Study on the Optimization Limit of Near-infrared Spectroscopy Calibration Model by Variable Selection Methods

PAN Zheng-hao; WANG Peng; CHEN Kun-yan; LI Qiu-tong; TANG Jie; YANG Jun; SHAO Li-min

doi:10.19969/j.fxcsxb.23082802

您当前的位置：

首页 >

文章列表页 >

Study on the Optimization Limit of Near-infrared Spectroscopy Calibration Model by Variable Selection Methods

Experimental Techniques and Methods | 更新时间：2023-12-25

- Study on the Optimization Limit of Near-infrared Spectroscopy Calibration Model by Variable Selection Methods
- Journal of Instrumental Analysis Vol. 42, Issue 12, Pages: 1659-1665(2023)
- 作者机构：
  
  1.中国科学技术大学化学与材料科学学院，安徽合肥 230026
  2.重庆中烟工业有限责任公司技术中心，重庆 400060
- 作者简介：
- 基金信息：
- DOI：10.19969/j.fxcsxb.23082802
  CLC：
扫描看全文
潘正豪,王鹏,陈昆燕等.变量选择方法对近红外光谱校正模型优化极限的研究[J].分析测试学报,2023,42(12):1659-1665.

PAN Zheng-hao,WANG Peng,CHEN Kun-yan,et al.Study on the Optimization Limit of Near-infrared Spectroscopy Calibration Model by Variable Selection Methods[J].Journal of Instrumental Analysis,2023,42(12):1659-1665.
潘正豪,王鹏,陈昆燕等.变量选择方法对近红外光谱校正模型优化极限的研究[J].分析测试学报,2023,42(12):1659-1665. DOI： 10.19969/j.fxcsxb.23082802.

PAN Zheng-hao,WANG Peng,CHEN Kun-yan,et al.Study on the Optimization Limit of Near-infrared Spectroscopy Calibration Model by Variable Selection Methods[J].Journal of Instrumental Analysis,2023,42(12):1659-1665. DOI： 10.19969/j.fxcsxb.23082802.

摘要

变量选择经常被用于优化近红外光谱线性校正模型，消除冗余信息，提升回归的准确性和可解释性。该文研究并设计了一种基于蒙特卡洛的方法，用于评估不同线性校正方法在变量选择的子空间中能达到的最优程度，寻找变量选择对线性校正模型的优化极限。该方法通过获得验证指标——预测均方根误差（RMSEP）的分布图，揭示变量选择方法在数据集上的优化效果与优化极限。将该方法应用于3组样品的近红外光谱建模研究，结果表明：在烟草-果胶数据集上的可优化率约为24.98%，RMSEP降低了15.2%；在小麦-蛋白质数据集上的可优化率约为13.90%，RMSEP降低了9.5%；在玉米-淀粉数据集上的可优化率约为14.05%，RMSEP降低了57.1%。应用该方法可以快速得到变量选择方法在模型上的优化极限，为变量选择方法的设计、应用和评估提供参考。

Abstract

Variable selection is often used to optimize linear calibration models for NIR spectroscopy，eliminating redundant information and improving the accuracy and interpretability of regression. In this paper，a Monte Carlo-based method is studied and designed to find the optimal limit of variable selection for linear calibration models，and can evaluate the optimal degree that different linear calibration methods（such as partial least squares regression PLSR） can achieve in the subspace of variable selection. In this study，the distribution plot of the root mean square error prediction（RMSEP） of the validation metric is obtained，and the optimization effect and optimization limit of the variable selection methods on the dataset are revealed. The method was applied to the near-infrared spectroscopy modeling of three datasets，and the results showed that the optimizable rate on the tobacco-pectin dataset was about 24.98%，and the prediction error RMSEP was reduced by 15.2%. The optimizable rate on the wheat-protein dataset is about 13.90%，and the prediction error RMSEP is reduced by 9.5%. The optimizable on the corn-starch dataset is about 14.05%，and the prediction error RMSEP is reduced by 57.1%. The application of this method can quickly obtain the optimization limit of the variable selection methods on the model，and provide reference for the design，application and evaluation of the variable selection methods.

关键词

化学计量学近红外光谱化学校正线性模型变量选择蒙特卡洛方法

Keywords

chemometricsnear-infrared spectroscopychemical calibrationlinear modelvariable selectionMonte Carlo method

references

Yukihiro O，Christian H，Satoru T，Søren B E. Near-infrared Spectroscopy. Singapore：Springer Singapore，2021：331-345.

Grassi S，Casiraghi E. Foods，2022，11：1250.

Callery E L，Rowbottom A W. Appl. Spectrosc. Rev.，2022，57（5）：411-440.

Chu X L，Huang Y，Yun Y H，Bian X H. Chemometric Methods in Analytical Spectroscopy Technology. Singapore：Springer Nature Singapore，2022：169-207.

Yun Y H，Li H D，Deng B C，Cao D S. Trends Anal. Chem.，2019，113：102-115.

Wang H P，Chen P，Dai J W，Liu D，Li J Y，Xu Y P，Chu X L. Trends Anal. Chem.，2022，153：116648.

Wold S，Sjostrom M，Eriksson L. Chemom. Intell. Lab. Syst.，2001，58（2）：109-130.

Xu H，Liu Z C，Cai W S，Shao X G. Chemom. Intell. Lab. Syst.，2009，97（2）：189-193.

Zou X B，Zhao J W，Li Y X. Vib. Spectrosc.，2007，44（2）：220-227.

Yun Y H，Wang W T，Deng B C，Lai G B，Liu X B，Ren D B，Liang Y Z，Fan W，Xu Q S. Anal. Chim. Acta，2015，862：14-23.

Leardi R. J. Chemom.，2000，14：643-655.

Kirkpatrick S，Gelatt C D，Vecchi M P. Science，1983，220（4598）：671-680.

Li H D，Liang Y Z，Xu Q S，Cao D S. Anal. Chim. Acta，2009，648（1）：77-84.

Cai W S，Li Y K，Shao X G. Chemom. Intell. Lab. Syst.，2008，90（2）：188-194.

Yun Y H，Li H D，Leslie E W，Fan W，Wang J J，Cao D S，Xu Q S，Liang Y Z. Spectrochim. Acta A，2013，111：31-36.

Norgaard L，Saudland A，Wagner J，Nielsen J P，Munck L，Engelsen S B. Appl. Spectrosc.，2000，54（3）：413-419.

Ciurczak E W. Handbook of Near-infrared Analysis. 4th ed. Boca Raton：CRC Press/Taylor & Francis Group，2021.

Brown S. Comprehensive Chemometrics：Chemical and Biochemical Data Analysis. Second edition. Amsterdam，Oxford， Cambridge，MA：Elsevier，2020.

Zhang J，Hu Y，Zhou L X，Li B Y. J. Instrum. Anal.（张进，胡芸，周罗雄，李博岩. 分析测试学报），2020，39（10）：1196-1203.

DB53/T 497-2013. Tobacco and Tobacco Products-Main Chemical Composition Indicators-Guidelines for the Establishment and Validation of Near-infrared Calibration Models. Local Standards in Yunnan Province（烟草及烟草制品主要化学成分指标近红外校正模型建立与验证导则. 云南省地方标准）.

Galvão R K H，Araujo M S U，José G M，Pontes M J C，Silva E C，Saldanha T C B. Talanta，2005，67（4）：736-740.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Progress of Chemometric Algorithms in Near infrared Spectroscopic Analysis

Rapid Determination of Antioxidant Activity from Sargassum Fusiforme Using Near-infrared Spectroscopy Combined with Chemometrics

A Variable Selection Method for Near-infrared Spectroscopy Based on Iterative Shrinkage Window Bootstrapping Soft Shrinkage Algorithm

Related Author

No data

Related Institution

贵州医科大学公共卫生学院环境污染与疾病监控教育部重点实验室

贵州医科大学食品科学学院

贵州中烟工业有限责任公司技术中心

College of Life and Environmental Science，Wenzhou University

Key Laboratory of Water Environment and Marine Biological Resources Protection of Zhejiang Province

Address：100 Xianlie Middle Road, Guangzhou Postal code：510070
Tel：020-87684776,37656606 Fax：020-87684776 Email：fxcsxb@china.com
Technical support is provided by Beijing Founder electronics co., LTD 粤ICP备12017312号-3 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