目的 建立中药皂角刺中山皂角刺和野皂角刺掺伪的快速分析鉴别方法。方法 利用近红外光谱法结合线性判别分析(LDA)、支持向量级(SVM)和人工神经网络法(BP-NN),建立中药皂角刺中山皂角刺和野皂角刺掺伪的快速无损鉴别模式识别模型;采用偏最小二乘(PLS)回归分析建立掺伪品中山皂角刺和野皂角刺伪品的掺伪量预测模型。结果 对于皂角刺正品和其山皂角刺掺伪及野皂角刺掺伪品SVM法分类效果优于LDA和BP-NN法。谱段选择5 000~4 200 cm-1、采用平滑-归一化法预处理数据方法时,SVM建模训练集、验证集和测试集分类准确率分别为100%、100%和96.4%。PLS回归模型结果显示,山皂角刺掺伪预测集rp、预测集均方根误(RMSEP)和偏差(bias)值分别为0.993、2.91%和-0.330 3;野皂角刺掺伪预测集rp、RMSE和bias值分别为0.995、2.57%和0.364 9。结论 本实验建立的模式识别模型及回归方法能够准确快速判别皂角刺及山皂角刺和野皂角刺掺伪品并能较准确预测正品中山皂角刺和野皂角刺掺伪量。
Abstract
OBJECTIVE To discriminate and quantify of Gleditsia japonica Miq. thorn (SZJ) and Gleditsia microphylla Gordon ex Y. T. Lee thorn (YZJ) in the Gleditsia sinensis Lam thorn (GST). METHODS Fourier transform near-infrared spectroscopy (FT-NIR) combined with linear discriminate analysis (LDA), support vector machine (SVM), as while as back propagation neural network (BPNN) algorithms were applied to construct the identification models. The SZJ and YZJ content in adulterated GST were determined by partial least squares regression (PLSR). RESULTS The SVM models performance best compared with LDA and BP-NN models for it could reach 100% accuracy in training and validation set for identifying authentic GST and GST adulterated with SZJ and YZJ based on the spectral region of 5 000-4 200 cm-1 combined with SG+VN processing. The rp, RMSEP (the root mean standard error of prediction) and bias for the prediction by PLS regression model were 0.993, 2.919% and -0.330 3 for SZJ, 0.995, 2.57% and 0.364 9 for YZJ, respectively. CONCLUSION Our results suggest that the combination of NIR spectroscopy and chemometric methods offers a simple, fast and reliable method for classifification and quantifification of SZJ and YZJ adulterants in the GST.
关键词
皂角刺 /
支持向量机 /
偏最小二乘回归 /
近红外光谱
{{custom_keyword}} /
Key words
Gleditsia sinensis Lam thorn /
support vector machine /
PLS regression /
near-infrared spectroscopy
{{custom_keyword}} /
中图分类号:
R917
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] LI K K, ZHOU X L, WONGH L, et al. In vivo and in vitro anti-inflammatory effects of Zao-Jiao-Ci (the spine of Gleditsia sinensis Lam.) aqueous extract and its mechanisms of action[J]. J Ethnopharmacol, 2016, 192: 192-200.
[2] YI J M, PARK J S, OH S M, et al. Ethanol extract of Gleditsia sinensis thorn suppresses angiogenesis in vitro and in vivo[J]. BMC Complem Altern M, 2012, 12:243.
[3] LEE S J, RYU D H, JANG L C, et al. Suppressive effects of an ethanol extract of Gleditsia sinensis thorns on human SNU-5 gastric cancer cells[J]. Oncol Rep, 2013, 29(4): 1609-1616.
[4] YU J Q, XIAN Y X, GENG Y L, et al. Anti-liver cancer constituents from the thorns of Gleditsia sinensis[J]. Phytochem Lett, 2015, 13: 343-347.
[5] HU M. Character and microscopic identification of Gleditisa sinensis thorn and its common adulterants[J]. Zhenjiang J Integr Tradit Chin West Med, 2013, 23(8): 673-674.
[6] SAVITZKY A, GOLAY M J E. Smoothing and differentiation of data by simplified least squares procedures[J]. Anal Chem, 1964, 36(8): 1627-1639.
[7] LI J B, HUANG W Q, ZHAO C J, et al. A comparative study for the quantitative determination of soluble solids content, pH and firmness of pears by Vis/NIR spectroscopy[J]. J Food Eng, 2013, 116(2): 324-332.
[8] ARAUJO M C U, SALDANHA T C B, GALVAO R K H, et al. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J]. Chemometr Intell Lab, 2001, 57(2): 65-73.
[9] LUNA A S. Chemometrics: Methods, Applications and New Research [M]. New York: Nova Science Publishers, 2017.
[10] VARMUZA K, FILZNOSER P. Introduction to Multivariate Statistical Analysis in Chemometrics [M]. Boca Raton: CRC Press, 2009.
[11] ESTEKI M, FARAJMAND B, KOLAHDERAZI Y, et al. Chromatographic fingerprinting with multivariate data analysis for detection and quantification of apricot kernel in almond powder[J]. Food Anal Method, 2017, 10:3312-3320.
[12] LI X F, XUJ P, WANG Y P, et al. The establishment of self-adaption algorithm of BP neural network and its application[J]. Theory Pract Sys Engin(系统工程理论与实践), 2004,24(5): 1-8.
[13] QIN H, LIN Z J, CHEN J W. The principle, analysis procedure and program of partial least squares regression[J]. J Mathem Med(数理医药学杂志), 2007, 20(4): 450-451.
[14] NIE P C, WU D, SUN D W, et al. Potential of visible and near infrared spectroscopy and pattern recognition for rapid quantification of notoginseng powder with adulterants[J]. Sensor, 2013, 13(10): 13820-13834.
[15] CAI J L, HUANG J Y, DENG W T, et al. Rapid determination of ethanol extracts content of Pogostemon cablin (Blanco) Benth. by near-infrared spectroscopy[J]. Chin Pharm J (中国药学杂志), 2012, 47(24): 2026-2028.
[16] CEN H Y, HE Y. Theory and application of near infrared reflectance spectroscopy in determination of food quality[J]. Trends Food Sci Tech, 2007, 18(2): 72-83.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
深圳市知识创新计划基础研究项目资助(JCYJ20170817141452019)
{{custom_fund}}