Determination of Luzhou-flavor liquor ages by three-dimensional fluorescence spectroscopy combined with NMF

Abstract

The determination of Luzhou-flavor liquor ages is carried out by three-dimensional fluorescence spectroscopy combined with non-negative matrix factorization (NMF). 37 samples of aged liquors with weighted ages of 15, 20 and 25 years were prepared by blending three Luzhou-flavor original base liquors with storage ages of 10, 20 and 30 years in different proportions. The fluorescence spectra of the samples were measured, and then factorized into basis matrix and coefficients matrix by multiplicative iterative NMF. The fluorescence spectra, reconstructed from the basis matrix, are similar to the original spectra. The coefficients matrix is taken as the input of support vector machine (SVM) to establish a prediction model for the determination of liquor ages. Compared with the principal component analysis, the prediction model based on SVM has a predicted accuracy better than 91.7%. This method can provide helps for the market supervision on the aged liquors.

References

[1] YaoF., YiB., ShenC., TaoF., LiuY., LinZ., XuP.. Scientific Reports, 2015, 5: 9553

[2] HanS., ZhangW., LiX., LiP., LiuJ.. Food Analytical Methods, 2016, 9: 2194

[3] ZhuS. M., XuM. L., RamaswamyH. S., YangM. Y., YuY.. Scientific Reports, 2016, 6: 30273

[4] ChengP., ZhouW., BurrG. S., FuY., FanY., WuS.. Scientific Reports, 2016, 6: 38381

[5] DingX., WuC., HuangJ., ZhouR.. Journal of Food Science, 2015, 80: 2373

[6] DingX., WuC., HuangJ., ZhouR.. LWT–Food Science and Technology, 2016, 66: 124

[7] YangT., LiG., ZhuangM.. Liquor Making, 2008, 35: 33

[8] XuM. L., YuY., RamaswamyH. S., ZhuS. M.. Scientific Reports, 2017, 7: 39671

[9] XuZ.. Liquor–Making Science and Technology, 2008, 2: 90

[10] MaC., ChenG., GaoS., ChenC., ShiY., GuL.. Optoelectronics Letters, 2011, 7: 158

[11] ZhuZ., QueL., WuY., ChenG., XuR., ZhuT.. Chinese Journal of Lasers, 2015, 42: 0615002

[12] LeeD. D., SeungH. S.. Learning the parts of objects by non–negative matrix factorization, Nature, 1999, 401: 788

[13] LiuY., LiaoY., TangL., TangF., LiuW.. Neurocomputing, 2016, 173: 224

[14] GuillametD., VitriaJ., SchieleB.. Pattern Recognition Letters, 2003, 24: 2447

[15] HoyerP. O.. Journal of Machine Learning Research, 2004, 5: 1457

[16] EggermontP. P. B.. Linear Algebra and its Applications, 1990, 130: 25

[17] KroonenbergP. M., de LeeuwJ.. Psychometrika, 1980, 45: 69

[18] ZhangL., ZhouW.. Journal of Computational and Applied Mathematics, 2006, 196: 478

[19] CortesC., VapnikV.. Support–vector networks, Machine Learning, 1995, 20: 273

[20] GrimmK. J., MazzaG. L., DavoudzadehP.. Structural Equation Modeling A Multidisciplinary Journal, 2017, 24: 246

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.