Rapid Identification of Calamina Based on Near-infrared Diffuse Reflectance Spectroscopy and PCA-SVM Algorithm

Long CHEN; Xiao-dong ZHANG; Yang-bo SUN; Ke-li CHEN

doi:10.13422/j.cnki.syfjx.20190747

您当前的位置：

首页 >

文章列表页 >

Rapid Identification of Calamina Based on Near-infrared Diffuse Reflectance Spectroscopy and PCA-SVM Algorithm

Pharmacy and Processing | 更新时间：2021-02-09

- Rapid Identification of Calamina Based on Near-infrared Diffuse Reflectance Spectroscopy and PCA-SVM Algorithm
- Chinese Journal of Experimental Traditional Medical Formulae Vol. 25, Issue 18, Pages: 116-123(2019)
- 作者机构：
  
  1.襄阳市中心医院，湖北文理学院附属医院，湖北　襄阳　 441021；
  2.湖北中医药大学　中药资源和中药复方教育部重点实验室，武汉　 430065
- 作者简介：
- 基金信息：
- DOI：10.13422/j.cnki.syfjx.20190747
  CLC： R22; R28; R9; O657; O433; C37
- Published：20 September 2019，
  
  Published Online：11 December 2018，
  
  Received：19 October 2018，
- 稿件说明：
扫描看全文
Long CHEN, Xiao-dong ZHANG, Yang-bo SUN, et al. Rapid Identification of Calamina Based on Near-infrared Diffuse Reflectance Spectroscopy and PCA-SVM Algorithm. [J]. Chinese Journal of Experimental Traditional Medical Formulae 25(18):116-123(2019)
DOI：

Long CHEN, Xiao-dong ZHANG, Yang-bo SUN, et al. Rapid Identification of Calamina Based on Near-infrared Diffuse Reflectance Spectroscopy and PCA-SVM Algorithm. [J]. Chinese Journal of Experimental Traditional Medical Formulae 25(18):116-123(2019) DOI： 10.13422/j.cnki.syfjx.20190747.

摘要

目的：

利用主成分分析(PCA)和支持向量机(SVM)算法，建立炉甘石生品、伪品及炮制品的近红外漫反射光谱(NIRS)鉴别模型。

方法：

采集炉甘石生品、伪品及炮制品的NIRS，选取特征谱段，优选光谱预处理方法及最佳主成分数，建立PCA-SVM鉴别模型。

结果：

在7 500～4 000 cm

－1

谱段，以一阶导数法(FD)为最佳光谱预处理方法，PCA提取的光谱前5个主成分为最佳主成分，并经网格搜索算法确定惩罚因子

＝0.25，核函数参数

＝8为最佳SVM内部参数，建立炉甘石PCA-SVM鉴别模型。该模型五折交叉验证准确率100%，且模型对训练集和测试集样品预测正确率亦均达100%。

结论：

基于PCA-SVM算法所建立的炉甘石NIRS鉴别模型预测准确率高，结合固体粉末漫反射技术无损、快速的优点，该模型可用于炉甘石生品、伪品及炮制品的无损、快速鉴别。

Abstract

Objective:

To establish a near-infrared diffuse reflectance spectroscopy(NIRS) identification model for crude products

counterfeit products and processed products of Calamina by principal component analysis(PCA) and support vector machine(SVM) algorithm.

Method:

NIRS of crude products

counterfeit products and processed products of Calamina were collected

the characteristic spectrum segments were selected

the preprocessing method and the optimum principal component number were optimized

and the PCA-SVM qualitative model was established.

Result:

The characteristic spectrum segment of analysis model was 7 500-4 000 cm

-1

.Spectra were preprocessed by the first-order derivative method(FD). The optimum principal component number was 5. And the optimum internal parameters of SVM[penalty factor(

)=0.25 and kernel function parameter(

)=8] were screened by applying the grid search algorithm.In the PCA-SVM qualitative model

the prediction accuracy rate was 100%for the 5-fold cross validation

and the prediction accuracy rates also were 100%both for training set and test set.

Conclusion:

PCA-SVM analysis model of NIRS for Calamina samples has a high prediction accuracy rate

and it can be used for the rapid and nondestructive identification of crude products

counterfeit products and processed products of Calamina by combining the diffuse reflection technique on solid powder.

关键词

炉甘石近红外漫反射光谱主成分分析支持向量机一阶导数法网格搜索算法五折交叉验证

Keywords

Calaminanear-infrared diffuse reflectance spectroscopyprincipal component analysissupport vector machinefirst-order derivative methodgrid search algorithm5-fold cross validation

references

国家中医药管理局《中华本草》编委会．中华本草[M]．上海：上海科技出版社，1999：382-383．

国家药典委员会．中华人民共和国药典．一部[M]．北京：中国医药科技出版社，2015：227．

周灵君，张丽，路长珍，等．市售生、煅炉甘石的成分分析及质量评价[J]．中国药房，2010，21(27)：2534-2536．

张杰红，刘友平，施学娇，等．市售炉甘石的化学成分及抑菌活性研究[J]．中药与临床，2011，2(6)：16-18．

周灵君，徐春蕾，张丽，等．炉甘石炮制机制研究[J]．中国中药杂志，2010，35(12)：1556-1559．

SUN Y B, CHEN L, HUANG B S, et al. A rapid identification method for calamine using near-infrared spectroscopy based on multi-reference correlation coefficient method and back propagation artificial neural network [J].Appl Spectrosc, 2017, 71(4): 1447-1456.

张晓冬，陈龙，白玉，等．近红外光谱结合主成分分析和聚类分析鉴别炉甘石生品、伪品和炮制品[J]．中国实验方剂学杂志，2018，24(12)：1-8．

明晶，陈龙，陈科力，等．基于近红外光谱和SVM算法对琥珀掺伪的定性鉴别与定量分析[J]．中药材，2017，40(1)：32-37．

魏从师，雷福汉，艾伟霞，等．基于NIRS技术和PCA-SVM算法6种树脂及其他类中药的快速鉴别[J]．中国实验方剂学杂志，2017，23(9)：17-23．

陈龙，袁明洋，陈科力．常见矿物药近红外漫反射光谱特征归纳与分析[J]．中国中药杂志，2016，41(19)：3528-3536．

陆婉珍，袁洪福，褚小立．近红外光谱仪器[M]．北京：化学工业出版社，2010：35-37．

尼珍，胡昌勤，冯芳．近红外光谱分析中光谱预处理方法的作用及其发展[J]．药物分析杂志，2008，28(5)：824-827．

Vapnik V N. The Nature of Statistical Learning Theory[M].New York: Springer, 1999: 988-999.

李盼池，许少华．支持向量机在模式识别中的核函数特性分析[J]．计算机工程与设计，2005，26(2)：302-304．

林升梁，刘志．基于RBF核函数的支持向量机参数选择[J]．浙江工业大学学报，2007，35(2)：163-167．

王健峰，张磊，陈国兴，等．基于改进的网格搜索法的SVM参数优化[J]．应用科技，2012，39(3)：28-31．

姚全珠，蔡婕．基于PSO的LS-SVM特征选择与参数优化算法[J]．计算机工程与应用，2010，46(1)：134-136．

杨旭，纪玉波，田雪．基于遗传算法的SVM参数选取[J]．辽宁石油化工大学学报，2004，24(1)：54-58．

徐子杰，陈龙，刘义梅，等．基于多参考相关系数法和BP-ANN建立紫石英的近红外光谱定性模型[J]．中国实验方剂学杂志，2017，23(22)：37-42．

史晶晶，张迪文，白雁，等．近红外光谱法快速测定酒女贞子中女贞苷含量[J]．中国实验方剂学杂志，2016，22(8)：69-73．

ZHANG X D, CHEN L, SUN Y B, et al. Determination of zinc oxide content of mineral medicine calamine using near-infrared spectroscopy based on MIV and BP-ANN algorithm [J].Spectrochim Acta A Mol Biomol Spectrosc, 2017, 193: 133-140.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Identification of Crude Products,Counterfeit Products and Processed Products of Calamina by Near Infrared Spectroscopy, Principal Component Analysis and Cluster Analysis

Meridian Tropism of Components in Bupleuri Radix Based on Nonalcoholic Steatohepatitis Model and Principal Component Analysis

Quality Evaluation of Aurantii Fructus Based on Fingerprint Qualitative Analysis， Multi-component Quantitative Analysis and Chemometrics

Prediction of Disintegration Time of Traditional Chinese Medicine Tablets Based on Generalized Regression Neural Network

Relationship Between Syndrome Elements and Therapy of Ischemic Stroke Based on Scale Hierarchy and Principal Component Analysis

Related Author

ZHANG Xiao-dong

CHEN Long

BAI Yu

CHEN Ke-li

Feihui HONG

Jiexin CHEN

Yuchan CHEN

Huimin LI

Related Institution

Key Laboratory of Basic and Application Research of Beiyao，Ministry of Education， Key Laboratory of Traditional Chinese Medicine （TCM） Pharmacodynamic Material Base， Heilongjiang University of Chinese Medicine

School of TCM， Guangdong Pharmaceutical University

Key Laboratory of Modern Preparation of Traditional Chinese Medicine， Ministry of Education， Jiangxi University of Chinese Medicine

The First Affiliated Hospital of Nanchang University

Engineering Research Center of Modern Chinese Medicine Discovery and Preparation Technique， Ministry of Education，Tianjin University of Traditional Chinese Medicine

Postal code：100700
Tel：010-84076882 Email：syfjx_2010@188.com
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备11006657号-10 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰