
BLANCO M, COELL J, ITURRIAGA H, et al.. NIR calibration in non-linear systems:different PLS approaches and artificial neural networks[J]. Chemometrics Intellig. Lab. Syst., 2000, 50(1):75-82.
CENTNER V, MASSART D L, NOORD O, et al.. Elimination of uninformative variables for multivariate calibration[J]. Anal. Chem., 1996, 68(21):3851-3858.
ARAUJO M, SALDANHA T, GALVAO R, et al.. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J]. Chemometrics Intellig. Lab. Syst., 2001, 57(2):65-73.
ZHENG J, SONG Z, GE Z. Probabilistic learning of partial least squares regression model:theory and industrial applications[J]. Chemometrics Intellig. Lab. Syst., 2016, 158:80-90.
陈家益, 赵忠盖, 刘飞. 鲁棒PPLS模型及其在过程监控中的应用[J]. 化工学报, 2016, 67(7):2907-2915. CHEN J Y, ZHAO Z G, LIU F. Robust PPLS model and its applications in process monitoring[J]. J. Chem. Ind. Eng., 2016, 67(7):2907-2915. (in Chinese)
GE Z. Supervised latent factor analysis for process data regression modeling and soft sensor application[J]. IEEE Trans. Control Syst. Technol., 2016, 24(3):203-209.
LI C, ZHAO T, LI C, et al.. Determination of gossypol content in cottonseeds by near infrared spectroscopy based on Monte Carlo uninformative variable elimination and nonlinear calibration methods[J]. Food Chem., 2017, 221:990-996.
JIE D, XIE L, FU X, et al.. Variable selection for partial least squares analysis of soluble solids content in watermelon using near-infrared diffuse transmission technique[J]. J. Food Eng., 2013, 118(4):387-392.
马红辉, 王中江, 袁天军, 等. 烟草中淀粉近红外光谱变量的筛选及校正模型的建立[J]. 烟草科技, 2015, 48(8):37-43. MA H H, WANG Z J, YUAN T J, et al.. Screening of NIR spectral variables of starch in tobacco and establishment of calibration model[J]. Tobacco Sci. Technol., 2015, 48(8):37-43. (in Chinese)
COZZOLINO D, CYNKAR W, SHAH N, et al.. Multivariate data analysis applied to spectroscopy:potential application to juice and fruit quality[J]. Food Res. Int., 2011, 44(7):1888-1896.
向伶俐, 李梦华, 李景明, 等. 近、中红外光谱法融合判定葡萄酒产地[J]. 光谱学与光谱分析, 2014, 34(10):2662-2666. XIANG L L, LI M H, LI J M, et al.. Determination of wine original regions using information fusion of NIR and MIR spectroscopy[J]. Spectrosc. Spect. Anal., 2014, 34(10):2662-2666. (in Chinese)
Theoretical Study of Pumping Method of High Power Tm3+-doped Fiber Amplifier for Thermal Effect Management
A General Model for Judging and Brix Detection of Grapefruit Variety Based on Near Infrared
Law of Spatial Prediction of Agro-product Qualities Based on Spectral Imaging
Spectrally Tunable Star Simulator Light Source Based on Digital Micro-mirror Device
Research on Color Mixing and Optimization of RGBW-LEDs Based on Genetic Algorithm
Related Author
Ting FENG
Wen-guo HAN
Feng-ping YAN
Ke ZHANG
OUYANG Yu-ping
JIANG Xiao-gang
HU Jun
SUN Xu-dong
Related Institution
Key Laboratory of All Optical Network and Advanced Telecommunication Network of Ministry of Education, Institute of Lightwave Technology, Beijing Jiaotong University
Photonics Information Innovation Center, College of Physics Science & Technology, Hebei University
School of Mechatronics and Vehicle Engineering, East China Jiaotong University
College of Mechanical and Electronic Engineering, Nanjing Forestry University