Systematic vs. stepwise parameter optimization for discriminant model development: A case study of differentiating Pinellia ternata from Pinellia pedatisecta with near infrared spectroscopy

Abstract

Near infrared (NIR) spectroscopy is an effective technique for adulteration detection in traditional Chinese medicine. The aim is to develop a discriminant model with the aid of chemometrics tools. The discriminant model is conventionally established by the means of stepwise optimization. This approach is often limited to trial-and-error and considered as a burden. In this study, a systematic optimization approach was proposed to develop the discriminant model with the aid of the design of experiment tools and applied to a case study of differentiating Pinellia ternata from Pinellia pedatisecta and adulterated Pinellia ternata using NIR spectroscopy. Spectral pretreatment, variable selection, and discriminant methods were identified as critical factors. The classification accuracy and no-error rate of the calibration set, cross-validation, and the prediction set were calculated to evaluate the performance of discriminant models. A full factorial design was applied to analyze the effect of critical factors at different levels on the model performance and optimize these factors. Three discriminant models including discriminant analysis coupled with principal component analysis (PCA-DA), partial least squares – discriminant analysis (PLS-DA), and k-nearest neighbors (KNN) were obtained by systematic optimization. The performance of PCA-DA and PLS-DA models obtained by systematic optimization was very good, and no samples were misclassified, which were better than those obtained by stepwise optimization. The performance of the KNN model obtained by systematic optimization was not desired and it was equal to that obtained by stepwise optimization. The results showed that Pinellia ternata could be successfully discriminated from Pinellia pedatisecta and adulterated Pinellia ternata by the PCA-DA and PLS-DA models. Compared to the stepwise optimization approach, the systematic optimization approach can improve the PCA-DA and PLS-DA model performance for differentiating Pinellia ternata from Pinellia pedatisecta and adulterated Pinellia ternata.

Keywords

Discriminant model design of experiment near infrared spectroscopy systematic optimization stepwise optimization

Get full access to this article

View all access options for this article.

References

Maki

Takahashi

and Shibata

An anti-emetic principle of Pinellia ternata tuber. Planta Med 1987; 53: 410–414.

Lee

Park

Lee

et al. Comprehensive chemical profiling of Pinellia species tuber and processed Pinellia tuber by gas chromatography-mass spectrometry and liquid chromatography-atmospheric pressure chemical ionization-tandem mass spectrometry. J Chromatogr A 2016; 1471: 164–177.

Zhang

Zhao

Cheng

et al. Metabonomic study of biochemical changes in the rat urine induced by Pinellia ternata (Thunb.) Breit. J Pharmaceut Biomed 2013; 85: 186–193.

Tomuta

Iovanov

Bodoki

et al. Development and validation of NIR-chemometric methods for chemical and pharmaceutical characterization of meloxicam tablets. Drug Dev Ind Pharm 2014; 40: 549–559.

Xie

Sun

Zhu

et al. Nondestructive measurements of freezing parameters of frozen porcine meat by NIR hyperspectral imaging. Food Bioprocess Tech 2016; 9: 1444–1454.

Márquez

López

Ruisánchez

et al. FT-Raman and NIR spectroscopy data fusion strategy for multivariate qualitative analysis of food fraud. Talanta 2016; 161: 80–86.

Macho

and Larrechi

MS.

Near-infrared spectroscopy and multivariate calibration for the quantitative determination of certain properties in the petrochemical industry. TrAC Trend Anal Chem 2012; 21: 799–806.

Lin

et al. NIR analysis for batch process of ethanol precipitation coupled with a new calibration model updating strategy. Anal Chim Acta 2012; 720: 22–28.

Xue

Yang

et al. Method validation for the analysis of licorice acid in the blending process by near infrared diffuse reflectance spectroscopy. Anal Methods 2015; 7: 5830–5837.

10.

Wei

Duan

et al. Vib Spectr 2012; 62: 17–22.

11.

Yang

et al. Determination of geographical origin and icariin content of Herba epimedii using near infrared spectroscopy and chemometrics. Spectrochim Acta A 2018; 191: 233–240.

12.

Sun

Zhang

et al. Determination of geographical origin and icariin content of Herba epimedii using near infrared spectroscopy and chemometrics. Spectrochim Acta A 2017; 171: 72–79.

13.

Zhao

Zhang

et al.

Optimization of Parameter Selection for Partial Least Squares Model Development.

Sci Rep 2015; 5: 11647.

14.

Rozet

Lebrun

Hubert

et al.

Design Spaces for analytical methods.

TrAC-Trend Anal Chem 2013; 42: 157–167.

15.

Dai

Zhang

et al. Establishment and reliability evaluation of the design space for HPLC analysis of six alkaloids in Coptis chinensis (Huanglian) using Bayesian approach. Chin J Nat Med 2016; 14: 697–708.

16.

Lachenmeier

DW.

Rapid quality control of spirit drinks and beer using multivariate data analysis of Fourier transform infrared spectra.

Food Chem 2007; 101: 825–832.

17.

Pierna

Wahl

De Noord

et al. Methods for outlier detection in prediction. Chemom Intell Lab Syst 2002; 63: 27–39.

18.

Liang

Cao

et al. Model-population analysis and its applications in chemical and biological modeling. TrAC-Trend Anal Chem 2012; 38: 154–162.

19.

Zhang

Meratnia

and Havinga

Outlier detection techniques for wireless sensor networks: A survey. IEEE Commun Surv Tut 2010; 12: 159–170.

20.

Wold

Esbensen

and Geladi

Principal component analysis. Chemom Intell Lab Syst 1987; 2: 37–52.

21.

The American Society for Testing and Materials (ASTM). Practice E1655-00. West Conshohocken, PA: ASTM Annual Book of Standards, 2000.

22.

Valderrama

Braga

JWB

and Poppi

RJ.

Variable selection, outlier detection, and figures of merit estimation in a partial least-squares regression multivariate calibration model. A case study for the determination of quality parameters in the alcohol Industry by Near-infrared Spectroscopy. J Agr Food Chem 2007; 55: 8331–8338.

23.

Silva

MAM

Ferreira

Braga

JWB

et al. Development and analytical validation of a multivariate calibration method for determination of amoxicillin in suspension formulations by near infrared spectroscopy. Talanta 2012; 89: 342–351.

24.

de Groot

Postma

Melssen

et al. Selecting a representative training set for the classification of demolition waste using remote NIR sensing. Anal Chim Acta 1999; 392: 67–75.

25.

Galvao

Araujo

Jose

et al. A method for calibration and validation subset partitioning. Talanta 2005; 67: 736–740.

26.

Mao

KZ.

Orthogonal forward selection and backward elimination algorithms for feature subset selection. IEEE Trans Syst Man Cybern B Cybern 2004; 34: 629–634.

27.

Zhao

Huang

et al. Pharmaceutical analysis model robustness from bagging-PLS and PLS using systematic tracking mapping. Front Chem 2018; 6: 262.

28.

Andersen

and Bro

Variable selection in regression—a tutorial. J Chemometr 2010; 24: 728–737.

29.

Xiaobo

Jiewen

Povey

et al. Variables selection methods in near-infrared spectroscopy. Anal Chim Acta 2010; 667: 14–32.

30.

Savitzky

and Golay

MJ.

Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 1964; 36: 1627–1639.

31.

Crumpton

Isenhart

and Mitchell

PD.

Nitrate and organic N analyses with second-derivative spectroscopy. Limnol Oceanogr 1992; 37: 907–913.

32.

Jain

Nandakumar

K and

Ross

Score normalization in multimodal biometric systems. Pattern Recogn 2005; 38: 2270–2285.

33.

Helland

Næs

and Isaksson

Related versions of the multiplicative scatter correction method for preprocessing spectroscopic data. Chemom Intell Lab Syst 1995; 29: 233–241.

34.

Barnes

Dhanoa

and Lister

SJ.

Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra. Appl Spectrosc 1989; 43: 772.

35.

Rinnan

van den Berg

and Engelsen

SB.

Review of the most common pre-processing techniques for near-infrared spectra. TrAC-Trend Anal Chem 2009; 28: 1201–1222.

36.

Cai

and Shao

A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra. Chemom Intell Lab Syst 2008; 90: 188–194.

37.

Leardi

R and

Nørgaard

Sequential application of backward interval partial least squares and genetic algorithms for the selection of relevant spectral regions. J Chemometr 2004; 18: 486–497.

38.

Liang

et al. Key wavelength screening using competitive adaptive reweighted sampling method for multivariate calibration. Anal Chim Acta 2009; 648: 77–84.

39.

Wang

et al. Noise incorporated subwindow permutation analysis for informative gene selection using support vector machines. Analyst 2011; 136: 1456–1463.

40.

Deb

Pratap

Agarwal

et al. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation. 2002; 6: 182–197.

41.

Farres

Platikanov

Tsakovski

et al. Comparison of the variable importance in projection (VIP) and of the selectivity ratio (SR) methods for variable selection and interpretation. J Chemometr 2015; 29: 528–536.

42.

Bro

and Smilde

AK.

Principal component analysis. Anal Methods 2014; 6: 2812–2831.

43.

Roggo

Chalus

Maurer

et al. A review of near infrared spectroscopy and chemometrics in pharmaceutical technologies. J Pharm Biomed Anal 2007; 44: 683–700.

44.

Suzuki

Kusano

Takahashi

et al. Rice-Arabidopsis FOX line screening with FT-NIR-based fingerprinting for GC-TOF/MS-based metabolite profiling. Metabolomics 2010; 6: 137–145.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.91 MB