“Huzhu” Qingke liquor is a product of geographical identification of origin protection in China, with the gradual expansion of people’s attention to it, fake and diluted “Huzhu” Qingke liquor flooded the market, which not only seriously damaged the interests of consumers, but also disrupted the market economy.Faced with the complex market, finding a quick, non-destructive, and scientific method to identify “Huzhu” Qingke liquor has always been the focus of analysis and research.In this study, “Huzhu” Qingke liquor, non-“Huzhu” Qingke liquor, and non-Qingke liquor were the research object and were studied the spectral characteristics of three kinds of liquor by ultraviolet spectroscopy.Then, the identification effects of four pretreatment methods, two feature variable screening methods, and six classification models on “Huzhu” Qingke liquor were investigated.The results showed that support vector machine, extreme learning machine, back propagation neural network (BPNN), and other classification methods optimized by red-billed blue magpie optimizer (RBMO) could significantly improve the classification effect.Among them, the data obtained after first-order derivative preprocessing and ReliefF feature variable screening combined with RBMO optimized BPNN has the best classification and recognition effect, with an accuracy of 96.20% on the training set and 100% on the test set, and the final fitness value was the lowest.It shows that RBMO optimizer combined with BPNN can distinguish Qingke liquor quickly, nondestructively, and accurately.
[1] ZHANG G Y, TUO X G, PENG Y J, et al.A rapid nondestructive detection method for liquor quality analysis using NIR spectroscopy and pattern recognition[J].Applied Sciences, 2024, 14(11):4392.
[2] QIAN W, LU Z M, CHAI L J, et al.Cooperation within the microbial consortia of fermented grains and pit mud drives organic acid synthesis in strong-flavor Baijiu production[J].Food Research International, 2021, 147:110449.
[3] FANG C, DU H, JIA W, et al.Compositional differences and similarities between typical Chinese Baijiu and western liquor as revealed by mass spectrometry-based metabolomics[J].Metabolites, 2018, 9(1):2.
[4] WU Z Z, XU E B, LI J P, et al.Determination of antioxidant capacity of Chinese rice wine and Zhuyeqing liquor using nanoparticle-based colorimetric methods[J].Food Analytical Methods, 2017, 10(3):788-798.
[5] HE F, DUAN J W, ZHAO J W, et al.Different distillation stages Baijiu classification by temperature-programmed headspace-gas chromatography-ion mobility spectrometry and gas chromatography-olfactometry-mass spectrometry combined with chemometric strategies[J].Food Chemistry, 2021, 365:130430.
[6] WU Z Y, QIN D, DUAN J W, et al.Characterization of benzenemethanethiol in sesame-flavour Baijiu by high-performance liquid chromatography-mass spectrometry and sensory science[J].Food Chemistry, 2021, 364:130345.
[7] HE M, CHEN X L, ZHANG J, et al.Identification of liquors from the same brand based on ultraviolet, near-infrared and fluorescence spectroscopy combined with chemometrics[J].Food Chemistry, 2023, 400:134064.
[8] SÁDECKÁ J, JAKUBÍKOVÁ M.Classification of tokaj wines by ultraviolet-visible spectroscopy[J].Food Analytical Methods, 2022, 15(1):56-66.
[9] 张有香, 唐东恒, 赵国华, 等.青稞酒窖池内不同层次酒醅酒体风味物质的研究[J].酿酒科技, 2024, (11):72-76;81.
ZHANG Y X, TANG D H, ZHAO G H, et al.Flavor substances of fermented grains in different layers in the pit of highland barley Baijiu[J].Liquor-Making Science & Technology, 2024, (11):72-76;81.
[10] STEIDLE NETO A J, DE CARVALHO LOPES D.Chemometrics coupled with near infrared spectroscopy for detecting adulteration levels in herbal teas[J].Journal of Food Composition and Analysis, 2024, 135:106637.
[11] ONG P, JIAN J B, LI X H, et al.Sugarcane disease recognition through visible and near-infrared spectroscopy using deep learning assisted continuous wavelet transform-based spectrogram[J].Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy, 2025, 324:125001.
[12] ZONG X Y, ZHOU X J, WEN L, et al.Identification of Baijiu based on the Raman spectroscopy and back-propagation neural network optimized using genetic algorithm[J].Journal of Food Composition and Analysis, 2024, 126:105917.
[13] CHENG X Y, HU X P, LI Z Z, et al.Using genetic algorithm and particle swarm optimization BP neural network algorithm to improve marine oil spill prediction[J].Water, Air, & Soil Pollution, 2022, 233(8):354.
[14] FU S W, LI K, HUANG H S, et al.Red-billed blue magpie optimizer:A novel metaheuristic algorithm for 2D/3D UAV path planning and engineering design problems[J].Artificial Intelligence Review, 2024, 57(6):134.
[15] EL-FERGANY A A, AGWA A M.Red-billed blue magpie optimizer for electrical characterization of fuel cells with prioritizing estimated parameters[J].Technologies, 2024, 12(9):156.
[16] ONG P, JIAN J B, YIN J H, et al.Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm[J].Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy, 2023, 302:123095.
[17] KHATUN M S, AL MASUM A, ISLAM M H, et al.Short wave-near infrared spectroscopy for predicting soluble solid content in intact mango with variable selection algorithms and chemometric model[J].Journal of Food Composition and Analysis, 2024, 136:106745.
[18] ZHAO J W, CHEN Q S, HUANG X Y, et al.Qualitative identification of tea categories by near infrared spectroscopy and support vector machine[J].Journal of Pharmaceutical and Biomedical Analysis, 2006, 41(4):1198-1204.
[19] LAMPTEY F P, AMUAH C L Y, BOADU V G, et al.Smart classification of organic and inorganic pineapple juice using dual NIR spectrometers combined with chemometric techniques[J].Applied Food Research, 2024, 4(2):100471.
[20] LOHUMI S, LEE S, CHO B K.Optimal variable selection for Fourier transform infrared spectroscopic analysis of starch-adulterated garlic powder[J].Sensors and Actuators B:Chemical, 2015, 216:622-628.
[21] CHONG I G, JUN C H.Performance of some variable selection methods when multicollinearity is present[J].Chemometrics and Intelligent Laboratory Systems, 2005, 78(1-2):103-112.
[22] WANG Z X, HE Q P, WANG J.Comparison of variable selection methods for PLS-based soft sensor modeling[J].Journal of Process Control, 2015, 26:56-72.
[23] KONONENKO I.Estimating attributes:Analysis and extensions of RELIEF[C].Machine Learning:ECML-94.Berlin, Heidelberg:Springer, 1994:171-182.
[24] 项颂阳, 许章华, 张艺伟, 等.高光谱图像分类的ReliefF-RFE特征选择算法构建与应用[J].光谱学与光谱分析, 2022, 42(10):3283-3290.
XIANG S Y, XU Z H, ZHANG Y W, et al.Construction and application of ReliefF-RFE feature selection algorithm for hyperspectral image classification[J].Spectroscopy and Spectral Analysis, 2022, 42(10):3283-3290.
[25] ZAREEF M, CHEN Q S, HASSAN M M, et al.An overview on the applications of typical non-linear algorithms coupled with NIR spectroscopy in food analysis[J].Food Engineering Reviews, 2020, 12(2):173-190.
[26] 苏媛媛, 姜雪, 仓义鹏, 等.紫外-可见光谱传感对高温大曲白酒真实性的准确鉴别[J].化学试剂, 2023, 45(10):8-13.
SU Y Y, JIANG X, CANG Y P, et al.Accurate identification of high-temperature Daqu liquor by UV-vis sensor[J].Chemical Reagents, 2023, 45(10):8-13.
[27] 张勋, 黄晓萱, 殷金可, 等.基于近红外和化学计量学方法对金线莲快速鉴别及其多糖含量测定的研究[J].中国现代应用药学, 2023, 40(19):2702-2712.
ZHANG X, HUANG X X, YIN J K, et al.Rapid identification and determination of polysaccharides contents in Anoectochilus roxburghii based on near infrared spectroscopy with chemometrics[J].Chinese Journal of Modern Applied Pharmacy, 2023, 40(19):2702-2712.
[28] DE SOUSA MARQUES A, NICÁCIO J T N, CIDRAL T A, et al.The use of near infrared spectroscopy and multivariate techniques to differentiate Escherichia coli and Salmonella Enteritidis inoculated into pulp juice[J].Journal of Microbiological Methods, 2013, 93(2):90-94.
[29] PENDHARKAR P.Misclassification cost minimizing fitness functions for genetic algorithm-based artificial neural network classifiers[J].Journal of the Operational Research Society, 2009, 60(8):1123-1134.
[30] TANG Z, LIU X F, WEI D P, et al.Enhanced multiclass support vector data description model for fault diagnosis of gears[J].Measurement, 2022, 194:110974.
