复杂体系近红外光谱建模方法研究
|
摘要
近红外光谱分析以样品前处理简单、快速、无损、绿色等优势在分析科学领域备受关注。由于信息提取困难，近红外光谱需要借助化学计量学方法进行定性、定量分析。多元校正是常用的化学计量学方法，利用它可以建立近红外光谱和待测目标的定量模型，直接对复杂样品进行分析。本论文围绕复杂体系近红外光谱建模分析中奇异样本识别、变量选择及建模方法等问题展开了研究工作，并针对实际样品开展了应用研究。
排序变量选择法是一种基于信息向量的方法。本论文将多模型共识思想引入排序变量选择法，提出一种共识排序变量选择法。该方法利用排序变量选择法建立多个模型，然后利用加权方法计算共识模型结果。由于加权方式对最终结果影响较大，方法中考察了三种加权方式，为结果的确定提供了指导。通过对三组近红外光谱数据的分析表明，共识排序变量选择法可以用于提高近红外光谱定量模型的预测能力。
提出了一种双共识多模型建模方法用于提高多模型共识方法的预测能力。在建立子模型前，该方法用无信息变量消除和连续投影算法建立代表性强、共线性小的变量子集。建立子模型时，先用蒙特卡洛采样法选择样品子集，再用交叉验证选择变量子集建立子模型。通过迭代该过程，可以得到多个子模型，用这些子模型的平均结果作为共识结果。由于建立子模型过程同时分析了建模变量和建模样品，子模型的预测精度和差异都得到了提高。通过对两组烟草样品近红外光谱建模分析表明，双共识模型可以用于提高多模型共识方法的预测能力。
变量选择方法一般计算量较大、耗时长。稀疏偏最小二乘回归方法在偏最小二乘回归建模过程嵌入变量选择步骤，在不显著增加计算量的基础上降低了无信息变量对模型的影响，提高了建模分析的预测精度。本论文提出了一种基于协方差的稀疏偏最小二乘回归方法，用于改进稀疏偏最小二乘回归方法的变量确定方式。通过三组近红外光谱数据和一组拉曼光谱数据的分析表明，基于协方差的稀疏偏最小二乘回归方法选择的变量少，预测误差小。
偏最小二乘回归的预测结果由多个隐变量（latent variable）决定。奇异样本的预测值在隐变量上的分布规律与正常样本有较大差异，基于这种差异提出了一种基于模型检验的奇异样本识别方法。该方法首先计算每个样品在隐变量上的预测值，然后利用局部异常因子方法分析样品是否奇异。通过对三组近红外光谱数据的分析发现，基于模型检验的奇异样本识别方法可以用于提高复杂体系近红外光谱分析的预测能力。通过分析还发现，奇异样本对大样本数据的影响较小。
利用间接模型的方法可以降低近红外光谱分析的检测限。基于间接模型原理，本论文研究了用近红外光谱法测定四种烟草产品特有的N-亚硝胺类化合物（TSNAs）的方法。为了优化模型降低误差，比较了预处理方法对预测结果的影响，发现背景扣除和光散射效应校正可以优化模型、降低误差；通过变量选择可以精简模型，显著提高模型的预测能力。通过对一组独立的预测集样品和一组不同年份样品的分析发现，偏最小二乘回归模型的预测结果和气相色谱-热能分析方法结果相一致。尽管部分低浓度样品的相对误差较大，但是该方法为烟草行业提供了一种简单、无损、快速测定TSNAs的方式。
Near-infrared (NIR) spectroscopy has been widely used in analyticalscience due to its fastness, accuracy, green and simplicity. Because it isdifficult to extract quantitative informations from NIR spectra,chemometric methods, such as multivariate calibration, have beenextensively used. Quantitative models between spectra and target can beobtained through multivariate calibration, and the model can be used toanalyze unknowing samples. In order to build robust NIR quantitativemodels, works on variable selection, consensus methods, outlierdetection and etc. were studied in this dissertation.
A consensus orderd predictor selection method is proposed fordealing with the NIR spectra of complex systems. In this method, theconsensus result is used as the prediction result and the influence of threeweighted methods on the consensus result was investigated. The superiority of the proposed method was demonstrated throuth three NIRspectra datasets.
A strategy for improving the performance of consensus methods inmultivariate calibration of NIR spectra is proposed. In the approach, asubset of non-collinear variables is generated using successiveprojections algorithm (SPA) for each variable in the reduced spectra byuninformative variables elimination (UVE). Then sub-models are builtfor each variable subset using the calibration subset determined by MonteCarlo (MC) re-sampling, and the sub-model that produces minimal errorin cross validation is selected as a member model. With repetition of theMC re-sampling, a series of member models are built and a consensusmodel is achieved by averaging all the member models. Since membermodels are built with the best variable subset and the randomly selectedcalibration subset, both the quality and the diversity of the membermodels are insured for the consensus model. Two NIR spectral datasets of tobacco lamina are used to investigate the proposed method. Thesuperiority of the method in both accuracy and reliability isdemonstrated.
Sparse partial least squares method builds multivariate calibrationmodels with selected informative variables. A modified sparse partialleast squares method based on covariance is proposed for NIRspectroscopic analysis. In the method, uninformative variables areeliminated in modeling process based on the convariance between thespectra and target. Compared with the conventional sparse partial leastsquares method, the proposed method is more parsimonious and accuracy.With three NIR datasets and a Raman spectroscopic dataset, the methodis proved to be a potential way to dealing with uninformative variables incomplex spectroscopic analysis.
An outlier detection method is proposed for near infrared spectralanalysis. The method is based on the definition of outlier and the principle of partial least squares (PLS) regression, i.e., an outlier in adataset behaves differently from the rest, and the prediction result of aPLS model is an accumulation of several independent latent variables.Therefore, the proposed method builds a PLS model with a calibrationdataset, and then the contribution of each latent variable is investigated.Outliers can be detected by comparing these contributions. Three datasets,including three NIR datasets of gasoline, beverage and tobacco lamina,are adopted for testing the method. It is found that the quality of themodels can be improved after removing the outliers detected by themethod.
Indirect modeling of trace components in real samples by use ofnear-infrared spectroscopy has gained much interest, because it mayprovide a rapid way for analyzing the industrial or agricultural products.Coupling near-infrared diffusive reflectance spectroscopy andchemometric techniques, a method for rapid analysis of four kinds tobacco specific N-nitrosamines (TSNAs) and their total content isstudied in this work. For optimization of the models, techniques forspectral preprocessing and variable selection are adopted and compared.It is found that removing the varying background and the correction ofthe multiplicative scattering effect in the spectra are important in themodeling, and variable selection can significantly improve the models.For validation of the models, the TSNA contents of independent testsamples and tobacco leaves harvested in different year are predicted.Consistent results are obtained between the reference contents byGC/TEA analysis and the predicted ones. Although the relative errors forsome low content samples are not so satisfactory, the method is apractical alternative for industrial analysis due to the non-destructive andrapid nature of the method.
排序变量选择法是一种基于信息向量的方法。本论文将多模型共识思想引入排序变量选择法，提出一种共识排序变量选择法。该方法利用排序变量选择法建立多个模型，然后利用加权方法计算共识模型结果。由于加权方式对最终结果影响较大，方法中考察了三种加权方式，为结果的确定提供了指导。通过对三组近红外光谱数据的分析表明，共识排序变量选择法可以用于提高近红外光谱定量模型的预测能力。
提出了一种双共识多模型建模方法用于提高多模型共识方法的预测能力。在建立子模型前，该方法用无信息变量消除和连续投影算法建立代表性强、共线性小的变量子集。建立子模型时，先用蒙特卡洛采样法选择样品子集，再用交叉验证选择变量子集建立子模型。通过迭代该过程，可以得到多个子模型，用这些子模型的平均结果作为共识结果。由于建立子模型过程同时分析了建模变量和建模样品，子模型的预测精度和差异都得到了提高。通过对两组烟草样品近红外光谱建模分析表明，双共识模型可以用于提高多模型共识方法的预测能力。
变量选择方法一般计算量较大、耗时长。稀疏偏最小二乘回归方法在偏最小二乘回归建模过程嵌入变量选择步骤，在不显著增加计算量的基础上降低了无信息变量对模型的影响，提高了建模分析的预测精度。本论文提出了一种基于协方差的稀疏偏最小二乘回归方法，用于改进稀疏偏最小二乘回归方法的变量确定方式。通过三组近红外光谱数据和一组拉曼光谱数据的分析表明，基于协方差的稀疏偏最小二乘回归方法选择的变量少，预测误差小。
偏最小二乘回归的预测结果由多个隐变量（latent variable）决定。奇异样本的预测值在隐变量上的分布规律与正常样本有较大差异，基于这种差异提出了一种基于模型检验的奇异样本识别方法。该方法首先计算每个样品在隐变量上的预测值，然后利用局部异常因子方法分析样品是否奇异。通过对三组近红外光谱数据的分析发现，基于模型检验的奇异样本识别方法可以用于提高复杂体系近红外光谱分析的预测能力。通过分析还发现，奇异样本对大样本数据的影响较小。
利用间接模型的方法可以降低近红外光谱分析的检测限。基于间接模型原理，本论文研究了用近红外光谱法测定四种烟草产品特有的N-亚硝胺类化合物（TSNAs）的方法。为了优化模型降低误差，比较了预处理方法对预测结果的影响，发现背景扣除和光散射效应校正可以优化模型、降低误差；通过变量选择可以精简模型，显著提高模型的预测能力。通过对一组独立的预测集样品和一组不同年份样品的分析发现，偏最小二乘回归模型的预测结果和气相色谱-热能分析方法结果相一致。尽管部分低浓度样品的相对误差较大，但是该方法为烟草行业提供了一种简单、无损、快速测定TSNAs的方式。
Near-infrared (NIR) spectroscopy has been widely used in analyticalscience due to its fastness, accuracy, green and simplicity. Because it isdifficult to extract quantitative informations from NIR spectra,chemometric methods, such as multivariate calibration, have beenextensively used. Quantitative models between spectra and target can beobtained through multivariate calibration, and the model can be used toanalyze unknowing samples. In order to build robust NIR quantitativemodels, works on variable selection, consensus methods, outlierdetection and etc. were studied in this dissertation.
A consensus orderd predictor selection method is proposed fordealing with the NIR spectra of complex systems. In this method, theconsensus result is used as the prediction result and the influence of threeweighted methods on the consensus result was investigated. The superiority of the proposed method was demonstrated throuth three NIRspectra datasets.
A strategy for improving the performance of consensus methods inmultivariate calibration of NIR spectra is proposed. In the approach, asubset of non-collinear variables is generated using successiveprojections algorithm (SPA) for each variable in the reduced spectra byuninformative variables elimination (UVE). Then sub-models are builtfor each variable subset using the calibration subset determined by MonteCarlo (MC) re-sampling, and the sub-model that produces minimal errorin cross validation is selected as a member model. With repetition of theMC re-sampling, a series of member models are built and a consensusmodel is achieved by averaging all the member models. Since membermodels are built with the best variable subset and the randomly selectedcalibration subset, both the quality and the diversity of the membermodels are insured for the consensus model. Two NIR spectral datasets of tobacco lamina are used to investigate the proposed method. Thesuperiority of the method in both accuracy and reliability isdemonstrated.
Sparse partial least squares method builds multivariate calibrationmodels with selected informative variables. A modified sparse partialleast squares method based on covariance is proposed for NIRspectroscopic analysis. In the method, uninformative variables areeliminated in modeling process based on the convariance between thespectra and target. Compared with the conventional sparse partial leastsquares method, the proposed method is more parsimonious and accuracy.With three NIR datasets and a Raman spectroscopic dataset, the methodis proved to be a potential way to dealing with uninformative variables incomplex spectroscopic analysis.
An outlier detection method is proposed for near infrared spectralanalysis. The method is based on the definition of outlier and the principle of partial least squares (PLS) regression, i.e., an outlier in adataset behaves differently from the rest, and the prediction result of aPLS model is an accumulation of several independent latent variables.Therefore, the proposed method builds a PLS model with a calibrationdataset, and then the contribution of each latent variable is investigated.Outliers can be detected by comparing these contributions. Three datasets,including three NIR datasets of gasoline, beverage and tobacco lamina,are adopted for testing the method. It is found that the quality of themodels can be improved after removing the outliers detected by themethod.
Indirect modeling of trace components in real samples by use ofnear-infrared spectroscopy has gained much interest, because it mayprovide a rapid way for analyzing the industrial or agricultural products.Coupling near-infrared diffusive reflectance spectroscopy andchemometric techniques, a method for rapid analysis of four kinds tobacco specific N-nitrosamines (TSNAs) and their total content isstudied in this work. For optimization of the models, techniques forspectral preprocessing and variable selection are adopted and compared.It is found that removing the varying background and the correction ofthe multiplicative scattering effect in the spectra are important in themodeling, and variable selection can significantly improve the models.For validation of the models, the TSNA contents of independent testsamples and tobacco leaves harvested in different year are predicted.Consistent results are obtained between the reference contents byGC/TEA analysis and the predicted ones. Although the relative errors forsome low content samples are not so satisfactory, the method is apractical alternative for industrial analysis due to the non-destructive andrapid nature of the method.
引文
[1]严衍禄,赵龙莲,韩东海等.近红外光谱分析基础与应用.北京:中国轻工业出版社,2005,286~563
[2]陆婉珍,袁洪福,徐广通等.现代近红外光谱分析技术.北京:中国石化出版社,2007,193~247
[3]刘建学.实用近红外光谱分析技术.北京:科学出版社,2008,158~239
[4] Massart D L. Chemometrics: a textbook. Amsterdam: ElsevierScience,1988,5~9
[5] Chau F. Chemometrics: from basics to wavelet transform. Hoboken:Wiley-Interscience,2004,5~12
[6] Brown S D, Tauler R, Walczak B. Comprehensive chemometrics:chemical and biochemical data analysis. Amsterdam: Elsevier,2009,459~463
[7] Martens H, Naes T. Multivariate calibration. Hoboken: John Wiley&Sons Inc,1992,1~30
[8] N s T, Isaksson T, Fearn T, et al. A user friendly guide to multivariatecalibration and classification. Chichester UK: NIR Publications,2002,11~17
[9] Brereton R G. Introduction to multivariate calibration in analyticalchemistry. Analyst,2000,125:2125~2154
[10] Williams P, Norris K. Near-infrared technology in the agriculturaland food industries. Minnesota: American Association of CerealChemists,1987
[11] Weisberg S. Applied linear regression, Third edition. Hoboken:Wiley Online Library,2005,211~230
[12] Hawkins D M. On the investigation of alternative regressions byprincipal component analysis. Appl Statist,1973,22:275~286
[13] N s T, Martens H. Principal component regression in NIR analysis:viewpoints, background details and selection of components. JChemometr,1988,2:155~167
[14] Sutter J M, Kalivas J H, Lang P M. Which principal components toutilize for principal component regression. J Chemometr,1992,6:217~225
[15] Depczynski U, Frost V J, Molt K. Genetic algorithms applied to theselection of factors in principal component regression. Anal ChimActa,2000,420:217~227
[16] Chang C W, Laird D A, Mausbach M J, Hurburgh Jr C R.Near-infrared reflectance spectroscopy-principal componentsregression analyses of soil properties. Soil Sci Soc Am J,2001.65:480~490
[17] Otsuka M. Comparative particle size determination of phenacetinbulk powder by using Kubelka-Munk theory and principalcomponent regression analysis based on near-infrared spectroscopy.Powder Technol,2004,141:244~250
[18]邵学广,蔡文生.化学信息学.北京:科学出版社,2005,206~207
[19] Vinzi V E, Chin W W, Henseler J. Handbook of partial least squares:Concepts, methods and applications. Berlin: Springer Verlag,2009,32~38
[20] Wold H. Partial least squares. Int J Cardiol,1985,147:581~591
[21] Geladi P, Kowalski B R. Partial least-squares regression: a tutorial.Anal Chim Acta,1986,185:1~17
[22] Wold S, Sjostrom M, Eriksson L. PLS-regression: a basic tool ofchemometrics. Chemometrics Intell Lab Syst,2001,58:109~130
[23] de Jong S. SIMPLS: an alternative approach to partial least squaresregression. Chemometrics Intell Lab Syst,1993,18:251~263
[24] Kvalheim O M, Karstang T V. Interpretation of latent variableregression models. Chemometrics Intell Lab Syst.1989,7:39~51
[25]Trygg J, Wold S. Orthogonal projections to latent structures (O-PLS).J Chemometr,2002,16:119~128
[26] Cloarec O, Dumas M E, Trygg J, et al. Evaluation of the orthogonalprojection on latent structure model limitations caused by chemicalshift variability and improved visualization of biomarker changes in1H NMR spectroscopic metabonomic studies. Anal Chem,2005,77:517~526
[27] Walczak B, Massart D L. The Radial Basis Functions--Partial LeastSquares approach as a flexible non-linear regression technique. AnalChim Acta,1996,331:177~185
[28] Rosipal R. Kernel partial least squares for nonlinear regression anddiscrimination. Neural Netw World,2003,13:291~300
[29] Chen D, Hu X G, Shao X G, et al. Variable selection by modifiedIPW (iterative predictor weighting)-PLS (partial least squares) incontinuous wavelet regression models. Analyst,2004,129:664~669
[30] Xu H, Cai W S, Shao X G. Weighted partial least squares regressionby variable grouping strategy for multivariate calibration of nearinfrared spectra. Anal Methods,2010,2:289~294
[31] Comon P. Independent component analysis, a new concept? SignalProcess,1994,36:287~314
[32] Hyvarinen A, Oja E. Independent component analysis: algorithmsand applications. Neural Netw,2000,13:411~430
[33] Wang G Q, Ding Q Z, Hou Z Y. Independent component analysisand its applications in signal processing for analytical chemistry.Trac-Trends Anal Chem,2008,27:368~376
[34] Shao X G, Liu Z C, Cai W S. Resolving multi-componentoverlapping GC-MS signals by immune algorithms. Trac-TrendsAnal Chem,2009,28:1312~1321
[35] Gustafsson M G. Independent component analysis yields chemicallyinterpretable latent variables in multivariate regression. J Chem InfModel,2005,45:1244~1255
[36] Shao X G, Wang W, Hou Z Y, et al. A new regression method basedon independent component analysis. Talanta,2006,69:676~680
[37] Zhang Y W, Zhang Y. Complex process monitoring using modifiedpartial least squares method of independent component regression.Chemometrics Intell Lab Syst,2009,98:143~148
[38] Al-Mbaideen A, Benaissa M. Coupling subband decomposition andindependent component regression for quantitative NIRspectroscopy. Chemometrics Intell Lab Syst,2011,108:112~122
[39] Parastar H, Jalali-Heravi M, Tauler R. Is Independent ComponentAnalysis appropriate for multivariate resolution in analyticalchemistry? Trac-Trends Anal Chem,2011.31:134~143
[40] Bouveresse D, Moya-González A, Ammari F, et al. Two novelmethods for the determination of the number of components inindependent components analysis models. Chemometrics Intell LabSyst,2012,112:24~32
[41] Candolfi A, De Maesschalck R, Jouan-Rimbaud D, et al. Theinfluence of data pre-processing in the pattern recognition ofexcipients near-infrared spectra. J Pharm Biomed Anal,1999,21:115~132
[42] Azzouz T, Puigdoménech A, Aragay M, et al. Comparison betweendifferent data pre-treatment methods in the analysis of foragesamples using near-infrared diffuse reflectance spectroscopy andpartial least-squares multivariate calibration method. Anal ChimActa,2003,484:121~134
[43] Rinnan A, van den Berg F, Engelsen S B. Review of the mostcommon pre-processing techniques for near-infrared spectra.Trac-Trends Anal Chem,2009,28:1201~1222
[44] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[45] Martens H, Stark E. Extended multiplicative signal correction andspectral interference subtraction: new preprocessing methods fornear infrared spectroscopy. J Pharm Biomed Anal,1991,9:625~635
[46] Martens H, Nielsen J P, Engelsen S B. Light scattering and lightabsorbance separated by extended multiplicative signal correction.Application to near-infrared transmission analysis of powdermixtures. Anal Chem,2003,75:394~404
[47] Barnes R, Dhanoa M, Lister S J. Standard normal variatetransformation and de-trending of near-infrared diffuse reflectancespectra. Appl Spectrosc,1989,43:772~777
[48] Dhanoa M S, Lister S J, Sanderson R, et al. The link betweenmultiplicative scatter correction (MSC) and standard normal variate(SNV) transformations of NIR spectra. J Near Infrared Spectrosc,1994,2:43~47
[49] Fearn T, Riccioli C, Garrido-Varo A, et al. On the geometry of SNVand MSC. Chemometrics Intell Lab Syst,2009,96:22~26
[50] Savitzky A, Golay M J E. Smoothing and differentiation of data bysimplified least squares procedures. Anal Chem,1964,36:1627~1639
[51] Steinier J, Termonia Y, Deltour J. Smoothing and differentiation ofdata by simplified least square procedure. Anal Chem,1972,44:1906~1909
[52] Shao X G, Pang C Y, Su Q D. A novel method to calculate theapproximate derivative photoacoustic spectrum using continuouswavelet transform. Fresen J Anal Chem,2000,367:525~529
[53] Shao X G, Cai W S. Wavelet analysis in analytical chemistry. RevAnal Chem,1998,17:235~285
[54] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[55] Shao X G, Gu H, Cai W S, et al. Studies on data compression of1-DNMR spectra using wavelet transform. Spectrosc Spectr Anal,1999,19:139~141
[56] Wang L S, Yang X Y, Xi S F, et al. Wavelet Smoothing andDenoising to Process Capillary Electrophoresis Signals. Chem JChin Univ,1999,3:383~386
[57] Shao X G, Cai W S, Pan Z X. Wavelet transform and its applicationsin high performance liquid chromatography (HPLC) analysis.Chemometrics Intell Lab Syst,1999,45:249~256
[58] Shao X G, Shao L M, Zhao G W. Extraction of extended X-rayabsorption fine structure information from the experimental datausing the wavelet transform. Anal Commun1998,35:135~137
[59] Wolkenstein M, Hutter H, Nikolov S G, Grasserbauer M.Improvement of SIMS image classification by means of waveletde-noising. Fresenius J Anal Chem,1997,357:783~788
[60] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear-infrared spectra. Chemometrics Intell Lab Syst,1998,44:175~185
[61] Chen D, Wang F, Shao X G, et al. Elimination of interferenceinformation by a new hybrid algorithm for quantitative calibrationof near infrared spectra. Analyst,2003,128:1200~1203
[62] Woody N A, Feudale R N, Myles A J, et al. Transfer of multivariatecalibrations between four near-infrared spectrometers usingorthogonal signal correction. Anal Chem,2004,76:2595~2600
[63] Ni W, Brown S D, Man R. Wavelet Orthogonal SignalCorrection-Based Discriminant Analysis. Anal Chem,2009,81:8962~8967
[64] Westerhuis J A, de Jong S, Smilde A K. Direct orthogonal signalcorrection. Chemometrics Intell Lab Syst,2001,56:13~25
[65] Faber N M, Rajko R. How to avoid over-fitting in multivariatecalibration-The conventional validation approach and an alternative.Anal Chim Acta,2007,595:98~106
[66] Wold S. Cross-validatory estimation of the number of componentsin factor and principal components models. Technometrics,1978:397~405
[67] Burman P. A comparative study of ordinary cross-validation, v-foldcross-validation and the repeated learning-testing methods.Biometrika,1989,76:503~514
[68] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[69] Xu Q S, Liang Y Z, Du Y P. Monte Carlo cross-validation forselecting a model and estimating the prediction error in multivariatecalibration. J Chemometr,2004,18:112~120
[70] Osten D W. Selection of optimal regression models viacross-validation. J Chemometr,1988,2:39~48
[71] Rutledge D N, Barros A, Delgadillo I. PoLiSh--smoothed partialleast-squares regression. Anal Chim Acta,2001,446:279~294
[72] Gourvenec S, Pierna J A F, Massart D L, et al. An evaluation of thePoLiSh smoothed regression and the Monte Carlo Cross-Validationfor the determination of the complexity of a PLS model.Chemometrics Intell Lab Syst,2003,68:41~51
[73] Durbin J, Watson G S. Testing for serial correlation in least squaresregression: I. Biometrika,1950,37:409~428
[74] van der Voet H. Comparing the predictive accuracy of models usinga simple randomization test. Chemometrics Intell Lab Syst,1994,25:313~323
[75] Wiklund S, Nilsson D, Eriksson L, et al. A randomization test forPLS component selection. J Chemometr,2007,21:427~439
[76] Liu Z C, Ma X, Wen Y D, et al. A practical approach for nearinfrared spectral quantitative analysis of complex samples usingpartial least squares modeling. Sci China Ser B-Chem,2009,52:1021~1027
[77] Rousseeuw P J, Leroy A M, Wiley J. Robust regression and outlierdetection. Hoboken: Wiley Online Library,1987,1~18
[78] Liang Y Z, Kvalheim O M. Robust methods for multivariateanalysis-a tutorial review. Chemometrics Intell Lab Syst,1996,32:1~10
[79] Pierna J A F, Wahl F, de Noord O E, et al. Methods for outlierdetection in prediction. Chemometrics Intell Lab Syst,2002,63:27~39
[80] Belsley D A, Kuh E, Welsch R E. Regression diagnostics. Hoboken:Wiley Online Library;1980.6~84
[81] De Maesschalck R, Jouan-Rimbaud D, Massart D L. Themahalanobis distance. Chemometrics Intell Lab Syst,2000,50:1~18
[82] Hotelling H. Analysis of a complex of statistical variables intoprincipal components. J Educ Psychology,1933,24:417~441
[83] Rousseeuw P J, Van Zomeren B C. Unmasking multivariate outliersand leverage points. J Am Stat Assoc,1990,85:633~639
[84] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[85] Liu Z C, Cai W S, Shao X G. Outlier detection in near-infraredspectroscopic analysis by using Monte Carlo cross-validation. SciChina Ser B-Chem,2008,51:751~759
[86] Bian X H, Cai W S, Shao X G, et al. Detecting influentialobservations by cluster analysis and Monte Carlo cross-validation.Analyst,2010,135:2841~2847
[87] Cao D S, Liang Y Z, Xu Q S, et al. A new strategy of outlierdetection for QSAR/QSPR. J Comput Chem,2010,31:592~602
[88] Daszykowski M, Kaczmarek K, Vander Heyden Y V, et al. Robuststatistics in data analysis-A review: Basic concepts. ChemometricsIntell Lab Syst,2007,85:203~219
[89] Serneels S, Croux C, Filzmoser P, et al. Partial robust M-regression.Chemometrics Intell Lab Syst,2005,79:55~64
[90] Hubert M, Branden K V. Robust methods for partial least squaresregression. J Chemometr,2003,17:537~549
[91] Hubert M, Rousseeuw P J, Verboven S. A fast method for robustprincipal components with applications to chemometrics.Chemometrics Intell Lab Syst,2002,60:101~111
[92] Guyon I, Elisseeff A. An introduction to variable and featureselection. Journal of Machine Learning Research2003,3:1152~1182
[93] Andersen C M, Bro R. Variable selection in regression-a tutorial. JChemometr,2010,24:728~737
[94] Xiaobo Z, Jiewen Z, Povey M J W, et al. Variables selectionmethods in near-infrared spectroscopy. Anal Chim Acta,2010,667:14~32
[95] Lindgren F, Geladi P, R nnar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[96] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[97] Norgaard L, Saudland A, Wagner J, et al. Interval partialleast-squares regression (iPLS): A comparative chemometric studywith an example from near-infrared spectroscopy. Appl Spectrosc,2000,54:413~419
[98] Zou X B, Zhao J W, Huang X Y, et al. Use of FT-NIR spectrometryin non-invasive measurements of soluble solid contents (SSC) of'Fuji' apple based on different PLS models. Chemometrics Intell LabSyst,2007,87:43~51
[99] Jiang J H, Berry R J, Siesler H W, et al. Wavelength intervalselection in multicomponent spectral analysis by moving windowpartial least-squares regression with applications to mid-infrared andhear-infrared spectroscopic data. Anal Chem,2002,74:3555~3565
[100] Kasemsumran S, Du Y P, Murayama K, et al. Near-infraredspectroscopic determination of human serum albumin,gamma-globulin, and glucose in a control serum solution withsearching combination moving window partial least squares. AnalChim Acta,2004,512:223~230
[101] Bro R, De Jong S. A fast non-negativity-constrained least squaresalgorithm. J chemometr,1997,11:393~401
[102] Du Y P, Liang Y Z, Jiang J H, et al. Spectral regions selection toimprove prediction ability of PLS models by changeable sizemoving window partial least squares and searching combinationmoving window partial least squares. Anal Chim Acta,2004,501:183~191
[103] Gareth J, Peter W, Robert C G, et al. Development and validation ofa genetic algorithm for flexible docking. J Mol Bio1999,267:727~748
[104] Haupt Randy L, Haupt S E. Practical genetic algorithms. Hoboken:Wiley,2004,27~47
[105] Leardi R, Gonzalez A L. Genetic algorithms applied to featureselection in PLS regression: how and when to use them.Chemometrics Intell Lab Syst,1998,41:195~207
[106] Koljonen J, Nordling T E M, Alander J T. A review of geneticalgorithms in near infrared spectroscopy and chemometrics: past andfuture. J Near Infrared Spectrosc,2008,16:189~197
[107] Galvao R K H, Pimentel M F, Araujo M C U, et al. Aspects of thesuccessive projections algorithm for variable selection inmultivariate calibration applied to plasma emission spectrometry.Anal Chim Acta,2001,443:107~115
[108] Araujo M C U, Saldanha T C B, Galvao R K H, et al. Thesuccessive projections algorithm for variable selection inspectroscopic multicomponent analysis. Chemometrics Intell LabSyst,2001,57:65~73
[109] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[110] Shao X G, Wang F, Chen D, et al. A method for near-infraredspectral calibration of complex plant samples with wavelettransform and elimination of uninformative variables. Anal BioanalChem,2004,378:1382~1387
[111] Chen D, Shao X G, Hu B, et al. A Background and noiseelimination method for quantitative calibration of near infraredspectra. Anal Chim Acta,2004,511:37~45
[112] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[113] Han Q J, Wu H L, Cai C B, et al. An ensemble of Monte Carlouninformative variable elimination for wavelength selection. AnalChim Acta,2008,612:121~125
[114] Moros J, Kuligowski J, Quintas G, et al. New cut-off criterion foruninformative variable elimination in multivariate calibration ofnear-infrared spectra for the determination of heroin in illicit streetdrugs. Anal Chim Acta,2008,630:150~160
[115] Ye S, Wang D, Min S. Successive projections algorithm combinedwith uninformative variable elimination for spectral variableselection. Chemometrics Intell Lab Syst,2008,91:194~199
[116] Wu D, Chen X, Zhu X, et al. Uninformative variable eliminationfor improvement of successive projections algorithm on spectralmultivariable selection with different calibration algorithms for therapid and non-destructive determination of protein content in driedlaver. Anal Methods,2011,3:1790~1796
[117] Xu H, Liu Z C, Cai W S, et al. A wavelength selection methodbased on randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[118] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[119] Zheng K Y, Li Q Q, Wang J J, et al. Stability competitive adaptivereweighted sampling (SCARS) and its applications to multivariatecalibration of NIR spectra. Chemometrics Intell Lab Syst,2012,112:48~54
[120] Teofilo R F, Martins J P A, Ferreira M M C. Sorting variables byusing informative vectors as a strategy for feature selection inmultivariate regression. J Chemometr,2009,23:32~48
[121] Gosselin R, Rodrigue D, Duchesne C. A Bootstrap-VIP approachfor selecting wavelength intervals in spectral imaging applications.Chemometrics Intell Lab Syst,2010,100:12~21
[122] Ferre J, Faber N M. Net analyte signal calculation for multivariatecalibration. Chemometrics Intell Lab Syst,2003,69:123~136
[123] Brown P J. Wavelength selection in multicomponent near‐infraredcalibration. J Chemometr,1992,6:151~161
[124] Shao X G, Bian X H, Liu J J, et al. Multivariate calibration methodsin near infrared spectroscopic analysis. Anal Methods,2010,2:1662~1666
[125] Li H D, Liang Y Z, Xu Q S, et al. Model population analysis forvariable selection. J Chemometr,2010,24:418~423
[126] Su Z Q, Tong W D, Shi L M, et al. A partial least squares-basedconsensus regression method for the analysis of near-infraredcomplex spectral data of plant samples. Anal Lett,2006,39,2073~2083
[127] Li Y K, Shao X G, Cai W S. Partial least squares regression methodbased on consensus modeling for quantitative analysis ofnear-infrared spectra. Chem J Chin Univ,2007,28:246~249
[128] Chen D, Cai W S, Shao X G. Removing uncertain variables basedon ensemble partial least squares. Anal Chim Acta,2007,598:19~26
[129] Chen D, Cai W S, Shao X G. A strategy for enhancing thereliability of near-infrared spectral analysis. Vib Spectrosc,2008,47:113~118
[130] Li Y K, Shao X G, Cai W S. A consensus least squares supportvector regression (LS-SVR) for analysis of near-infrared spectra ofplant samples. Talanta,2007,72:217~222
[131] Cao D S, Xu Q S, Liang Y Z, et al. The boosting: A new idea ofbuilding models. Chemometrics Intell Lab Syst,2010,100:1~11
[132] Zhang M H, Xu Q S, Massart D L. Boosting partial least squares.Anal Chem,2005,77:1423~1431
[133] Zhou Y P, Cai C B, Huan S, et al. QSAR study of angiotensin IIantagonists using robust boosting partial least squares regression.Anal Chim Acta,2007,593:68~74
[134] Shao X G, Bian X H, Cai W S. An improved boosting partial leastsquares method for near-infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[135] Shinzawa H, Jiang J H, Ritthiruangdej P, et al. Investigations ofbagged kernel partial least squares (KPLS) and boosting KPLS withapplications to near-infrared (NIR) spectra. J Chemometr,2006,20:436~444
[136] Zhou Y P, Jiang J H, Wu H L,et al. Dry film method withytterbium as the internal standard for near infrared spectroscopicplasma glucose assay coupled with boosting support vectorregression. J Chemometr,2006,20:13~21
[137] Jing M, Cai W S, Shao X G. Quantitative Determination of theComponents in Corn and Tobacco Samples by Using Near-InfraredSpectroscopy and Multiblock Partial Least Squares. Anal Lett,2010,43:1910~1921
[138] Tan C, W J Y, Wu T, et al. Determination of nicotine in tobaccosamples by near-infrared spectroscopy and boosting partial leastsquares. Vib Spectrosc,2010,54:35~41
[139] Ni W, Brown S D, Man R. Stacked partial least squares regressionanalysis for spectral calibration and prediction. J Chemometr,2009,23:505~517
[140] Melssen W, Ustun B, Buydens L. SOMPLS: A supervisedself-organising map-partial least squares algorithm for multivariateregression problems. Chemometrics Intell Lab Syst,2007,86:102~120
[141] Ballabio D, Consonni V, Todeschini R. The Kohonen and CP-ANNtoolbox: A collection of MATLAB modules for Self OrganizingMaps and Counterpropagation Artificial Neural Networks.Chemometrics Intell Lab Syst,2009,98:115~122
[142] Tan C, Qin X, Li M L. Subspace Regression Ensemble MethodBased on Variable Clustering for Near-Infrared SpectroscopicCalibration. Anal Lett,2009,42:1693~1710
[143] Tan H, Brown S D. Dual-domain regression analysis for spectralcalibration models. J Chemometr,2003,17:111~122
[144] Jing M, Cai W S, Shao X G. Multiblock partial least squaresregression based on wavelet transform for quantitative analysis ofnear infrared spectra. Chemometrics Intell Lab Syst,2010,100:22~27
[145] Liu Z C, Cai W S, Shao X G. A weighted multiscale regression formultivariate calibration of near infrared spectra. Analyst,2009,134:261~266
[146] Chen D, Chen Z W, Grant E R. Adaptive multiscale regression forreliable Raman quantitative analysis. Analyst,2012,137:237~244
[1] Siesler H W, Ozaki Y, Kawata S, et al. Near-infrared spectroscopy,principles, instruments, applications. Wiley, New York,2002,11~35
[2] Roggo Y, Chalus P, Maurer L, et al. A review of near infraredspectroscopy and chemometrics in pharmaceutical technologies. JPharm Biomed Anal,2007,44:683~700
[3] Geladi P. Chemometrics in spectroscopy. Part1. Classicalchemometrics. Spectroc Acta Pt B-Atom Spectr,2003,58:767~782
[4] Wold S, Sjostrom M, Eriksson L. PLS-regression: a basic tool ofchemometrics. Chemometrics Intell Lab Syst,2001,58:109~130
[5] Chu X L, Yuan H F, Lu W Z. Progress and application of spectral datapretreatment and wavelength selection methods in NIR analyticaltechnique. Prog Chem,2004,16:528~542
[6] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[7] Guo Q, Wu W, Massart D L. The robust normal variate transform forpattern recognition with near-infrared data. Anal Chim Acta,1999,382:87~103
[8] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear-infrared spectra. Chemometrics Intell Lab Syst,1998,44:175~185
[9] Fearn T. On orthogonal signal correction. Chemometrics Intell LabSyst,2000,50:47~52
[10] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[11] Shao X G, Ma C X. A general approach to derivative calculationusing wavelet transform. Chemometrics Intell Lab Syst,2003,69:157~165
[12] Andersen C M, Bro R. Variable selection in regression-a tutorial. JChemometr,2010,24:728~737
[13] Zou X B, Zhao J W, Povey M J W, et al. Variables selection methodsin near-infrared spectroscopy. Anal Chim Acta,2010,667:14~32
[14] Leardi R, Gonzalez A L. Genetic algorithms applied to featureselection in PLS regression: how and when to use them.Chemometrics Intell Lab Syst,1998,41:195~207
[15] Leardi R. Application of genetic algorithm-PLS for feature selectionin spectral data sets. J Chemometr,2000,14:643~655
[16] Lindgren F, Geladi P, Rannar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[17] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[18] Centner V, Massart D L, de Noord O E, et al. Elimination ofUninformative Variables for Multivariate Calibration. Anal Chem,1996,68:3851~3858
[19] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[20] Han Q J, Wu H L, Cai C B, et al. An ensemble of Monte Carlouninformative variable elimination for wavelength selection. AnalChim Acta,2008,612:121~125
[21] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[22] Araujo M C U, Saldanha T C B, Galvao R K H, et al. Thesuccessive projections algorithm for variable selection inspectroscopic multicomponent analysis. Chemometrics Intell LabSyst,2001,57:65~73
[23] Galvao R K H, Araujo M C U, Fragoso W D, et al. A variableelimination method to improve the parsimony of MLR models usingthe successive projections algorithm. Chemometrics Intell Lab Syst,2008,92:83~91
[24] Teofilo R F, Martins J P A, Ferreira M M C. Sorting variables byusing informative vectors as a strategy for feature selection inmultivariate regression. J Chemometr,2009,23:32~48
[25] Gosselin R, Rodrigue D, Duchesne C. A Bootstrap-VIP approach forselecting wavelength intervals in spectral imaging applications.Chemometrics Intell Lab Syst,2010,100:12~21
[26] Lorber A. Error propagation and figures of merit for quantificationby solving matrix equations. Anal Chem,1986,58:1167~1172
[27] Ferre J, Faber N M. Net analyte signal calculation for multivariatecalibration. Chemometrics Intell Lab Syst,2003,69:123~136
[28] Brown P J. Wavelength selection in multicomponent near-infraredcalibration. J Chemometr,1992,6:151~161
[29] Rajalahti T, Arneberg R, Berven F S, et al. Biomarker discovery inmass spectral profiles by means of selectivity ratio plot.Chemometrics Intell Lab Syst,2009,95:35~48
[30] Jiang J H, Berry R J, Siesler H W, et al. Wavelength intervalselection in multicomponent spectral analysis by moving windowpartial least-squares regression with applications to mid-infrared andhear-infrared spectroscopic data. Anal Chem,2002,74:3555~3565
[31] Roger J M, Palagos B, Bertrand D, et al. CovSel: Variable selectionfor highly multivariate and multi-response calibration Application toIR spectroscopy. Chemometrics Intell Lab Syst,2011,106:216~223
[32] Li Y K, Shao X G, Cai W S. A consensus least squares supportvector regression (LS-SVR) for analysis of near-infrared spectra ofplant samples. Talanta,2007,72:217~222
[33] Liu Z C, Cai W S, Shao X G. A weighted multiscale regression formultivariate calibration of near infrared spectra. Analyst,2009,134:261~266
[34] Shao X G, Bian X H, Cai W S. An improved boosting partial leastsquares method for near-infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[35] Cao D S, Xu Q S, Liang Y Z, et al. The boosting: A new idea ofbuilding models. Chemometrics Intell Lab Syst,2010,100:1~11
[36] de Jong S. SIMPLS: an alternative approach to partial least squaresregression. Chemometrics Intell Lab Syst,1993,18:251~263
[37] Bro R, De Jong S. A fast non-negativity-constrained least squaresalgorithm. J Chemometr,1997,11:393~401
[38] Kuenstner J T, Norris K H, McCarthy W F. Measurement ofhemoglobin in unlysed blood by near-infrared spectroscopy. ApplSpectrosc,1994,48:484~488
[39] Kalivas J H. Two data sets of near infrared spectra. ChemometricsIntell Lab Syst,1997,37:255~259
[40] Kennard R W, Stone L A. Computer aided desigh of experiments.Technometrics,1969,11:137~148
[41] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[42] Liu Z C, Ma X, Wen Y D, et al. A practical approach for nearinfrared spectral quantitative analysis of complex samples usingpartial least squares modeling. Sci China Ser B-Chem,2009,52:1021~1027
[1] Bosco G L. Symposium2009on near-infrared spectroscopy.Trac-Trends Anal Chem,2010,29:197~208
[2] Wold S, Sjostrom M, Eriksson L. PLS-regression: A basic tool ofchemometrics. Chemometr Intell Lab Syst,2001,58:109~130
[3] Bro R. Multivariate calibration-What is in chemometrics for theanalytical chemist? Anal Chim Acta,2003,500:185~194
[4] Candolfi A, De Maesschalck R, Jouan-Rimbaud D, et al. Theinfluence of data pre-processing in the pattern recognition ofexcipients near-infrared spectra. J Pharm Biomed Anal,1999,21:115~132
[5] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[6] Guo Q, Wu W, Massart D L. The robust normal variate transform forpattern recognition with near-infrared data. Anal Chim Acta,1999,382:87~103
[7] Savitzky A, Golay M J E. Smoothing and differentiation of data bysimplified least squares procedures. Anal Chem,1964,36:1627~1639
[8] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear-infrared spectra. Chemometr Intell Lab Syst,1998,44:175~185
[9]Fearn T. On orthogonal signal correction. Chemometr. Intell Lab Syst,2000,50:47~52
[10] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Acc Chem Res,2003,36:276~283
[11] Chen D, Shao X G, Hu B, et al. A background and noise eliminationmethod for quantitative calibration of near infrared spectra. AnalChim Acta,2004,511:37~45
[12] Cummins D J, Andrews C W. Iteratively reweighted partial leastsquares: A performance analysis by monte carlo simulation. JChemometr,1995,9:489~507
[13] Serneels S, Croux C, Filzmoser P, et al. Partial robust M-regression.Chemometr Intell Lab Syst,2005,79:55~64
[14] Lindgren F, Geladi P, Rannar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[15] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[16] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[17] Shao X G, Wang F, Chen D, et al. A method for near-infraredspectral calibration of complex plant samples with wavelettransform and elimination of uninformative variables. Anal BioanalChem,2004,378:1382~1387
[18] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis. Chemometr.Intell Lab Syst,2009,97:189~193
[19] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometr Intell Lab Syst,2008,90:188~194
[20] Galvao R K H, Araujo M C U, Fragoso W D, et al. A variableelimination method to improve the parsimony of MLR models usingthe successive projections algorithm. Chemometr Intell Lab Syst,2008,92:83~91
[21] Ye S F, Wang D, Min S G. Successive projections algorithmcombined with uninformative variable elimination for spectralvariable selection. Chemometr Intell Lab Syst,2008,91:194~199
[22] Breiman L. Bagging predictors. Mach Learn,1996,24:123~140
[23] Cao D S, Xu Q S, Liang Y Z, et al. The boosting, A new idea ofbuilding models. Chemometr Intell Lab Syst,2010,100:1~11
[24] Li Y K, Shao X G, Cai W S. Partial least squares regression methodbased on consensus modeling for quantitative analysis ofnear-infrared spectra. Chem J Chin Univ,2007,28:246~249
[25] Li Y K, Shao X G, Cai W S. A consensus least squares supportvector regression (LS-SVR) for analysis of near-infrared spectra ofplant samples. Talanta,2007,72:217~222
[26] Zhou Y P, Cai C B, Huan S, et al. QSAR study of angiotensin IIantagonists using robust boosting partial least squares regression.Anal Chim Acta,2007,593:68~74
[27] Shao X G, Bian X H, Liu Z C, et al. An improved boosting partialleast squares for near-infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[28] Carney J, Cunningham P. Tuning diversity in bagged ensembles. IntJ Neural Syst,2000,10:267~280
[29] Tan C, Qin X, Li M L. Subspace regression ensemble method basedon variable clustering for near-infrared spectroscopic calibration.Anal Lett,2009,42:1693~1710
[30] Liu Z C, Cai W S, Shao X G. A weighted multiscale regression formultivariate calibration of near infrared spectra. Analyst,2009,134:261~266
[31] Ni W D, Brown S D, Man R L. Stacked partial least squaresregression analysis for spectral calibration and prediction. JChemometr,2009,23:505~517
[32] Xu Q S, Liang Y Z. Monte Carlo cross validation. Chemometr IntellLab Syst,2001,56:1~11
[33] Kennard R W, Stone L A. Computer aided design of experiments.Technometrics,1969,11:137~148
[1] Siesler H W, Ozaki Y, Kawata S, et al. Near-infrared spectroscopy,principles, instruments, applications. Wiley, New York,2002,11~35
[2] Geladi P. Chemometrics in spectroscopy. Part1. Classicalchemometrics. Spectroc Acta Pt B-Atom Spectr,2003,58:767~782
[3] Wold S, Sjostrom M, Eriksson L. PLS-regression: a basic tool ofchemometrics. Chemometrics Intell Lab Syst,2001,58:109~130
[4] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[5] Shao X G, Ma C X. A general approach to derivative calculationusing wavelet transform. Chemometrics Intell Lab Syst,2003,69:157~165
[6] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[7] Guo Q, Wu W, Massart D L. The robust normal variate transform forpattern recognition with near-infrared data. Anal Chim Acta,1999,382:87~103
[8] Andersen C M, Bro R. Variable selection in regression-a tutorial. JChemometr,2010,24:728~737
[9] Zou X B, Zhao J W, Povey M J W, et al. Variables selection methodsin near-infrared spectroscopy. Anal Chim Acta,2010,667:14~32
[10] Lindgren F, Geladi P, Rannar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[11] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[12] Centner V, Massart D L, de Noord O E, et al. Elimination ofUninformative Variables for Multivariate Calibration. Anal Chem,1996,68:3851~3858
[13] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[14] Han Q J, Wu H L, Cai C B, et al. An ensemble of Monte Carlouninformative variable elimination for wavelength selection. AnalChim Acta,2008,612:121~125
[15] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[16] Teofilo R F, Martins J P A, Ferreira M M C. Sorting variables byusing informative vectors as a strategy for feature selection inmultivariate regression. J Chemometr,2009,23:32~48
[17] Durand A, Devos O, Ruckebusch C, et al. Genetic algorithmoptimisation combined with partial least squares regression andmutual information variable selection procedures in near-infraredquantitative analysis of cotton-viscose textiles. Anal Chim Acta,2007,595:72~79
[18] Arakawa M, Yamashita Y, Funatsu K. Genetic algorithm-basedwavelength selection method for spectral calibration. J Chemometr,2011,25:10~19
[19] Shamsipur M, Zare-Shahabadi V, Hemmateenejad B, et al. Antcolony optimisation: a powerful tool for wavelength selection. JChemometr,2006,20:146~157
[20] Galvao R K H, Araujo M C U, Fragoso W D, et al. A variableelimination method to improve the parsimony of MLR models usingthe successive projections algorithm. Chemometrics Intell Lab Syst,2008,92:83~91
[21] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[22] Fu G H, Xu Q S, Li H D, et al. Elastic Net Grouping VariableSelection Combined with Partial Least Squares Regression(EN-PLSR) for the Analysis of Strongly Multi-collinearSpectroscopic Data. Appl Spectrosc,2011,65:402~408
[23] Chun H, Keles S. Sparse partial least squares regression forsimultaneous dimension reduction and variable selection. J R STATSOC B,2010,72:3~25
[24] McWilliams B, Montana G. Sparse partial least squares regressionfor on-line variable selection with multivariate data streams. StatAnal Data Mining,2010,3:170~193
[25] Lee D, Lee W, Lee Y, et al. Sparse partial least-squares regressionand its applications to high-throughput data analysis. ChemometricsIntell Lab Syst,2011,109:1~8
[26] Roger J M, Palagos B, Bertrand D, et al. CovSel: Variable selectionfor highly multivariate and multi-response calibration Application toIR spectroscopy. Chemometrics Intell Lab Syst,2011,106:216~223
[27] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[28] Kennard R W, Stone L A. Computer aided desigh of experiments.Technometrics,1969,11:137~148
[1] Siesler H W, Ozaki Y, Kawata S, et al. Near-infrared spectroscopy,principles, instruments, applications, Wiley, New York,2002
[2] Massart D L, Vandeginste B G M, Buydens L M C, et al. Handbookof chemometrics and Qualimetrics: Part A, Elsevier, Amsterdam,1997
[3] Wold S, Ruhe A, Wold H, et al. The collinearity problem in linearregression. The partial least squares (PLS) approach to generalizedinverses. SIAM J Sci Stat Comput,1984,5:735~743
[4] Shao X G, Bian X H, Liu J J, et al. Multivariate calibration methodsin near infrared spectroscopic analysis. Anal Methods,2010,2:1662~1666
[5] de Jong S. SIMPLS: an alternative approach to partial least squaresregression. Chemometrics Intell Lab Syst,1993,18:251~263
[6] Barman I, Kong C R, Dingari N C, et al. Development of RobustCalibration Models Using Support Vector Machines forSpectroscopic Monitoring of Blood Glucose. Anal Chem,2010,82:9719~9726
[7] Belousov A I, Verzakov S A, von Frese J. Applicational aspects ofsupport vector machines. J of Chemometr,2002,16:482~489
[8] Li Y K, Shao X G, Cai W S. A consensus least squares support vectorregression (LS-SVR) for analysis of near-infrared spectra of plantsamples. Talanta,2007,72:217~222
[9] Jin L, Pierna J A F, Xu Q, et al. Delaunay triangulation method formultivariate calibration. Anal Chim Acta,2003,488:1~14
[10] Perez Marin D C, Garrido Varo A, Guerrero J E. Non-linearregression methods in NIRS quantitative analysis. Talanta,2007,72:28~42
[11] Li Y K, Shao X G, Cai W S. Partial least squares regression methodbased on consensus modeling for quantitative analysis ofnear-infrared spectra. Chem J Chin Univ,2007,28:246~249
[12] Cao D S, Wang B, Zeng M M, et al. A new strategy of exploringmetabolomics data using Monte Carlo tree. Analyst,2011,136:947~954
[13] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[14] Ma C X, Shao X G. Continuous wavelet transform applied toremoving the fluctuating background in near-infrared spectra. JChem Inf Comp Sci,2004,44:907~911
[15] Chen D, Shao X G, Hu B, et al. A Background and noise eliminationmethod for quantitative calibration of near infrared spectra. AnalChim Acta,2004,511:37~45.
[16] Chen D, Hu B, Shao X G, et al. A new hybrid strategy forconstructing a robust calibration model for near-infrared spectralanalysis. Anal Bioanal Chem,2005,381:795~805
[17] Geladi P, MacDougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[18] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear~infrared spectra. Chemometrics Intell Lab Syst,1998,44:175~185
[19] Westerhuis J A, de Jong S, Smilde A K. Direct orthogonal signalcorrection. Chemometrics Intell Lab Syst,2001,56:13~25
[20] Norgaard L, Saudland A, Wagner J, et al. Interval partialleast-squares regression (iPLS): A comparative chemometric studywith an example from near-infrared spectroscopy. Appl Spectrosc,2000,54:413~419
[21] Leardi R, Norgaard L. Sequential application of backward intervalpartial least squares and genetic algorithms for the selection ofrelevant spectral regions. J Chemometr,2004,18:486~497
[22] Lindgren F, Geladi P, Rannar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[23] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. J ofChemometr,1995,9:331~342
[24] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[25] Shao X G, Wang F, Chen D, et al. A method for near-infraredspectral calibration of complex plant samples with wavelettransform and elimination of uninformative variables. Anal BioanalChem,2004,378:1382~1387
[26] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[27] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[28] Araujo M C U, Saldanha T C B, Galvao R K H, et al. Thesuccessive projections algorithm for variable selection inspectroscopic multicomponent analysis. Chemometrics Intell LabSyst,2001,57:65~73
[29] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[30] Liang Y Z, Kvalheim O M. Robust methods for multivariateanalysis: A tutorial review. Chemometrics Intell Lab Syst,1996,32:1~10
[31] De Maesschalck R, Jouan-Rimbaud D, Massart D L. TheMahalanobis distance. Chemometrics Intell Lab Syst,2000,50:1~18
[32] Rousseeuw P J, van Zomeren B C. Unmasking Multivariate Outliersand Leverage Points. J Am Stat Assoc,1990,85:871~880
[33] Fung W K. Unmasking outliers and leverage points: A confirmation.J Am Stat Assoc,1993:515~519
[34] Pierna J A F, Wahl F, de Noord O E, et al. Methods for outlierdetection in prediction. Chemometrics Intell Lab Syst,2002,63:27~39
[35] Walczak B, Massart D L. Multiple outlier detection revisited.Chemometrics Intell Lab Syst,1998,41:1~15
[36] Hadi A S. Identifying multiple outliers in multivariate data. J R StatSoc B,1992,54:761~771
[37] De Vries S, Ter Braak C J F. Prediction error in partial least squaresregression: a critique on the deviation used in the Unscrambler.Chemometrics Intell Lab Syst,1995,30:239~245
[38] Hoy M, Steen K, Martens H. Review of partial least squaresregression prediction error in Unscrambler. Chemometrics Intell LabSyst,1998,44:123~133
[39] Pierna J A F, Jin L, Daszykowski M, et al. A methodology to detectoutliers/inliers in prediction with PLS. Chemometrics Intell LabSyst,2003,68:17~28
[40] Liu Z C, Cai W S, Shao X G. Outlier detection in near-infraredspectroscopic analysis by using Monte Carlo cross-validation. SciChina Ser B-Chem,2008,51:751~759
[41] Bian X H, Cai W S, Shao X G, et al. Detecting influentialobservations by cluster analysis and Monte Carlo cross-validation.Analyst,2010,135:2841~2847
[42] Liebmann B, Filzmoser P, Varmuza K. Robust and classical PLSregression compared. J Chemometr,2010,24:111~120
[43] Vanden Branden K, Hubert M. Robustness properties of a robustpartial least squares regression method. Anal Chim Acta,2004,515:229~241
[44] Serneels S, Croux C, Filzmoser P, et al. Partial robust M~regression.Chemometrics Intell Lab Syst,2005,79:55~64
[45] Serneels S, Filzmoser P, Croux C, et al. Robust continuumregression. Chemometrics Intell Lab Syst,2005,76:197~204
[46] Shao X G, Bian X H, Cai W S. An improved boosting partial leastsquares method for near~infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[47] Liu Z C, Ma X, Wen Y D, et al. A practical approach for nearinfrared spectral quantitative analysis of complex samples usingpartial least squares modeling. Sci China Ser B-Chem,2009,52:1021~1027
[48] Breunig M M, Kriegel H P, Ng R T, et al. LOF: Identifyingdensity-based local outliers. Sigmod Rec,2000,29:93~104
[49] Kalivas J H. Two data sets of near infrared spectra. ChemometricsIntell Lab Syst,1997,37:255~259
[50] Li W, Goovaerts P, Meurens M. Quantitative analysis of individualsugars and acids in orange juices by near~infrared spectroscopy ofdry extract. J arg food chem,1996,44:2252~2259
[1] Rickert W S, Joza P J, Sharifi M, et al. Reductions in the tobaccospecific nitrosamine (TSNA) content of tobaccos taken fromcommercial Canadian cigarettes and corresponding reductions inTSNA deliveries in mainstream smoke from such cigarettes. RegulToxicol Pharm,2008,51:306~310
[2] Zhou J, Bai R S, Zhu Y F. Determination of four tobacco-specificnitrosamines in mainstream cigarette smoke by gaschromatography/ion trap mass spectrometry. Rapid Commun MassSp,2007,21:4086~4092
[3] Wu W J, Ashley D L, Watson C H. Simultaneous determination offive tobacco-specific nitrosamines in mainstream cigarette smoke byisotope dilution liquid chromatography/electrospray ionizationtandem mass spectrometry. Anal Chem,2003,75:4827~4832
[4] Wagner K A, Finkel N H, Fossett J E, et al. Development of aquantitative method for the analysis of tobacco-specificnitrosamines in mainstream cigarette smoke using isotope dilutionliquid chromatography/electrospray ionization tandem massspectrometry. Anal Chem,2005,77:1001~1006
[5] Wu J C, Joza P, Sharifi M, et al. Quantitative method for the analysisof tobacco-specific nitrosamines in cigarette tobacco andmainstream cigarette smoke by use of isotope dilution liquidchromatography tandem mass spectrometry. Anal Chem,2008,80:1341~1345
[6] Wu W J, Song S Q, Ashley D L, et al. Assessment of tobacco-specificnitrosamines in the tobacco and mainstream smoke of Bidicigarettes. Carcinogenesis,2004,25:283~287
[7] Clayton P M, Cunningham A, van Heemst J D H. Quantification offour tobacco-specific nitrosamines in cigarette filter tips using liquidchromatography-tandem mass spectrometry. Anal Methods,2010,2:1085~1094
[8] Kavvadias D, Scherer G, Urban M, et al. Simultaneous determinationof four tobacco-specific N-nitrosamines (TSNA) in human urine. JChromatogr B,2009,877:1185~1192
[9] Stepanov I, Hecht S S, Mirvish S S, et al. Comparative analysis oftobacco-specific nitrosamines and total N-nitroso compounds inMoldovan cigarette tobacco. J Agr Food Chem,2005,53:8082~8086
[10] Sleiman M, Maddalena R L, Gundel L A, et al. Rapid and sensitivegas chromatography-ion-trap tandem mass spectrometry method forthe determination of tobacco-specific N-nitrosamines in secondhandsmoke. J Chromatogr A,2009,1216:7899~7905
[11] Moros J, Garrigues S, de la Guardia M. Vibrational spectroscopyprovides a green tool for multi-component analysis. Trac-TrendsAnal Chem,2010,29:578~591
[12] Du C G, Zhou J M. Evaluation of soil fertility using infraredspectroscopy: a review. Environ Chem Lett,2009,7:97~113
[13] Cozzolino D. Near Infrared Spectroscopy in Natural ProductsAnalysis. Planta Med,2009,75:746~756
[14] Feng Y C, Zhang X B, Hu C Q. Construction of identificationsystem for non-invasive analysis of macrolides tablets using nearinfrared diffuse reflectance spectroscopy. J Pharm Biomed Anal,2010,51:12~17
[15] Jing M, Cai W S, Shao X G. Quantitative Determination of theComponents in Corn and Tobacco Samples by Using Near-InfraredSpectroscopy and Multiblock Partial Least Squares. Anal Lett,2010,43:1910~1921
[16] Liu J J, Xu H, Cai W S, et al. Discrimination of industrial productsby on-line near infrared spectroscopy with an improved dendrogram.Chin Chem Lett,2011,22:1241~1244
[17] Huang H B, Yu H Y, Xu H R, et al. Near infrared spectroscopy foron/in-line monitoring of quality in foods and beverages: A review. JFood Eng,2008,87:303~313
[18] Nordon A, Littlejohn D, Dann A S, et al. In situ monitoring of theseed stage of a fermentation process using non-invasive NIRspectrometry. Analyst,2008,133:660~666
[19] Roychoudhury P, O'Kennedy R, McNeil B, et al. Multiplexing fibreoptic near infrared (NIR) spectroscopy as an emerging technology tomonitor industrial bioprocesses. Anal Chim Acta,2007,590:110~117
[20] Liu J J, Ma X, Wen Y D, et al. Online near-Infrared SpectroscopyCombined with Alternating Trilinear Decomposition for ProcessAnalysis of Industrial Production and Quality Assurance. Ind EngChem Res,2011,50:7677~7681
[21] Rinnan A, van den Berg F, Engelsen S B. Review of the mostcommon pre-processing techniques for near-infrared spectra.Trac-Trends Anal Chem,2009,28:1201~1222
[22] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[23] Cummins D J, Andrews C W. Iteratively reweighted partial leastsquares: A performance analysis by monte carlo simulation. JChemometr,1995,9:489~507
[24] Egan W J, Mogan S L. Outlier detection in multivariate analyticalchemical data. Anal Chem,1998,70:2372~2379
[25] Serneels S, Croux C, Filzmoser P, et al. Partial robust M-regression.Chemometrics Intell Lab Syst,2005,79:55~64
[26] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[27] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[28] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[29] Huang Z X, Tao W, Fang J J, et al. Multivariate calibration ofon-line enrichment near-infrared (NIR) spectra and determination oftrace lead in water. Chemometrics Intell Lab Syst,2009,98:195~200
[30] Sheng N, Cai W S, Shao X G. An approach by using near-infrareddiffuse reflectance spectroscopy and resin adsorption for thedetermination of copper, cobalt and nickel ions in dilute solution.Talanta,2009,79:339~343
[31] Li J H, Zhang Y, Cai W S, et al. Simultaneous determination ofmercury, lead and cadmium ions in water using near-infraredspectroscopy with preconcentration by thiol-functionalizedmagnesium phyllosilicate clay. Talanta,2011,84:679~683
[32] Moros J, Llorca I, Cervera M L, et al. Chemometric determinationof arsenic and lead in untreated powdered red paprika by diffusereflectance near-infrared spectroscopy. Anal Chim Acta,2008,613:196~206
[33] Chang C W, Laird D A, Mausbach M J, et al. Near-infraredreflectance spectroscopy principal components regression analysesof soil properties. Soil Sci Soc Am J,2001,65:480~490
[34] Font R, Del Rio-Celestino M, Velez D, et al. Visible andnear-infrared spectroscopy as a technique for screening the inorganicarsenic content in the red crayfish (Procambarus clarkii Girard).Anal Chem,2004,76:3893~3898
[35] Font R, Velez D, Del Rio-Celestino M, et al. Screening inorganicarsenic in rice by visible and near-infrared spectroscopy. MicrochimActa,2005,151:231~239
[36] Cozzolino D, Kwiatkowski M J, Dambergs R G, et al. Analysis ofelements in wine using near infrared spectroscopy and partial leastsquares regression. Talanta,2008,74:711~716
[37] Kennard R W, Stone L A. Computer aided design of experiments.Technometrics,1969,11:137~148
[38] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[39] Shao X G, Ma C X. A general approach to derivative calculationusing wavelet transform. Chemometrics Intell Lab Syst,2003,69:157~165
[40] Ma C X, Shao X G. Continuous wavelet transform applied toremoving the fluctuating background in near-infrared spectra. JChem Inf Comp Sci,2004,44:907~911
[41] Chen D, Shao X G, Hu B, et al. A Background and noise eliminationmethod for quantitative calibration of near infrared spectra. AnalChim Acta,2004,511:37~45
[1]严衍禄,赵龙莲,韩东海等.近红外光谱分析基础与应用.北京:中国轻工业出版社,2005,286~563
[2]陆婉珍,袁洪福,徐广通等.现代近红外光谱分析技术.北京:中国石化出版社,2007,193~247
[3]刘建学.实用近红外光谱分析技术.北京:科学出版社,2008,158~239
[4] Massart D L. Chemometrics: a textbook. Amsterdam: ElsevierScience,1988,5~9
[5] Chau F. Chemometrics: from basics to wavelet transform. Hoboken:Wiley-Interscience,2004,5~12
[6] Brown S D, Tauler R, Walczak B. Comprehensive chemometrics:chemical and biochemical data analysis. Amsterdam: Elsevier,2009,459~463
[7] Martens H, Naes T. Multivariate calibration. Hoboken: John Wiley&Sons Inc,1992,1~30
[8] N s T, Isaksson T, Fearn T, et al. A user friendly guide to multivariatecalibration and classification. Chichester UK: NIR Publications,2002,11~17
[9] Brereton R G. Introduction to multivariate calibration in analyticalchemistry. Analyst,2000,125:2125~2154
[10] Williams P, Norris K. Near-infrared technology in the agriculturaland food industries. Minnesota: American Association of CerealChemists,1987
[11] Weisberg S. Applied linear regression, Third edition. Hoboken:Wiley Online Library,2005,211~230
[12] Hawkins D M. On the investigation of alternative regressions byprincipal component analysis. Appl Statist,1973,22:275~286
[13] N s T, Martens H. Principal component regression in NIR analysis:viewpoints, background details and selection of components. JChemometr,1988,2:155~167
[14] Sutter J M, Kalivas J H, Lang P M. Which principal components toutilize for principal component regression. J Chemometr,1992,6:217~225
[15] Depczynski U, Frost V J, Molt K. Genetic algorithms applied to theselection of factors in principal component regression. Anal ChimActa,2000,420:217~227
[16] Chang C W, Laird D A, Mausbach M J, Hurburgh Jr C R.Near-infrared reflectance spectroscopy-principal componentsregression analyses of soil properties. Soil Sci Soc Am J,2001.65:480~490
[17] Otsuka M. Comparative particle size determination of phenacetinbulk powder by using Kubelka-Munk theory and principalcomponent regression analysis based on near-infrared spectroscopy.Powder Technol,2004,141:244~250
[18]邵学广,蔡文生.化学信息学.北京:科学出版社,2005,206~207
[19] Vinzi V E, Chin W W, Henseler J. Handbook of partial least squares:Concepts, methods and applications. Berlin: Springer Verlag,2009,32~38
[20] Wold H. Partial least squares. Int J Cardiol,1985,147:581~591
[21] Geladi P, Kowalski B R. Partial least-squares regression: a tutorial.Anal Chim Acta,1986,185:1~17
[22] Wold S, Sjostrom M, Eriksson L. PLS-regression: a basic tool ofchemometrics. Chemometrics Intell Lab Syst,2001,58:109~130
[23] de Jong S. SIMPLS: an alternative approach to partial least squaresregression. Chemometrics Intell Lab Syst,1993,18:251~263
[24] Kvalheim O M, Karstang T V. Interpretation of latent variableregression models. Chemometrics Intell Lab Syst.1989,7:39~51
[25]Trygg J, Wold S. Orthogonal projections to latent structures (O-PLS).J Chemometr,2002,16:119~128
[26] Cloarec O, Dumas M E, Trygg J, et al. Evaluation of the orthogonalprojection on latent structure model limitations caused by chemicalshift variability and improved visualization of biomarker changes in1H NMR spectroscopic metabonomic studies. Anal Chem,2005,77:517~526
[27] Walczak B, Massart D L. The Radial Basis Functions--Partial LeastSquares approach as a flexible non-linear regression technique. AnalChim Acta,1996,331:177~185
[28] Rosipal R. Kernel partial least squares for nonlinear regression anddiscrimination. Neural Netw World,2003,13:291~300
[29] Chen D, Hu X G, Shao X G, et al. Variable selection by modifiedIPW (iterative predictor weighting)-PLS (partial least squares) incontinuous wavelet regression models. Analyst,2004,129:664~669
[30] Xu H, Cai W S, Shao X G. Weighted partial least squares regressionby variable grouping strategy for multivariate calibration of nearinfrared spectra. Anal Methods,2010,2:289~294
[31] Comon P. Independent component analysis, a new concept? SignalProcess,1994,36:287~314
[32] Hyvarinen A, Oja E. Independent component analysis: algorithmsand applications. Neural Netw,2000,13:411~430
[33] Wang G Q, Ding Q Z, Hou Z Y. Independent component analysisand its applications in signal processing for analytical chemistry.Trac-Trends Anal Chem,2008,27:368~376
[34] Shao X G, Liu Z C, Cai W S. Resolving multi-componentoverlapping GC-MS signals by immune algorithms. Trac-TrendsAnal Chem,2009,28:1312~1321
[35] Gustafsson M G. Independent component analysis yields chemicallyinterpretable latent variables in multivariate regression. J Chem InfModel,2005,45:1244~1255
[36] Shao X G, Wang W, Hou Z Y, et al. A new regression method basedon independent component analysis. Talanta,2006,69:676~680
[37] Zhang Y W, Zhang Y. Complex process monitoring using modifiedpartial least squares method of independent component regression.Chemometrics Intell Lab Syst,2009,98:143~148
[38] Al-Mbaideen A, Benaissa M. Coupling subband decomposition andindependent component regression for quantitative NIRspectroscopy. Chemometrics Intell Lab Syst,2011,108:112~122
[39] Parastar H, Jalali-Heravi M, Tauler R. Is Independent ComponentAnalysis appropriate for multivariate resolution in analyticalchemistry? Trac-Trends Anal Chem,2011.31:134~143
[40] Bouveresse D, Moya-González A, Ammari F, et al. Two novelmethods for the determination of the number of components inindependent components analysis models. Chemometrics Intell LabSyst,2012,112:24~32
[41] Candolfi A, De Maesschalck R, Jouan-Rimbaud D, et al. Theinfluence of data pre-processing in the pattern recognition ofexcipients near-infrared spectra. J Pharm Biomed Anal,1999,21:115~132
[42] Azzouz T, Puigdoménech A, Aragay M, et al. Comparison betweendifferent data pre-treatment methods in the analysis of foragesamples using near-infrared diffuse reflectance spectroscopy andpartial least-squares multivariate calibration method. Anal ChimActa,2003,484:121~134
[43] Rinnan A, van den Berg F, Engelsen S B. Review of the mostcommon pre-processing techniques for near-infrared spectra.Trac-Trends Anal Chem,2009,28:1201~1222
[44] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[45] Martens H, Stark E. Extended multiplicative signal correction andspectral interference subtraction: new preprocessing methods fornear infrared spectroscopy. J Pharm Biomed Anal,1991,9:625~635
[46] Martens H, Nielsen J P, Engelsen S B. Light scattering and lightabsorbance separated by extended multiplicative signal correction.Application to near-infrared transmission analysis of powdermixtures. Anal Chem,2003,75:394~404
[47] Barnes R, Dhanoa M, Lister S J. Standard normal variatetransformation and de-trending of near-infrared diffuse reflectancespectra. Appl Spectrosc,1989,43:772~777
[48] Dhanoa M S, Lister S J, Sanderson R, et al. The link betweenmultiplicative scatter correction (MSC) and standard normal variate(SNV) transformations of NIR spectra. J Near Infrared Spectrosc,1994,2:43~47
[49] Fearn T, Riccioli C, Garrido-Varo A, et al. On the geometry of SNVand MSC. Chemometrics Intell Lab Syst,2009,96:22~26
[50] Savitzky A, Golay M J E. Smoothing and differentiation of data bysimplified least squares procedures. Anal Chem,1964,36:1627~1639
[51] Steinier J, Termonia Y, Deltour J. Smoothing and differentiation ofdata by simplified least square procedure. Anal Chem,1972,44:1906~1909
[52] Shao X G, Pang C Y, Su Q D. A novel method to calculate theapproximate derivative photoacoustic spectrum using continuouswavelet transform. Fresen J Anal Chem,2000,367:525~529
[53] Shao X G, Cai W S. Wavelet analysis in analytical chemistry. RevAnal Chem,1998,17:235~285
[54] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[55] Shao X G, Gu H, Cai W S, et al. Studies on data compression of1-DNMR spectra using wavelet transform. Spectrosc Spectr Anal,1999,19:139~141
[56] Wang L S, Yang X Y, Xi S F, et al. Wavelet Smoothing andDenoising to Process Capillary Electrophoresis Signals. Chem JChin Univ,1999,3:383~386
[57] Shao X G, Cai W S, Pan Z X. Wavelet transform and its applicationsin high performance liquid chromatography (HPLC) analysis.Chemometrics Intell Lab Syst,1999,45:249~256
[58] Shao X G, Shao L M, Zhao G W. Extraction of extended X-rayabsorption fine structure information from the experimental datausing the wavelet transform. Anal Commun1998,35:135~137
[59] Wolkenstein M, Hutter H, Nikolov S G, Grasserbauer M.Improvement of SIMS image classification by means of waveletde-noising. Fresenius J Anal Chem,1997,357:783~788
[60] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear-infrared spectra. Chemometrics Intell Lab Syst,1998,44:175~185
[61] Chen D, Wang F, Shao X G, et al. Elimination of interferenceinformation by a new hybrid algorithm for quantitative calibrationof near infrared spectra. Analyst,2003,128:1200~1203
[62] Woody N A, Feudale R N, Myles A J, et al. Transfer of multivariatecalibrations between four near-infrared spectrometers usingorthogonal signal correction. Anal Chem,2004,76:2595~2600
[63] Ni W, Brown S D, Man R. Wavelet Orthogonal SignalCorrection-Based Discriminant Analysis. Anal Chem,2009,81:8962~8967
[64] Westerhuis J A, de Jong S, Smilde A K. Direct orthogonal signalcorrection. Chemometrics Intell Lab Syst,2001,56:13~25
[65] Faber N M, Rajko R. How to avoid over-fitting in multivariatecalibration-The conventional validation approach and an alternative.Anal Chim Acta,2007,595:98~106
[66] Wold S. Cross-validatory estimation of the number of componentsin factor and principal components models. Technometrics,1978:397~405
[67] Burman P. A comparative study of ordinary cross-validation, v-foldcross-validation and the repeated learning-testing methods.Biometrika,1989,76:503~514
[68] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[69] Xu Q S, Liang Y Z, Du Y P. Monte Carlo cross-validation forselecting a model and estimating the prediction error in multivariatecalibration. J Chemometr,2004,18:112~120
[70] Osten D W. Selection of optimal regression models viacross-validation. J Chemometr,1988,2:39~48
[71] Rutledge D N, Barros A, Delgadillo I. PoLiSh--smoothed partialleast-squares regression. Anal Chim Acta,2001,446:279~294
[72] Gourvenec S, Pierna J A F, Massart D L, et al. An evaluation of thePoLiSh smoothed regression and the Monte Carlo Cross-Validationfor the determination of the complexity of a PLS model.Chemometrics Intell Lab Syst,2003,68:41~51
[73] Durbin J, Watson G S. Testing for serial correlation in least squaresregression: I. Biometrika,1950,37:409~428
[74] van der Voet H. Comparing the predictive accuracy of models usinga simple randomization test. Chemometrics Intell Lab Syst,1994,25:313~323
[75] Wiklund S, Nilsson D, Eriksson L, et al. A randomization test forPLS component selection. J Chemometr,2007,21:427~439
[76] Liu Z C, Ma X, Wen Y D, et al. A practical approach for nearinfrared spectral quantitative analysis of complex samples usingpartial least squares modeling. Sci China Ser B-Chem,2009,52:1021~1027
[77] Rousseeuw P J, Leroy A M, Wiley J. Robust regression and outlierdetection. Hoboken: Wiley Online Library,1987,1~18
[78] Liang Y Z, Kvalheim O M. Robust methods for multivariateanalysis-a tutorial review. Chemometrics Intell Lab Syst,1996,32:1~10
[79] Pierna J A F, Wahl F, de Noord O E, et al. Methods for outlierdetection in prediction. Chemometrics Intell Lab Syst,2002,63:27~39
[80] Belsley D A, Kuh E, Welsch R E. Regression diagnostics. Hoboken:Wiley Online Library;1980.6~84
[81] De Maesschalck R, Jouan-Rimbaud D, Massart D L. Themahalanobis distance. Chemometrics Intell Lab Syst,2000,50:1~18
[82] Hotelling H. Analysis of a complex of statistical variables intoprincipal components. J Educ Psychology,1933,24:417~441
[83] Rousseeuw P J, Van Zomeren B C. Unmasking multivariate outliersand leverage points. J Am Stat Assoc,1990,85:633~639
[84] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[85] Liu Z C, Cai W S, Shao X G. Outlier detection in near-infraredspectroscopic analysis by using Monte Carlo cross-validation. SciChina Ser B-Chem,2008,51:751~759
[86] Bian X H, Cai W S, Shao X G, et al. Detecting influentialobservations by cluster analysis and Monte Carlo cross-validation.Analyst,2010,135:2841~2847
[87] Cao D S, Liang Y Z, Xu Q S, et al. A new strategy of outlierdetection for QSAR/QSPR. J Comput Chem,2010,31:592~602
[88] Daszykowski M, Kaczmarek K, Vander Heyden Y V, et al. Robuststatistics in data analysis-A review: Basic concepts. ChemometricsIntell Lab Syst,2007,85:203~219
[89] Serneels S, Croux C, Filzmoser P, et al. Partial robust M-regression.Chemometrics Intell Lab Syst,2005,79:55~64
[90] Hubert M, Branden K V. Robust methods for partial least squaresregression. J Chemometr,2003,17:537~549
[91] Hubert M, Rousseeuw P J, Verboven S. A fast method for robustprincipal components with applications to chemometrics.Chemometrics Intell Lab Syst,2002,60:101~111
[92] Guyon I, Elisseeff A. An introduction to variable and featureselection. Journal of Machine Learning Research2003,3:1152~1182
[93] Andersen C M, Bro R. Variable selection in regression-a tutorial. JChemometr,2010,24:728~737
[94] Xiaobo Z, Jiewen Z, Povey M J W, et al. Variables selectionmethods in near-infrared spectroscopy. Anal Chim Acta,2010,667:14~32
[95] Lindgren F, Geladi P, R nnar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[96] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[97] Norgaard L, Saudland A, Wagner J, et al. Interval partialleast-squares regression (iPLS): A comparative chemometric studywith an example from near-infrared spectroscopy. Appl Spectrosc,2000,54:413~419
[98] Zou X B, Zhao J W, Huang X Y, et al. Use of FT-NIR spectrometryin non-invasive measurements of soluble solid contents (SSC) of'Fuji' apple based on different PLS models. Chemometrics Intell LabSyst,2007,87:43~51
[99] Jiang J H, Berry R J, Siesler H W, et al. Wavelength intervalselection in multicomponent spectral analysis by moving windowpartial least-squares regression with applications to mid-infrared andhear-infrared spectroscopic data. Anal Chem,2002,74:3555~3565
[100] Kasemsumran S, Du Y P, Murayama K, et al. Near-infraredspectroscopic determination of human serum albumin,gamma-globulin, and glucose in a control serum solution withsearching combination moving window partial least squares. AnalChim Acta,2004,512:223~230
[101] Bro R, De Jong S. A fast non-negativity-constrained least squaresalgorithm. J chemometr,1997,11:393~401
[102] Du Y P, Liang Y Z, Jiang J H, et al. Spectral regions selection toimprove prediction ability of PLS models by changeable sizemoving window partial least squares and searching combinationmoving window partial least squares. Anal Chim Acta,2004,501:183~191
[103] Gareth J, Peter W, Robert C G, et al. Development and validation ofa genetic algorithm for flexible docking. J Mol Bio1999,267:727~748
[104] Haupt Randy L, Haupt S E. Practical genetic algorithms. Hoboken:Wiley,2004,27~47
[105] Leardi R, Gonzalez A L. Genetic algorithms applied to featureselection in PLS regression: how and when to use them.Chemometrics Intell Lab Syst,1998,41:195~207
[106] Koljonen J, Nordling T E M, Alander J T. A review of geneticalgorithms in near infrared spectroscopy and chemometrics: past andfuture. J Near Infrared Spectrosc,2008,16:189~197
[107] Galvao R K H, Pimentel M F, Araujo M C U, et al. Aspects of thesuccessive projections algorithm for variable selection inmultivariate calibration applied to plasma emission spectrometry.Anal Chim Acta,2001,443:107~115
[108] Araujo M C U, Saldanha T C B, Galvao R K H, et al. Thesuccessive projections algorithm for variable selection inspectroscopic multicomponent analysis. Chemometrics Intell LabSyst,2001,57:65~73
[109] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[110] Shao X G, Wang F, Chen D, et al. A method for near-infraredspectral calibration of complex plant samples with wavelettransform and elimination of uninformative variables. Anal BioanalChem,2004,378:1382~1387
[111] Chen D, Shao X G, Hu B, et al. A Background and noiseelimination method for quantitative calibration of near infraredspectra. Anal Chim Acta,2004,511:37~45
[112] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[113] Han Q J, Wu H L, Cai C B, et al. An ensemble of Monte Carlouninformative variable elimination for wavelength selection. AnalChim Acta,2008,612:121~125
[114] Moros J, Kuligowski J, Quintas G, et al. New cut-off criterion foruninformative variable elimination in multivariate calibration ofnear-infrared spectra for the determination of heroin in illicit streetdrugs. Anal Chim Acta,2008,630:150~160
[115] Ye S, Wang D, Min S. Successive projections algorithm combinedwith uninformative variable elimination for spectral variableselection. Chemometrics Intell Lab Syst,2008,91:194~199
[116] Wu D, Chen X, Zhu X, et al. Uninformative variable eliminationfor improvement of successive projections algorithm on spectralmultivariable selection with different calibration algorithms for therapid and non-destructive determination of protein content in driedlaver. Anal Methods,2011,3:1790~1796
[117] Xu H, Liu Z C, Cai W S, et al. A wavelength selection methodbased on randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[118] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[119] Zheng K Y, Li Q Q, Wang J J, et al. Stability competitive adaptivereweighted sampling (SCARS) and its applications to multivariatecalibration of NIR spectra. Chemometrics Intell Lab Syst,2012,112:48~54
[120] Teofilo R F, Martins J P A, Ferreira M M C. Sorting variables byusing informative vectors as a strategy for feature selection inmultivariate regression. J Chemometr,2009,23:32~48
[121] Gosselin R, Rodrigue D, Duchesne C. A Bootstrap-VIP approachfor selecting wavelength intervals in spectral imaging applications.Chemometrics Intell Lab Syst,2010,100:12~21
[122] Ferre J, Faber N M. Net analyte signal calculation for multivariatecalibration. Chemometrics Intell Lab Syst,2003,69:123~136
[123] Brown P J. Wavelength selection in multicomponent near‐infraredcalibration. J Chemometr,1992,6:151~161
[124] Shao X G, Bian X H, Liu J J, et al. Multivariate calibration methodsin near infrared spectroscopic analysis. Anal Methods,2010,2:1662~1666
[125] Li H D, Liang Y Z, Xu Q S, et al. Model population analysis forvariable selection. J Chemometr,2010,24:418~423
[126] Su Z Q, Tong W D, Shi L M, et al. A partial least squares-basedconsensus regression method for the analysis of near-infraredcomplex spectral data of plant samples. Anal Lett,2006,39,2073~2083
[127] Li Y K, Shao X G, Cai W S. Partial least squares regression methodbased on consensus modeling for quantitative analysis ofnear-infrared spectra. Chem J Chin Univ,2007,28:246~249
[128] Chen D, Cai W S, Shao X G. Removing uncertain variables basedon ensemble partial least squares. Anal Chim Acta,2007,598:19~26
[129] Chen D, Cai W S, Shao X G. A strategy for enhancing thereliability of near-infrared spectral analysis. Vib Spectrosc,2008,47:113~118
[130] Li Y K, Shao X G, Cai W S. A consensus least squares supportvector regression (LS-SVR) for analysis of near-infrared spectra ofplant samples. Talanta,2007,72:217~222
[131] Cao D S, Xu Q S, Liang Y Z, et al. The boosting: A new idea ofbuilding models. Chemometrics Intell Lab Syst,2010,100:1~11
[132] Zhang M H, Xu Q S, Massart D L. Boosting partial least squares.Anal Chem,2005,77:1423~1431
[133] Zhou Y P, Cai C B, Huan S, et al. QSAR study of angiotensin IIantagonists using robust boosting partial least squares regression.Anal Chim Acta,2007,593:68~74
[134] Shao X G, Bian X H, Cai W S. An improved boosting partial leastsquares method for near-infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[135] Shinzawa H, Jiang J H, Ritthiruangdej P, et al. Investigations ofbagged kernel partial least squares (KPLS) and boosting KPLS withapplications to near-infrared (NIR) spectra. J Chemometr,2006,20:436~444
[136] Zhou Y P, Jiang J H, Wu H L,et al. Dry film method withytterbium as the internal standard for near infrared spectroscopicplasma glucose assay coupled with boosting support vectorregression. J Chemometr,2006,20:13~21
[137] Jing M, Cai W S, Shao X G. Quantitative Determination of theComponents in Corn and Tobacco Samples by Using Near-InfraredSpectroscopy and Multiblock Partial Least Squares. Anal Lett,2010,43:1910~1921
[138] Tan C, W J Y, Wu T, et al. Determination of nicotine in tobaccosamples by near-infrared spectroscopy and boosting partial leastsquares. Vib Spectrosc,2010,54:35~41
[139] Ni W, Brown S D, Man R. Stacked partial least squares regressionanalysis for spectral calibration and prediction. J Chemometr,2009,23:505~517
[140] Melssen W, Ustun B, Buydens L. SOMPLS: A supervisedself-organising map-partial least squares algorithm for multivariateregression problems. Chemometrics Intell Lab Syst,2007,86:102~120
[141] Ballabio D, Consonni V, Todeschini R. The Kohonen and CP-ANNtoolbox: A collection of MATLAB modules for Self OrganizingMaps and Counterpropagation Artificial Neural Networks.Chemometrics Intell Lab Syst,2009,98:115~122
[142] Tan C, Qin X, Li M L. Subspace Regression Ensemble MethodBased on Variable Clustering for Near-Infrared SpectroscopicCalibration. Anal Lett,2009,42:1693~1710
[143] Tan H, Brown S D. Dual-domain regression analysis for spectralcalibration models. J Chemometr,2003,17:111~122
[144] Jing M, Cai W S, Shao X G. Multiblock partial least squaresregression based on wavelet transform for quantitative analysis ofnear infrared spectra. Chemometrics Intell Lab Syst,2010,100:22~27
[145] Liu Z C, Cai W S, Shao X G. A weighted multiscale regression formultivariate calibration of near infrared spectra. Analyst,2009,134:261~266
[146] Chen D, Chen Z W, Grant E R. Adaptive multiscale regression forreliable Raman quantitative analysis. Analyst,2012,137:237~244
[147] Siesler H W, Ozaki Y, Kawata S, et al. Near-infrared spectroscopy,principles, instruments, applications. Wiley, New York,2002,11~35
[148] Roggo Y, Chalus P, Maurer L, et al. A review of near infraredspectroscopy and chemometrics in pharmaceutical technologies. JPharm Biomed Anal,2007,44:683~700
[149] Geladi P. Chemometrics in spectroscopy. Part1. Classicalchemometrics. Spectroc Acta Pt B-Atom Spectr,2003,58:767~782
[150] Chu X L, Yuan H F, Lu W Z. Progress and application of spectraldata pretreatment and wavelength selection methods in NIRanalytical technique. Prog Chem,2004,16:528~542
[151] Guo Q, Wu W, Massart D L. The robust normal variate transformfor pattern recognition with near-infrared data. Anal Chim Acta,1999,382:87~103
[152] Fearn T. On orthogonal signal correction. Chemometrics Intell LabSyst,2000,50:47~52
[153] Shao X G, Ma C X. A general approach to derivative calculationusing wavelet transform. Chemometrics Intell Lab Syst,2003,69:157~165
[154] Leardi R. Application of genetic algorithm-PLS for featureselection in spectral data sets. J Chemometr,2000,14:643~655
[155] Galvao R K H, Araujo M C U, Fragoso W D, et al. A variableelimination method to improve the parsimony of MLR models usingthe successive projections algorithm. Chemometrics Intell Lab Syst,2008,92:83~91
[156] Lorber A. Error propagation and figures of merit for quantificationby solving matrix equations. Anal Chem,1986,58:1167~1172
[157] Rajalahti T, Arneberg R, Berven F S, et al. Biomarker discovery inmass spectral profiles by means of selectivity ratio plot.Chemometrics Intell Lab Syst,2009,95:35~48
[158] Roger J M, Palagos B, Bertrand D, et al. CovSel: Variable selectionfor highly multivariate and multi-response calibration Application toIR spectroscopy. Chemometrics Intell Lab Syst,2011,106:216~223
[159] Kuenstner J T, Norris K H, McCarthy W F. Measurement ofhemoglobin in unlysed blood by near-infrared spectroscopy. ApplSpectrosc,1994,48:484~488
[160] Kalivas J H. Two data sets of near infrared spectra. ChemometricsIntell Lab Syst,1997,37:255~259
[161] Kennard R W, Stone L A. Computer aided desigh of experiments.Technometrics,1969,11:137~148
[162] Bosco G L. Symposium2009on near-infrared spectroscopy.Trac-Trends Anal Chem,2010,29:197~208
[163] Bro R. Multivariate calibration-What is in chemometrics for theanalytical chemist? Anal Chim Acta,2003,500:185~194
[164] Cummins D J, Andrews C W. Iteratively reweighted partial leastsquares: A performance analysis by monte carlo simulation. JChemometr,1995,9:489~507
[165] Breiman L. Bagging predictors. Mach Learn,1996,24:123~140
[166] Carney J, Cunningham P. Tuning diversity in bagged ensembles.Int J Neural Syst,2000,10:267~280
[167] Durand A, Devos O, Ruckebusch C, et al. Genetic algorithmoptimisation combined with partial least squares regression andmutual information variable selection procedures in near-infraredquantitative analysis of cotton-viscose textiles. Anal Chim Acta,2007,595:72~79
[168] Arakawa M, Yamashita Y, Funatsu K. Genetic algorithm-basedwavelength selection method for spectral calibration. J Chemometr,2011,25:10~19
[169] Shamsipur M, Zare-Shahabadi V, Hemmateenejad B, et al. Antcolony optimisation: a powerful tool for wavelength selection. JChemometr,2006,20:146~157
[170] Fu G H, Xu Q S, Li H D, et al. Elastic Net Grouping VariableSelection Combined with Partial Least Squares Regression(EN-PLSR) for the Analysis of Strongly Multi-collinearSpectroscopic Data. Appl Spectrosc,2011,65:402~408
[171] Chun H, Keles S. Sparse partial least squares regression forsimultaneous dimension reduction and variable selection. J R STATSOC B,2010,72:3~25
[172] McWilliams B, Montana G. Sparse partial least squares regressionfor on-line variable selection with multivariate data streams. StatAnal Data Mining,2010,3:170~193
[173] Lee D, Lee W, Lee Y, et al. Sparse partial least-squares regressionand its applications to high-throughput data analysis. ChemometricsIntell Lab Syst,2011,109:1~8
[174] Massart D L, Vandeginste B G M, Buydens L M C, et al. Handbookof chemometrics and Qualimetrics: Part A, Elsevier, Amsterdam,1997
[175] Wold S, Ruhe A, Wold H, et al. The collinearity problem in linearregression. The partial least squares (PLS) approach to generalizedinverses. SIAM J Sci Stat Comput,1984,5:735~743
[176] Barman I, Kong C R, Dingari N C, et al. Development of RobustCalibration Models Using Support Vector Machines forSpectroscopic Monitoring of Blood Glucose. Anal Chem,2010,82:9719~9726
[177] Belousov A I, Verzakov S A, von Frese J. Applicational aspects ofsupport vector machines. J of Chemometr,2002,16:482~489
[178] Jin L, Pierna J A F, Xu Q, et al. Delaunay triangulation method formultivariate calibration. Anal Chim Acta,2003,488:1~14
[179] Perez Marin D C, Garrido Varo A, Guerrero J E. Non-linearregression methods in NIRS quantitative analysis. Talanta,2007,72:28~42
[180] Cao D S, Wang B, Zeng M M, et al. A new strategy of exploringmetabolomics data using Monte Carlo tree. Analyst,2011,136:947~954
[181] Ma C X, Shao X G. Continuous wavelet transform applied toremoving the fluctuating background in near-infrared spectra. JChem Inf Comp Sci,2004,44:907~911
[182] Chen D, Hu B, Shao X G, et al. A new hybrid strategy forconstructing a robust calibration model for near-infrared spectralanalysis. Anal Bioanal Chem,2005,381:795~805
[183] Leardi R, Norgaard L. Sequential application of backward intervalpartial least squares and genetic algorithms for the selection ofrelevant spectral regions. J Chemometr,2004,18:486~497
[184] Rousseeuw P J, van Zomeren B C. Unmasking MultivariateOutliers and Leverage Points. J Am Stat Assoc,1990,85:871~880
[185] Fung W K. Unmasking outliers and leverage points: A confirmation.J Am Stat Assoc,1993:515~519
[186] Walczak B, Massart D L. Multiple outlier detection revisited.Chemometrics Intell Lab Syst,1998,41:1~15
[187] Hadi A S. Identifying multiple outliers in multivariate data. J R StatSoc B,1992,54:761~771
[188] De Vries S, Ter Braak C J F. Prediction error in partial least squaresregression: a critique on the deviation used in the Unscrambler.Chemometrics Intell Lab Syst,1995,30:239~245
[189] Hoy M, Steen K, Martens H. Review of partial least squaresregression prediction error in Unscrambler. Chemometrics Intell LabSyst,1998,44:123~133
[190] Pierna J A F, Jin L, Daszykowski M, et al. A methodology to detectoutliers/inliers in prediction with PLS. Chemometrics Intell LabSyst,2003,68:17~28
[191] Liebmann B, Filzmoser P, Varmuza K. Robust and classical PLSregression compared. J Chemometr,2010,24:111~120
[192] Vanden Branden K, Hubert M. Robustness properties of a robustpartial least squares regression method. Anal Chim Acta,2004,515:229~241
[193] Serneels S, Filzmoser P, Croux C, et al. Robust continuumregression. Chemometrics Intell Lab Syst,2005,76:197~204
[194] Breunig M M, Kriegel H P, Ng R T, et al. LOF: Identifyingdensity-based local outliers. Sigmod Rec,2000,29:93~104
[195] Li W, Goovaerts P, Meurens M. Quantitative analysis of individualsugars and acids in orange juices by near~infrared spectroscopy ofdry extract. J arg food chem,1996,44:2252~2259
[196] Rickert W S, Joza P J, Sharifi M, et al. Reductions in the tobaccospecific nitrosamine (TSNA) content of tobaccos taken fromcommercial Canadian cigarettes and corresponding reductions inTSNA deliveries in mainstream smoke from such cigarettes. RegulToxicol Pharm,2008,51:306~310
[197] Zhou J, Bai R S, Zhu Y F. Determination of four tobacco-specificnitrosamines in mainstream cigarette smoke by gaschromatography/ion trap mass spectrometry. Rapid Commun MassSp,2007,21:4086~4092
[198] Wu W J, Ashley D L, Watson C H. Simultaneous determination offive tobacco-specific nitrosamines in mainstream cigarette smoke byisotope dilution liquid chromatography/electrospray ionizationtandem mass spectrometry. Anal Chem,2003,75:4827~4832
[199] Wagner K A, Finkel N H, Fossett J E, et al. Development of aquantitative method for the analysis of tobacco-specificnitrosamines in mainstream cigarette smoke using isotope dilutionliquid chromatography/electrospray ionization tandem massspectrometry. Anal Chem,2005,77:1001~1006
[200] Wu J C, Joza P, Sharifi M, et al. Quantitative method for theanalysis of tobacco-specific nitrosamines in cigarette tobacco andmainstream cigarette smoke by use of isotope dilution liquidchromatography tandem mass spectrometry. Anal Chem,2008,80:1341~1345
[201] Wu W J, Song S Q, Ashley D L, et al. Assessment oftobacco-specific nitrosamines in the tobacco and mainstream smokeof Bidi cigarettes. Carcinogenesis,2004,25:283~287
[202] Clayton P M, Cunningham A, van Heemst J D H. Quantification offour tobacco-specific nitrosamines in cigarette filter tips using liquidchromatography-tandem mass spectrometry. Anal Methods,2010,2:1085~1094
[203] Kavvadias D, Scherer G, Urban M, et al. Simultaneousdetermination of four tobacco-specific N-nitrosamines (TSNA) inhuman urine. J Chromatogr B,2009,877:1185~1192
[204] Stepanov I, Hecht S S, Mirvish S S, et al. Comparative analysis oftobacco-specific nitrosamines and total N-nitroso compounds inMoldovan cigarette tobacco. J Agr Food Chem,2005,53:8082~8086
[205] Sleiman M, Maddalena R L, Gundel L A, et al. Rapid and sensitivegas chromatography-ion-trap tandem mass spectrometry method forthe determination of tobacco-specific N-nitrosamines in secondhandsmoke. J Chromatogr A,2009,1216:7899~7905
[206] Moros J, Garrigues S, de la Guardia M. Vibrational spectroscopyprovides a green tool for multi-component analysis. Trac-TrendsAnal Chem,2010,29:578~591
[207] Du C G, Zhou J M. Evaluation of soil fertility using infraredspectroscopy: a review. Environ Chem Lett,2009,7:97~113
[208] Cozzolino D. Near Infrared Spectroscopy in Natural ProductsAnalysis. Planta Med,2009,75:746~756
[209] Feng Y C, Zhang X B, Hu C Q. Construction of identificationsystem for non-invasive analysis of macrolides tablets using nearinfrared diffuse reflectance spectroscopy. J Pharm Biomed Anal,2010,51:12~17
[210] Liu J J, Xu H, Cai W S, et al. Discrimination of industrial productsby on-line near infrared spectroscopy with an improved dendrogram.Chin Chem Lett,2011,22:1241~1244
[211] Huang H B, Yu H Y, Xu H R, et al. Near infrared spectroscopy foron/in-line monitoring of quality in foods and beverages: A review. JFood Eng,2008,87:303~313
[212] Nordon A, Littlejohn D, Dann A S, et al. In situ monitoring of theseed stage of a fermentation process using non-invasive NIRspectrometry. Analyst,2008,133:660~666
[213] Roychoudhury P, O'Kennedy R, McNeil B, et al. Multiplexing fibreoptic near infrared (NIR) spectroscopy as an emerging technology tomonitor industrial bioprocesses. Anal Chim Acta,2007,590:110~117
[214] Liu J J, Ma X, Wen Y D, et al. Online near-Infrared SpectroscopyCombined with Alternating Trilinear Decomposition for ProcessAnalysis of Industrial Production and Quality Assurance. Ind EngChem Res,2011,50:7677~7681
[215] Egan W J, Mogan S L. Outlier detection in multivariate analyticalchemical data. Anal Chem,1998,70:2372~2379
[216] Huang Z X, Tao W, Fang J J, et al. Multivariate calibration ofon-line enrichment near-infrared (NIR) spectra and determination oftrace lead in water. Chemometrics Intell Lab Syst,2009,98:195~200
[217] Sheng N, Cai W S, Shao X G. An approach by using near-infrareddiffuse reflectance spectroscopy and resin adsorption for thedetermination of copper, cobalt and nickel ions in dilute solution.Talanta,2009,79:339~343
[218] Li J H, Zhang Y, Cai W S, et al. Simultaneous determination ofmercury, lead and cadmium ions in water using near-infraredspectroscopy with preconcentration by thiol-functionalizedmagnesium phyllosilicate clay. Talanta,2011,84:679~683
[219] Moros J, Llorca I, Cervera M L, et al. Chemometric determinationof arsenic and lead in untreated powdered red paprika by diffusereflectance near-infrared spectroscopy. Anal Chim Acta,2008,613:196~206
[220] Font R, Del Rio-Celestino M, Velez D, et al. Visible andnear-infrared spectroscopy as a technique for screening the inorganicarsenic content in the red crayfish (Procambarus clarkii Girard).Anal Chem,2004,76:3893~3898
[221] Font R, Velez D, Del Rio-Celestino M, et al. Screening inorganicarsenic in rice by visible and near-infrared spectroscopy. MicrochimActa,2005,151:231~239
[222] Cozzolino D, Kwiatkowski M J, Dambergs R G, et al. Analysis ofelements in wine using near infrared spectroscopy and partial leastsquares regression. Talanta,2008,74:711~716
[2]陆婉珍,袁洪福,徐广通等.现代近红外光谱分析技术.北京:中国石化出版社,2007,193~247
[3]刘建学.实用近红外光谱分析技术.北京:科学出版社,2008,158~239
[4] Massart D L. Chemometrics: a textbook. Amsterdam: ElsevierScience,1988,5~9
[5] Chau F. Chemometrics: from basics to wavelet transform. Hoboken:Wiley-Interscience,2004,5~12
[6] Brown S D, Tauler R, Walczak B. Comprehensive chemometrics:chemical and biochemical data analysis. Amsterdam: Elsevier,2009,459~463
[7] Martens H, Naes T. Multivariate calibration. Hoboken: John Wiley&Sons Inc,1992,1~30
[8] N s T, Isaksson T, Fearn T, et al. A user friendly guide to multivariatecalibration and classification. Chichester UK: NIR Publications,2002,11~17
[9] Brereton R G. Introduction to multivariate calibration in analyticalchemistry. Analyst,2000,125:2125~2154
[10] Williams P, Norris K. Near-infrared technology in the agriculturaland food industries. Minnesota: American Association of CerealChemists,1987
[11] Weisberg S. Applied linear regression, Third edition. Hoboken:Wiley Online Library,2005,211~230
[12] Hawkins D M. On the investigation of alternative regressions byprincipal component analysis. Appl Statist,1973,22:275~286
[13] N s T, Martens H. Principal component regression in NIR analysis:viewpoints, background details and selection of components. JChemometr,1988,2:155~167
[14] Sutter J M, Kalivas J H, Lang P M. Which principal components toutilize for principal component regression. J Chemometr,1992,6:217~225
[15] Depczynski U, Frost V J, Molt K. Genetic algorithms applied to theselection of factors in principal component regression. Anal ChimActa,2000,420:217~227
[16] Chang C W, Laird D A, Mausbach M J, Hurburgh Jr C R.Near-infrared reflectance spectroscopy-principal componentsregression analyses of soil properties. Soil Sci Soc Am J,2001.65:480~490
[17] Otsuka M. Comparative particle size determination of phenacetinbulk powder by using Kubelka-Munk theory and principalcomponent regression analysis based on near-infrared spectroscopy.Powder Technol,2004,141:244~250
[18]邵学广,蔡文生.化学信息学.北京:科学出版社,2005,206~207
[19] Vinzi V E, Chin W W, Henseler J. Handbook of partial least squares:Concepts, methods and applications. Berlin: Springer Verlag,2009,32~38
[20] Wold H. Partial least squares. Int J Cardiol,1985,147:581~591
[21] Geladi P, Kowalski B R. Partial least-squares regression: a tutorial.Anal Chim Acta,1986,185:1~17
[22] Wold S, Sjostrom M, Eriksson L. PLS-regression: a basic tool ofchemometrics. Chemometrics Intell Lab Syst,2001,58:109~130
[23] de Jong S. SIMPLS: an alternative approach to partial least squaresregression. Chemometrics Intell Lab Syst,1993,18:251~263
[24] Kvalheim O M, Karstang T V. Interpretation of latent variableregression models. Chemometrics Intell Lab Syst.1989,7:39~51
[25]Trygg J, Wold S. Orthogonal projections to latent structures (O-PLS).J Chemometr,2002,16:119~128
[26] Cloarec O, Dumas M E, Trygg J, et al. Evaluation of the orthogonalprojection on latent structure model limitations caused by chemicalshift variability and improved visualization of biomarker changes in1H NMR spectroscopic metabonomic studies. Anal Chem,2005,77:517~526
[27] Walczak B, Massart D L. The Radial Basis Functions--Partial LeastSquares approach as a flexible non-linear regression technique. AnalChim Acta,1996,331:177~185
[28] Rosipal R. Kernel partial least squares for nonlinear regression anddiscrimination. Neural Netw World,2003,13:291~300
[29] Chen D, Hu X G, Shao X G, et al. Variable selection by modifiedIPW (iterative predictor weighting)-PLS (partial least squares) incontinuous wavelet regression models. Analyst,2004,129:664~669
[30] Xu H, Cai W S, Shao X G. Weighted partial least squares regressionby variable grouping strategy for multivariate calibration of nearinfrared spectra. Anal Methods,2010,2:289~294
[31] Comon P. Independent component analysis, a new concept? SignalProcess,1994,36:287~314
[32] Hyvarinen A, Oja E. Independent component analysis: algorithmsand applications. Neural Netw,2000,13:411~430
[33] Wang G Q, Ding Q Z, Hou Z Y. Independent component analysisand its applications in signal processing for analytical chemistry.Trac-Trends Anal Chem,2008,27:368~376
[34] Shao X G, Liu Z C, Cai W S. Resolving multi-componentoverlapping GC-MS signals by immune algorithms. Trac-TrendsAnal Chem,2009,28:1312~1321
[35] Gustafsson M G. Independent component analysis yields chemicallyinterpretable latent variables in multivariate regression. J Chem InfModel,2005,45:1244~1255
[36] Shao X G, Wang W, Hou Z Y, et al. A new regression method basedon independent component analysis. Talanta,2006,69:676~680
[37] Zhang Y W, Zhang Y. Complex process monitoring using modifiedpartial least squares method of independent component regression.Chemometrics Intell Lab Syst,2009,98:143~148
[38] Al-Mbaideen A, Benaissa M. Coupling subband decomposition andindependent component regression for quantitative NIRspectroscopy. Chemometrics Intell Lab Syst,2011,108:112~122
[39] Parastar H, Jalali-Heravi M, Tauler R. Is Independent ComponentAnalysis appropriate for multivariate resolution in analyticalchemistry? Trac-Trends Anal Chem,2011.31:134~143
[40] Bouveresse D, Moya-González A, Ammari F, et al. Two novelmethods for the determination of the number of components inindependent components analysis models. Chemometrics Intell LabSyst,2012,112:24~32
[41] Candolfi A, De Maesschalck R, Jouan-Rimbaud D, et al. Theinfluence of data pre-processing in the pattern recognition ofexcipients near-infrared spectra. J Pharm Biomed Anal,1999,21:115~132
[42] Azzouz T, Puigdoménech A, Aragay M, et al. Comparison betweendifferent data pre-treatment methods in the analysis of foragesamples using near-infrared diffuse reflectance spectroscopy andpartial least-squares multivariate calibration method. Anal ChimActa,2003,484:121~134
[43] Rinnan A, van den Berg F, Engelsen S B. Review of the mostcommon pre-processing techniques for near-infrared spectra.Trac-Trends Anal Chem,2009,28:1201~1222
[44] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[45] Martens H, Stark E. Extended multiplicative signal correction andspectral interference subtraction: new preprocessing methods fornear infrared spectroscopy. J Pharm Biomed Anal,1991,9:625~635
[46] Martens H, Nielsen J P, Engelsen S B. Light scattering and lightabsorbance separated by extended multiplicative signal correction.Application to near-infrared transmission analysis of powdermixtures. Anal Chem,2003,75:394~404
[47] Barnes R, Dhanoa M, Lister S J. Standard normal variatetransformation and de-trending of near-infrared diffuse reflectancespectra. Appl Spectrosc,1989,43:772~777
[48] Dhanoa M S, Lister S J, Sanderson R, et al. The link betweenmultiplicative scatter correction (MSC) and standard normal variate(SNV) transformations of NIR spectra. J Near Infrared Spectrosc,1994,2:43~47
[49] Fearn T, Riccioli C, Garrido-Varo A, et al. On the geometry of SNVand MSC. Chemometrics Intell Lab Syst,2009,96:22~26
[50] Savitzky A, Golay M J E. Smoothing and differentiation of data bysimplified least squares procedures. Anal Chem,1964,36:1627~1639
[51] Steinier J, Termonia Y, Deltour J. Smoothing and differentiation ofdata by simplified least square procedure. Anal Chem,1972,44:1906~1909
[52] Shao X G, Pang C Y, Su Q D. A novel method to calculate theapproximate derivative photoacoustic spectrum using continuouswavelet transform. Fresen J Anal Chem,2000,367:525~529
[53] Shao X G, Cai W S. Wavelet analysis in analytical chemistry. RevAnal Chem,1998,17:235~285
[54] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[55] Shao X G, Gu H, Cai W S, et al. Studies on data compression of1-DNMR spectra using wavelet transform. Spectrosc Spectr Anal,1999,19:139~141
[56] Wang L S, Yang X Y, Xi S F, et al. Wavelet Smoothing andDenoising to Process Capillary Electrophoresis Signals. Chem JChin Univ,1999,3:383~386
[57] Shao X G, Cai W S, Pan Z X. Wavelet transform and its applicationsin high performance liquid chromatography (HPLC) analysis.Chemometrics Intell Lab Syst,1999,45:249~256
[58] Shao X G, Shao L M, Zhao G W. Extraction of extended X-rayabsorption fine structure information from the experimental datausing the wavelet transform. Anal Commun1998,35:135~137
[59] Wolkenstein M, Hutter H, Nikolov S G, Grasserbauer M.Improvement of SIMS image classification by means of waveletde-noising. Fresenius J Anal Chem,1997,357:783~788
[60] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear-infrared spectra. Chemometrics Intell Lab Syst,1998,44:175~185
[61] Chen D, Wang F, Shao X G, et al. Elimination of interferenceinformation by a new hybrid algorithm for quantitative calibrationof near infrared spectra. Analyst,2003,128:1200~1203
[62] Woody N A, Feudale R N, Myles A J, et al. Transfer of multivariatecalibrations between four near-infrared spectrometers usingorthogonal signal correction. Anal Chem,2004,76:2595~2600
[63] Ni W, Brown S D, Man R. Wavelet Orthogonal SignalCorrection-Based Discriminant Analysis. Anal Chem,2009,81:8962~8967
[64] Westerhuis J A, de Jong S, Smilde A K. Direct orthogonal signalcorrection. Chemometrics Intell Lab Syst,2001,56:13~25
[65] Faber N M, Rajko R. How to avoid over-fitting in multivariatecalibration-The conventional validation approach and an alternative.Anal Chim Acta,2007,595:98~106
[66] Wold S. Cross-validatory estimation of the number of componentsin factor and principal components models. Technometrics,1978:397~405
[67] Burman P. A comparative study of ordinary cross-validation, v-foldcross-validation and the repeated learning-testing methods.Biometrika,1989,76:503~514
[68] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[69] Xu Q S, Liang Y Z, Du Y P. Monte Carlo cross-validation forselecting a model and estimating the prediction error in multivariatecalibration. J Chemometr,2004,18:112~120
[70] Osten D W. Selection of optimal regression models viacross-validation. J Chemometr,1988,2:39~48
[71] Rutledge D N, Barros A, Delgadillo I. PoLiSh--smoothed partialleast-squares regression. Anal Chim Acta,2001,446:279~294
[72] Gourvenec S, Pierna J A F, Massart D L, et al. An evaluation of thePoLiSh smoothed regression and the Monte Carlo Cross-Validationfor the determination of the complexity of a PLS model.Chemometrics Intell Lab Syst,2003,68:41~51
[73] Durbin J, Watson G S. Testing for serial correlation in least squaresregression: I. Biometrika,1950,37:409~428
[74] van der Voet H. Comparing the predictive accuracy of models usinga simple randomization test. Chemometrics Intell Lab Syst,1994,25:313~323
[75] Wiklund S, Nilsson D, Eriksson L, et al. A randomization test forPLS component selection. J Chemometr,2007,21:427~439
[76] Liu Z C, Ma X, Wen Y D, et al. A practical approach for nearinfrared spectral quantitative analysis of complex samples usingpartial least squares modeling. Sci China Ser B-Chem,2009,52:1021~1027
[77] Rousseeuw P J, Leroy A M, Wiley J. Robust regression and outlierdetection. Hoboken: Wiley Online Library,1987,1~18
[78] Liang Y Z, Kvalheim O M. Robust methods for multivariateanalysis-a tutorial review. Chemometrics Intell Lab Syst,1996,32:1~10
[79] Pierna J A F, Wahl F, de Noord O E, et al. Methods for outlierdetection in prediction. Chemometrics Intell Lab Syst,2002,63:27~39
[80] Belsley D A, Kuh E, Welsch R E. Regression diagnostics. Hoboken:Wiley Online Library;1980.6~84
[81] De Maesschalck R, Jouan-Rimbaud D, Massart D L. Themahalanobis distance. Chemometrics Intell Lab Syst,2000,50:1~18
[82] Hotelling H. Analysis of a complex of statistical variables intoprincipal components. J Educ Psychology,1933,24:417~441
[83] Rousseeuw P J, Van Zomeren B C. Unmasking multivariate outliersand leverage points. J Am Stat Assoc,1990,85:633~639
[84] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[85] Liu Z C, Cai W S, Shao X G. Outlier detection in near-infraredspectroscopic analysis by using Monte Carlo cross-validation. SciChina Ser B-Chem,2008,51:751~759
[86] Bian X H, Cai W S, Shao X G, et al. Detecting influentialobservations by cluster analysis and Monte Carlo cross-validation.Analyst,2010,135:2841~2847
[87] Cao D S, Liang Y Z, Xu Q S, et al. A new strategy of outlierdetection for QSAR/QSPR. J Comput Chem,2010,31:592~602
[88] Daszykowski M, Kaczmarek K, Vander Heyden Y V, et al. Robuststatistics in data analysis-A review: Basic concepts. ChemometricsIntell Lab Syst,2007,85:203~219
[89] Serneels S, Croux C, Filzmoser P, et al. Partial robust M-regression.Chemometrics Intell Lab Syst,2005,79:55~64
[90] Hubert M, Branden K V. Robust methods for partial least squaresregression. J Chemometr,2003,17:537~549
[91] Hubert M, Rousseeuw P J, Verboven S. A fast method for robustprincipal components with applications to chemometrics.Chemometrics Intell Lab Syst,2002,60:101~111
[92] Guyon I, Elisseeff A. An introduction to variable and featureselection. Journal of Machine Learning Research2003,3:1152~1182
[93] Andersen C M, Bro R. Variable selection in regression-a tutorial. JChemometr,2010,24:728~737
[94] Xiaobo Z, Jiewen Z, Povey M J W, et al. Variables selectionmethods in near-infrared spectroscopy. Anal Chim Acta,2010,667:14~32
[95] Lindgren F, Geladi P, R nnar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[96] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[97] Norgaard L, Saudland A, Wagner J, et al. Interval partialleast-squares regression (iPLS): A comparative chemometric studywith an example from near-infrared spectroscopy. Appl Spectrosc,2000,54:413~419
[98] Zou X B, Zhao J W, Huang X Y, et al. Use of FT-NIR spectrometryin non-invasive measurements of soluble solid contents (SSC) of'Fuji' apple based on different PLS models. Chemometrics Intell LabSyst,2007,87:43~51
[99] Jiang J H, Berry R J, Siesler H W, et al. Wavelength intervalselection in multicomponent spectral analysis by moving windowpartial least-squares regression with applications to mid-infrared andhear-infrared spectroscopic data. Anal Chem,2002,74:3555~3565
[100] Kasemsumran S, Du Y P, Murayama K, et al. Near-infraredspectroscopic determination of human serum albumin,gamma-globulin, and glucose in a control serum solution withsearching combination moving window partial least squares. AnalChim Acta,2004,512:223~230
[101] Bro R, De Jong S. A fast non-negativity-constrained least squaresalgorithm. J chemometr,1997,11:393~401
[102] Du Y P, Liang Y Z, Jiang J H, et al. Spectral regions selection toimprove prediction ability of PLS models by changeable sizemoving window partial least squares and searching combinationmoving window partial least squares. Anal Chim Acta,2004,501:183~191
[103] Gareth J, Peter W, Robert C G, et al. Development and validation ofa genetic algorithm for flexible docking. J Mol Bio1999,267:727~748
[104] Haupt Randy L, Haupt S E. Practical genetic algorithms. Hoboken:Wiley,2004,27~47
[105] Leardi R, Gonzalez A L. Genetic algorithms applied to featureselection in PLS regression: how and when to use them.Chemometrics Intell Lab Syst,1998,41:195~207
[106] Koljonen J, Nordling T E M, Alander J T. A review of geneticalgorithms in near infrared spectroscopy and chemometrics: past andfuture. J Near Infrared Spectrosc,2008,16:189~197
[107] Galvao R K H, Pimentel M F, Araujo M C U, et al. Aspects of thesuccessive projections algorithm for variable selection inmultivariate calibration applied to plasma emission spectrometry.Anal Chim Acta,2001,443:107~115
[108] Araujo M C U, Saldanha T C B, Galvao R K H, et al. Thesuccessive projections algorithm for variable selection inspectroscopic multicomponent analysis. Chemometrics Intell LabSyst,2001,57:65~73
[109] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[110] Shao X G, Wang F, Chen D, et al. A method for near-infraredspectral calibration of complex plant samples with wavelettransform and elimination of uninformative variables. Anal BioanalChem,2004,378:1382~1387
[111] Chen D, Shao X G, Hu B, et al. A Background and noiseelimination method for quantitative calibration of near infraredspectra. Anal Chim Acta,2004,511:37~45
[112] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[113] Han Q J, Wu H L, Cai C B, et al. An ensemble of Monte Carlouninformative variable elimination for wavelength selection. AnalChim Acta,2008,612:121~125
[114] Moros J, Kuligowski J, Quintas G, et al. New cut-off criterion foruninformative variable elimination in multivariate calibration ofnear-infrared spectra for the determination of heroin in illicit streetdrugs. Anal Chim Acta,2008,630:150~160
[115] Ye S, Wang D, Min S. Successive projections algorithm combinedwith uninformative variable elimination for spectral variableselection. Chemometrics Intell Lab Syst,2008,91:194~199
[116] Wu D, Chen X, Zhu X, et al. Uninformative variable eliminationfor improvement of successive projections algorithm on spectralmultivariable selection with different calibration algorithms for therapid and non-destructive determination of protein content in driedlaver. Anal Methods,2011,3:1790~1796
[117] Xu H, Liu Z C, Cai W S, et al. A wavelength selection methodbased on randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[118] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[119] Zheng K Y, Li Q Q, Wang J J, et al. Stability competitive adaptivereweighted sampling (SCARS) and its applications to multivariatecalibration of NIR spectra. Chemometrics Intell Lab Syst,2012,112:48~54
[120] Teofilo R F, Martins J P A, Ferreira M M C. Sorting variables byusing informative vectors as a strategy for feature selection inmultivariate regression. J Chemometr,2009,23:32~48
[121] Gosselin R, Rodrigue D, Duchesne C. A Bootstrap-VIP approachfor selecting wavelength intervals in spectral imaging applications.Chemometrics Intell Lab Syst,2010,100:12~21
[122] Ferre J, Faber N M. Net analyte signal calculation for multivariatecalibration. Chemometrics Intell Lab Syst,2003,69:123~136
[123] Brown P J. Wavelength selection in multicomponent near‐infraredcalibration. J Chemometr,1992,6:151~161
[124] Shao X G, Bian X H, Liu J J, et al. Multivariate calibration methodsin near infrared spectroscopic analysis. Anal Methods,2010,2:1662~1666
[125] Li H D, Liang Y Z, Xu Q S, et al. Model population analysis forvariable selection. J Chemometr,2010,24:418~423
[126] Su Z Q, Tong W D, Shi L M, et al. A partial least squares-basedconsensus regression method for the analysis of near-infraredcomplex spectral data of plant samples. Anal Lett,2006,39,2073~2083
[127] Li Y K, Shao X G, Cai W S. Partial least squares regression methodbased on consensus modeling for quantitative analysis ofnear-infrared spectra. Chem J Chin Univ,2007,28:246~249
[128] Chen D, Cai W S, Shao X G. Removing uncertain variables basedon ensemble partial least squares. Anal Chim Acta,2007,598:19~26
[129] Chen D, Cai W S, Shao X G. A strategy for enhancing thereliability of near-infrared spectral analysis. Vib Spectrosc,2008,47:113~118
[130] Li Y K, Shao X G, Cai W S. A consensus least squares supportvector regression (LS-SVR) for analysis of near-infrared spectra ofplant samples. Talanta,2007,72:217~222
[131] Cao D S, Xu Q S, Liang Y Z, et al. The boosting: A new idea ofbuilding models. Chemometrics Intell Lab Syst,2010,100:1~11
[132] Zhang M H, Xu Q S, Massart D L. Boosting partial least squares.Anal Chem,2005,77:1423~1431
[133] Zhou Y P, Cai C B, Huan S, et al. QSAR study of angiotensin IIantagonists using robust boosting partial least squares regression.Anal Chim Acta,2007,593:68~74
[134] Shao X G, Bian X H, Cai W S. An improved boosting partial leastsquares method for near-infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[135] Shinzawa H, Jiang J H, Ritthiruangdej P, et al. Investigations ofbagged kernel partial least squares (KPLS) and boosting KPLS withapplications to near-infrared (NIR) spectra. J Chemometr,2006,20:436~444
[136] Zhou Y P, Jiang J H, Wu H L,et al. Dry film method withytterbium as the internal standard for near infrared spectroscopicplasma glucose assay coupled with boosting support vectorregression. J Chemometr,2006,20:13~21
[137] Jing M, Cai W S, Shao X G. Quantitative Determination of theComponents in Corn and Tobacco Samples by Using Near-InfraredSpectroscopy and Multiblock Partial Least Squares. Anal Lett,2010,43:1910~1921
[138] Tan C, W J Y, Wu T, et al. Determination of nicotine in tobaccosamples by near-infrared spectroscopy and boosting partial leastsquares. Vib Spectrosc,2010,54:35~41
[139] Ni W, Brown S D, Man R. Stacked partial least squares regressionanalysis for spectral calibration and prediction. J Chemometr,2009,23:505~517
[140] Melssen W, Ustun B, Buydens L. SOMPLS: A supervisedself-organising map-partial least squares algorithm for multivariateregression problems. Chemometrics Intell Lab Syst,2007,86:102~120
[141] Ballabio D, Consonni V, Todeschini R. The Kohonen and CP-ANNtoolbox: A collection of MATLAB modules for Self OrganizingMaps and Counterpropagation Artificial Neural Networks.Chemometrics Intell Lab Syst,2009,98:115~122
[142] Tan C, Qin X, Li M L. Subspace Regression Ensemble MethodBased on Variable Clustering for Near-Infrared SpectroscopicCalibration. Anal Lett,2009,42:1693~1710
[143] Tan H, Brown S D. Dual-domain regression analysis for spectralcalibration models. J Chemometr,2003,17:111~122
[144] Jing M, Cai W S, Shao X G. Multiblock partial least squaresregression based on wavelet transform for quantitative analysis ofnear infrared spectra. Chemometrics Intell Lab Syst,2010,100:22~27
[145] Liu Z C, Cai W S, Shao X G. A weighted multiscale regression formultivariate calibration of near infrared spectra. Analyst,2009,134:261~266
[146] Chen D, Chen Z W, Grant E R. Adaptive multiscale regression forreliable Raman quantitative analysis. Analyst,2012,137:237~244
[1] Siesler H W, Ozaki Y, Kawata S, et al. Near-infrared spectroscopy,principles, instruments, applications. Wiley, New York,2002,11~35
[2] Roggo Y, Chalus P, Maurer L, et al. A review of near infraredspectroscopy and chemometrics in pharmaceutical technologies. JPharm Biomed Anal,2007,44:683~700
[3] Geladi P. Chemometrics in spectroscopy. Part1. Classicalchemometrics. Spectroc Acta Pt B-Atom Spectr,2003,58:767~782
[4] Wold S, Sjostrom M, Eriksson L. PLS-regression: a basic tool ofchemometrics. Chemometrics Intell Lab Syst,2001,58:109~130
[5] Chu X L, Yuan H F, Lu W Z. Progress and application of spectral datapretreatment and wavelength selection methods in NIR analyticaltechnique. Prog Chem,2004,16:528~542
[6] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[7] Guo Q, Wu W, Massart D L. The robust normal variate transform forpattern recognition with near-infrared data. Anal Chim Acta,1999,382:87~103
[8] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear-infrared spectra. Chemometrics Intell Lab Syst,1998,44:175~185
[9] Fearn T. On orthogonal signal correction. Chemometrics Intell LabSyst,2000,50:47~52
[10] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[11] Shao X G, Ma C X. A general approach to derivative calculationusing wavelet transform. Chemometrics Intell Lab Syst,2003,69:157~165
[12] Andersen C M, Bro R. Variable selection in regression-a tutorial. JChemometr,2010,24:728~737
[13] Zou X B, Zhao J W, Povey M J W, et al. Variables selection methodsin near-infrared spectroscopy. Anal Chim Acta,2010,667:14~32
[14] Leardi R, Gonzalez A L. Genetic algorithms applied to featureselection in PLS regression: how and when to use them.Chemometrics Intell Lab Syst,1998,41:195~207
[15] Leardi R. Application of genetic algorithm-PLS for feature selectionin spectral data sets. J Chemometr,2000,14:643~655
[16] Lindgren F, Geladi P, Rannar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[17] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[18] Centner V, Massart D L, de Noord O E, et al. Elimination ofUninformative Variables for Multivariate Calibration. Anal Chem,1996,68:3851~3858
[19] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[20] Han Q J, Wu H L, Cai C B, et al. An ensemble of Monte Carlouninformative variable elimination for wavelength selection. AnalChim Acta,2008,612:121~125
[21] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[22] Araujo M C U, Saldanha T C B, Galvao R K H, et al. Thesuccessive projections algorithm for variable selection inspectroscopic multicomponent analysis. Chemometrics Intell LabSyst,2001,57:65~73
[23] Galvao R K H, Araujo M C U, Fragoso W D, et al. A variableelimination method to improve the parsimony of MLR models usingthe successive projections algorithm. Chemometrics Intell Lab Syst,2008,92:83~91
[24] Teofilo R F, Martins J P A, Ferreira M M C. Sorting variables byusing informative vectors as a strategy for feature selection inmultivariate regression. J Chemometr,2009,23:32~48
[25] Gosselin R, Rodrigue D, Duchesne C. A Bootstrap-VIP approach forselecting wavelength intervals in spectral imaging applications.Chemometrics Intell Lab Syst,2010,100:12~21
[26] Lorber A. Error propagation and figures of merit for quantificationby solving matrix equations. Anal Chem,1986,58:1167~1172
[27] Ferre J, Faber N M. Net analyte signal calculation for multivariatecalibration. Chemometrics Intell Lab Syst,2003,69:123~136
[28] Brown P J. Wavelength selection in multicomponent near-infraredcalibration. J Chemometr,1992,6:151~161
[29] Rajalahti T, Arneberg R, Berven F S, et al. Biomarker discovery inmass spectral profiles by means of selectivity ratio plot.Chemometrics Intell Lab Syst,2009,95:35~48
[30] Jiang J H, Berry R J, Siesler H W, et al. Wavelength intervalselection in multicomponent spectral analysis by moving windowpartial least-squares regression with applications to mid-infrared andhear-infrared spectroscopic data. Anal Chem,2002,74:3555~3565
[31] Roger J M, Palagos B, Bertrand D, et al. CovSel: Variable selectionfor highly multivariate and multi-response calibration Application toIR spectroscopy. Chemometrics Intell Lab Syst,2011,106:216~223
[32] Li Y K, Shao X G, Cai W S. A consensus least squares supportvector regression (LS-SVR) for analysis of near-infrared spectra ofplant samples. Talanta,2007,72:217~222
[33] Liu Z C, Cai W S, Shao X G. A weighted multiscale regression formultivariate calibration of near infrared spectra. Analyst,2009,134:261~266
[34] Shao X G, Bian X H, Cai W S. An improved boosting partial leastsquares method for near-infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[35] Cao D S, Xu Q S, Liang Y Z, et al. The boosting: A new idea ofbuilding models. Chemometrics Intell Lab Syst,2010,100:1~11
[36] de Jong S. SIMPLS: an alternative approach to partial least squaresregression. Chemometrics Intell Lab Syst,1993,18:251~263
[37] Bro R, De Jong S. A fast non-negativity-constrained least squaresalgorithm. J Chemometr,1997,11:393~401
[38] Kuenstner J T, Norris K H, McCarthy W F. Measurement ofhemoglobin in unlysed blood by near-infrared spectroscopy. ApplSpectrosc,1994,48:484~488
[39] Kalivas J H. Two data sets of near infrared spectra. ChemometricsIntell Lab Syst,1997,37:255~259
[40] Kennard R W, Stone L A. Computer aided desigh of experiments.Technometrics,1969,11:137~148
[41] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[42] Liu Z C, Ma X, Wen Y D, et al. A practical approach for nearinfrared spectral quantitative analysis of complex samples usingpartial least squares modeling. Sci China Ser B-Chem,2009,52:1021~1027
[1] Bosco G L. Symposium2009on near-infrared spectroscopy.Trac-Trends Anal Chem,2010,29:197~208
[2] Wold S, Sjostrom M, Eriksson L. PLS-regression: A basic tool ofchemometrics. Chemometr Intell Lab Syst,2001,58:109~130
[3] Bro R. Multivariate calibration-What is in chemometrics for theanalytical chemist? Anal Chim Acta,2003,500:185~194
[4] Candolfi A, De Maesschalck R, Jouan-Rimbaud D, et al. Theinfluence of data pre-processing in the pattern recognition ofexcipients near-infrared spectra. J Pharm Biomed Anal,1999,21:115~132
[5] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[6] Guo Q, Wu W, Massart D L. The robust normal variate transform forpattern recognition with near-infrared data. Anal Chim Acta,1999,382:87~103
[7] Savitzky A, Golay M J E. Smoothing and differentiation of data bysimplified least squares procedures. Anal Chem,1964,36:1627~1639
[8] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear-infrared spectra. Chemometr Intell Lab Syst,1998,44:175~185
[9]Fearn T. On orthogonal signal correction. Chemometr. Intell Lab Syst,2000,50:47~52
[10] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Acc Chem Res,2003,36:276~283
[11] Chen D, Shao X G, Hu B, et al. A background and noise eliminationmethod for quantitative calibration of near infrared spectra. AnalChim Acta,2004,511:37~45
[12] Cummins D J, Andrews C W. Iteratively reweighted partial leastsquares: A performance analysis by monte carlo simulation. JChemometr,1995,9:489~507
[13] Serneels S, Croux C, Filzmoser P, et al. Partial robust M-regression.Chemometr Intell Lab Syst,2005,79:55~64
[14] Lindgren F, Geladi P, Rannar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[15] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[16] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[17] Shao X G, Wang F, Chen D, et al. A method for near-infraredspectral calibration of complex plant samples with wavelettransform and elimination of uninformative variables. Anal BioanalChem,2004,378:1382~1387
[18] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis. Chemometr.Intell Lab Syst,2009,97:189~193
[19] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometr Intell Lab Syst,2008,90:188~194
[20] Galvao R K H, Araujo M C U, Fragoso W D, et al. A variableelimination method to improve the parsimony of MLR models usingthe successive projections algorithm. Chemometr Intell Lab Syst,2008,92:83~91
[21] Ye S F, Wang D, Min S G. Successive projections algorithmcombined with uninformative variable elimination for spectralvariable selection. Chemometr Intell Lab Syst,2008,91:194~199
[22] Breiman L. Bagging predictors. Mach Learn,1996,24:123~140
[23] Cao D S, Xu Q S, Liang Y Z, et al. The boosting, A new idea ofbuilding models. Chemometr Intell Lab Syst,2010,100:1~11
[24] Li Y K, Shao X G, Cai W S. Partial least squares regression methodbased on consensus modeling for quantitative analysis ofnear-infrared spectra. Chem J Chin Univ,2007,28:246~249
[25] Li Y K, Shao X G, Cai W S. A consensus least squares supportvector regression (LS-SVR) for analysis of near-infrared spectra ofplant samples. Talanta,2007,72:217~222
[26] Zhou Y P, Cai C B, Huan S, et al. QSAR study of angiotensin IIantagonists using robust boosting partial least squares regression.Anal Chim Acta,2007,593:68~74
[27] Shao X G, Bian X H, Liu Z C, et al. An improved boosting partialleast squares for near-infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[28] Carney J, Cunningham P. Tuning diversity in bagged ensembles. IntJ Neural Syst,2000,10:267~280
[29] Tan C, Qin X, Li M L. Subspace regression ensemble method basedon variable clustering for near-infrared spectroscopic calibration.Anal Lett,2009,42:1693~1710
[30] Liu Z C, Cai W S, Shao X G. A weighted multiscale regression formultivariate calibration of near infrared spectra. Analyst,2009,134:261~266
[31] Ni W D, Brown S D, Man R L. Stacked partial least squaresregression analysis for spectral calibration and prediction. JChemometr,2009,23:505~517
[32] Xu Q S, Liang Y Z. Monte Carlo cross validation. Chemometr IntellLab Syst,2001,56:1~11
[33] Kennard R W, Stone L A. Computer aided design of experiments.Technometrics,1969,11:137~148
[1] Siesler H W, Ozaki Y, Kawata S, et al. Near-infrared spectroscopy,principles, instruments, applications. Wiley, New York,2002,11~35
[2] Geladi P. Chemometrics in spectroscopy. Part1. Classicalchemometrics. Spectroc Acta Pt B-Atom Spectr,2003,58:767~782
[3] Wold S, Sjostrom M, Eriksson L. PLS-regression: a basic tool ofchemometrics. Chemometrics Intell Lab Syst,2001,58:109~130
[4] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[5] Shao X G, Ma C X. A general approach to derivative calculationusing wavelet transform. Chemometrics Intell Lab Syst,2003,69:157~165
[6] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[7] Guo Q, Wu W, Massart D L. The robust normal variate transform forpattern recognition with near-infrared data. Anal Chim Acta,1999,382:87~103
[8] Andersen C M, Bro R. Variable selection in regression-a tutorial. JChemometr,2010,24:728~737
[9] Zou X B, Zhao J W, Povey M J W, et al. Variables selection methodsin near-infrared spectroscopy. Anal Chim Acta,2010,667:14~32
[10] Lindgren F, Geladi P, Rannar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[11] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[12] Centner V, Massart D L, de Noord O E, et al. Elimination ofUninformative Variables for Multivariate Calibration. Anal Chem,1996,68:3851~3858
[13] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[14] Han Q J, Wu H L, Cai C B, et al. An ensemble of Monte Carlouninformative variable elimination for wavelength selection. AnalChim Acta,2008,612:121~125
[15] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[16] Teofilo R F, Martins J P A, Ferreira M M C. Sorting variables byusing informative vectors as a strategy for feature selection inmultivariate regression. J Chemometr,2009,23:32~48
[17] Durand A, Devos O, Ruckebusch C, et al. Genetic algorithmoptimisation combined with partial least squares regression andmutual information variable selection procedures in near-infraredquantitative analysis of cotton-viscose textiles. Anal Chim Acta,2007,595:72~79
[18] Arakawa M, Yamashita Y, Funatsu K. Genetic algorithm-basedwavelength selection method for spectral calibration. J Chemometr,2011,25:10~19
[19] Shamsipur M, Zare-Shahabadi V, Hemmateenejad B, et al. Antcolony optimisation: a powerful tool for wavelength selection. JChemometr,2006,20:146~157
[20] Galvao R K H, Araujo M C U, Fragoso W D, et al. A variableelimination method to improve the parsimony of MLR models usingthe successive projections algorithm. Chemometrics Intell Lab Syst,2008,92:83~91
[21] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[22] Fu G H, Xu Q S, Li H D, et al. Elastic Net Grouping VariableSelection Combined with Partial Least Squares Regression(EN-PLSR) for the Analysis of Strongly Multi-collinearSpectroscopic Data. Appl Spectrosc,2011,65:402~408
[23] Chun H, Keles S. Sparse partial least squares regression forsimultaneous dimension reduction and variable selection. J R STATSOC B,2010,72:3~25
[24] McWilliams B, Montana G. Sparse partial least squares regressionfor on-line variable selection with multivariate data streams. StatAnal Data Mining,2010,3:170~193
[25] Lee D, Lee W, Lee Y, et al. Sparse partial least-squares regressionand its applications to high-throughput data analysis. ChemometricsIntell Lab Syst,2011,109:1~8
[26] Roger J M, Palagos B, Bertrand D, et al. CovSel: Variable selectionfor highly multivariate and multi-response calibration Application toIR spectroscopy. Chemometrics Intell Lab Syst,2011,106:216~223
[27] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[28] Kennard R W, Stone L A. Computer aided desigh of experiments.Technometrics,1969,11:137~148
[1] Siesler H W, Ozaki Y, Kawata S, et al. Near-infrared spectroscopy,principles, instruments, applications, Wiley, New York,2002
[2] Massart D L, Vandeginste B G M, Buydens L M C, et al. Handbookof chemometrics and Qualimetrics: Part A, Elsevier, Amsterdam,1997
[3] Wold S, Ruhe A, Wold H, et al. The collinearity problem in linearregression. The partial least squares (PLS) approach to generalizedinverses. SIAM J Sci Stat Comput,1984,5:735~743
[4] Shao X G, Bian X H, Liu J J, et al. Multivariate calibration methodsin near infrared spectroscopic analysis. Anal Methods,2010,2:1662~1666
[5] de Jong S. SIMPLS: an alternative approach to partial least squaresregression. Chemometrics Intell Lab Syst,1993,18:251~263
[6] Barman I, Kong C R, Dingari N C, et al. Development of RobustCalibration Models Using Support Vector Machines forSpectroscopic Monitoring of Blood Glucose. Anal Chem,2010,82:9719~9726
[7] Belousov A I, Verzakov S A, von Frese J. Applicational aspects ofsupport vector machines. J of Chemometr,2002,16:482~489
[8] Li Y K, Shao X G, Cai W S. A consensus least squares support vectorregression (LS-SVR) for analysis of near-infrared spectra of plantsamples. Talanta,2007,72:217~222
[9] Jin L, Pierna J A F, Xu Q, et al. Delaunay triangulation method formultivariate calibration. Anal Chim Acta,2003,488:1~14
[10] Perez Marin D C, Garrido Varo A, Guerrero J E. Non-linearregression methods in NIRS quantitative analysis. Talanta,2007,72:28~42
[11] Li Y K, Shao X G, Cai W S. Partial least squares regression methodbased on consensus modeling for quantitative analysis ofnear-infrared spectra. Chem J Chin Univ,2007,28:246~249
[12] Cao D S, Wang B, Zeng M M, et al. A new strategy of exploringmetabolomics data using Monte Carlo tree. Analyst,2011,136:947~954
[13] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[14] Ma C X, Shao X G. Continuous wavelet transform applied toremoving the fluctuating background in near-infrared spectra. JChem Inf Comp Sci,2004,44:907~911
[15] Chen D, Shao X G, Hu B, et al. A Background and noise eliminationmethod for quantitative calibration of near infrared spectra. AnalChim Acta,2004,511:37~45.
[16] Chen D, Hu B, Shao X G, et al. A new hybrid strategy forconstructing a robust calibration model for near-infrared spectralanalysis. Anal Bioanal Chem,2005,381:795~805
[17] Geladi P, MacDougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[18] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear~infrared spectra. Chemometrics Intell Lab Syst,1998,44:175~185
[19] Westerhuis J A, de Jong S, Smilde A K. Direct orthogonal signalcorrection. Chemometrics Intell Lab Syst,2001,56:13~25
[20] Norgaard L, Saudland A, Wagner J, et al. Interval partialleast-squares regression (iPLS): A comparative chemometric studywith an example from near-infrared spectroscopy. Appl Spectrosc,2000,54:413~419
[21] Leardi R, Norgaard L. Sequential application of backward intervalpartial least squares and genetic algorithms for the selection ofrelevant spectral regions. J Chemometr,2004,18:486~497
[22] Lindgren F, Geladi P, Rannar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[23] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. J ofChemometr,1995,9:331~342
[24] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[25] Shao X G, Wang F, Chen D, et al. A method for near-infraredspectral calibration of complex plant samples with wavelettransform and elimination of uninformative variables. Anal BioanalChem,2004,378:1382~1387
[26] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[27] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[28] Araujo M C U, Saldanha T C B, Galvao R K H, et al. Thesuccessive projections algorithm for variable selection inspectroscopic multicomponent analysis. Chemometrics Intell LabSyst,2001,57:65~73
[29] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[30] Liang Y Z, Kvalheim O M. Robust methods for multivariateanalysis: A tutorial review. Chemometrics Intell Lab Syst,1996,32:1~10
[31] De Maesschalck R, Jouan-Rimbaud D, Massart D L. TheMahalanobis distance. Chemometrics Intell Lab Syst,2000,50:1~18
[32] Rousseeuw P J, van Zomeren B C. Unmasking Multivariate Outliersand Leverage Points. J Am Stat Assoc,1990,85:871~880
[33] Fung W K. Unmasking outliers and leverage points: A confirmation.J Am Stat Assoc,1993:515~519
[34] Pierna J A F, Wahl F, de Noord O E, et al. Methods for outlierdetection in prediction. Chemometrics Intell Lab Syst,2002,63:27~39
[35] Walczak B, Massart D L. Multiple outlier detection revisited.Chemometrics Intell Lab Syst,1998,41:1~15
[36] Hadi A S. Identifying multiple outliers in multivariate data. J R StatSoc B,1992,54:761~771
[37] De Vries S, Ter Braak C J F. Prediction error in partial least squaresregression: a critique on the deviation used in the Unscrambler.Chemometrics Intell Lab Syst,1995,30:239~245
[38] Hoy M, Steen K, Martens H. Review of partial least squaresregression prediction error in Unscrambler. Chemometrics Intell LabSyst,1998,44:123~133
[39] Pierna J A F, Jin L, Daszykowski M, et al. A methodology to detectoutliers/inliers in prediction with PLS. Chemometrics Intell LabSyst,2003,68:17~28
[40] Liu Z C, Cai W S, Shao X G. Outlier detection in near-infraredspectroscopic analysis by using Monte Carlo cross-validation. SciChina Ser B-Chem,2008,51:751~759
[41] Bian X H, Cai W S, Shao X G, et al. Detecting influentialobservations by cluster analysis and Monte Carlo cross-validation.Analyst,2010,135:2841~2847
[42] Liebmann B, Filzmoser P, Varmuza K. Robust and classical PLSregression compared. J Chemometr,2010,24:111~120
[43] Vanden Branden K, Hubert M. Robustness properties of a robustpartial least squares regression method. Anal Chim Acta,2004,515:229~241
[44] Serneels S, Croux C, Filzmoser P, et al. Partial robust M~regression.Chemometrics Intell Lab Syst,2005,79:55~64
[45] Serneels S, Filzmoser P, Croux C, et al. Robust continuumregression. Chemometrics Intell Lab Syst,2005,76:197~204
[46] Shao X G, Bian X H, Cai W S. An improved boosting partial leastsquares method for near~infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[47] Liu Z C, Ma X, Wen Y D, et al. A practical approach for nearinfrared spectral quantitative analysis of complex samples usingpartial least squares modeling. Sci China Ser B-Chem,2009,52:1021~1027
[48] Breunig M M, Kriegel H P, Ng R T, et al. LOF: Identifyingdensity-based local outliers. Sigmod Rec,2000,29:93~104
[49] Kalivas J H. Two data sets of near infrared spectra. ChemometricsIntell Lab Syst,1997,37:255~259
[50] Li W, Goovaerts P, Meurens M. Quantitative analysis of individualsugars and acids in orange juices by near~infrared spectroscopy ofdry extract. J arg food chem,1996,44:2252~2259
[1] Rickert W S, Joza P J, Sharifi M, et al. Reductions in the tobaccospecific nitrosamine (TSNA) content of tobaccos taken fromcommercial Canadian cigarettes and corresponding reductions inTSNA deliveries in mainstream smoke from such cigarettes. RegulToxicol Pharm,2008,51:306~310
[2] Zhou J, Bai R S, Zhu Y F. Determination of four tobacco-specificnitrosamines in mainstream cigarette smoke by gaschromatography/ion trap mass spectrometry. Rapid Commun MassSp,2007,21:4086~4092
[3] Wu W J, Ashley D L, Watson C H. Simultaneous determination offive tobacco-specific nitrosamines in mainstream cigarette smoke byisotope dilution liquid chromatography/electrospray ionizationtandem mass spectrometry. Anal Chem,2003,75:4827~4832
[4] Wagner K A, Finkel N H, Fossett J E, et al. Development of aquantitative method for the analysis of tobacco-specificnitrosamines in mainstream cigarette smoke using isotope dilutionliquid chromatography/electrospray ionization tandem massspectrometry. Anal Chem,2005,77:1001~1006
[5] Wu J C, Joza P, Sharifi M, et al. Quantitative method for the analysisof tobacco-specific nitrosamines in cigarette tobacco andmainstream cigarette smoke by use of isotope dilution liquidchromatography tandem mass spectrometry. Anal Chem,2008,80:1341~1345
[6] Wu W J, Song S Q, Ashley D L, et al. Assessment of tobacco-specificnitrosamines in the tobacco and mainstream smoke of Bidicigarettes. Carcinogenesis,2004,25:283~287
[7] Clayton P M, Cunningham A, van Heemst J D H. Quantification offour tobacco-specific nitrosamines in cigarette filter tips using liquidchromatography-tandem mass spectrometry. Anal Methods,2010,2:1085~1094
[8] Kavvadias D, Scherer G, Urban M, et al. Simultaneous determinationof four tobacco-specific N-nitrosamines (TSNA) in human urine. JChromatogr B,2009,877:1185~1192
[9] Stepanov I, Hecht S S, Mirvish S S, et al. Comparative analysis oftobacco-specific nitrosamines and total N-nitroso compounds inMoldovan cigarette tobacco. J Agr Food Chem,2005,53:8082~8086
[10] Sleiman M, Maddalena R L, Gundel L A, et al. Rapid and sensitivegas chromatography-ion-trap tandem mass spectrometry method forthe determination of tobacco-specific N-nitrosamines in secondhandsmoke. J Chromatogr A,2009,1216:7899~7905
[11] Moros J, Garrigues S, de la Guardia M. Vibrational spectroscopyprovides a green tool for multi-component analysis. Trac-TrendsAnal Chem,2010,29:578~591
[12] Du C G, Zhou J M. Evaluation of soil fertility using infraredspectroscopy: a review. Environ Chem Lett,2009,7:97~113
[13] Cozzolino D. Near Infrared Spectroscopy in Natural ProductsAnalysis. Planta Med,2009,75:746~756
[14] Feng Y C, Zhang X B, Hu C Q. Construction of identificationsystem for non-invasive analysis of macrolides tablets using nearinfrared diffuse reflectance spectroscopy. J Pharm Biomed Anal,2010,51:12~17
[15] Jing M, Cai W S, Shao X G. Quantitative Determination of theComponents in Corn and Tobacco Samples by Using Near-InfraredSpectroscopy and Multiblock Partial Least Squares. Anal Lett,2010,43:1910~1921
[16] Liu J J, Xu H, Cai W S, et al. Discrimination of industrial productsby on-line near infrared spectroscopy with an improved dendrogram.Chin Chem Lett,2011,22:1241~1244
[17] Huang H B, Yu H Y, Xu H R, et al. Near infrared spectroscopy foron/in-line monitoring of quality in foods and beverages: A review. JFood Eng,2008,87:303~313
[18] Nordon A, Littlejohn D, Dann A S, et al. In situ monitoring of theseed stage of a fermentation process using non-invasive NIRspectrometry. Analyst,2008,133:660~666
[19] Roychoudhury P, O'Kennedy R, McNeil B, et al. Multiplexing fibreoptic near infrared (NIR) spectroscopy as an emerging technology tomonitor industrial bioprocesses. Anal Chim Acta,2007,590:110~117
[20] Liu J J, Ma X, Wen Y D, et al. Online near-Infrared SpectroscopyCombined with Alternating Trilinear Decomposition for ProcessAnalysis of Industrial Production and Quality Assurance. Ind EngChem Res,2011,50:7677~7681
[21] Rinnan A, van den Berg F, Engelsen S B. Review of the mostcommon pre-processing techniques for near-infrared spectra.Trac-Trends Anal Chem,2009,28:1201~1222
[22] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[23] Cummins D J, Andrews C W. Iteratively reweighted partial leastsquares: A performance analysis by monte carlo simulation. JChemometr,1995,9:489~507
[24] Egan W J, Mogan S L. Outlier detection in multivariate analyticalchemical data. Anal Chem,1998,70:2372~2379
[25] Serneels S, Croux C, Filzmoser P, et al. Partial robust M-regression.Chemometrics Intell Lab Syst,2005,79:55~64
[26] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[27] Xu H, Liu Z C, Cai W S, et al. A wavelength selection method basedon randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[28] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[29] Huang Z X, Tao W, Fang J J, et al. Multivariate calibration ofon-line enrichment near-infrared (NIR) spectra and determination oftrace lead in water. Chemometrics Intell Lab Syst,2009,98:195~200
[30] Sheng N, Cai W S, Shao X G. An approach by using near-infrareddiffuse reflectance spectroscopy and resin adsorption for thedetermination of copper, cobalt and nickel ions in dilute solution.Talanta,2009,79:339~343
[31] Li J H, Zhang Y, Cai W S, et al. Simultaneous determination ofmercury, lead and cadmium ions in water using near-infraredspectroscopy with preconcentration by thiol-functionalizedmagnesium phyllosilicate clay. Talanta,2011,84:679~683
[32] Moros J, Llorca I, Cervera M L, et al. Chemometric determinationof arsenic and lead in untreated powdered red paprika by diffusereflectance near-infrared spectroscopy. Anal Chim Acta,2008,613:196~206
[33] Chang C W, Laird D A, Mausbach M J, et al. Near-infraredreflectance spectroscopy principal components regression analysesof soil properties. Soil Sci Soc Am J,2001,65:480~490
[34] Font R, Del Rio-Celestino M, Velez D, et al. Visible andnear-infrared spectroscopy as a technique for screening the inorganicarsenic content in the red crayfish (Procambarus clarkii Girard).Anal Chem,2004,76:3893~3898
[35] Font R, Velez D, Del Rio-Celestino M, et al. Screening inorganicarsenic in rice by visible and near-infrared spectroscopy. MicrochimActa,2005,151:231~239
[36] Cozzolino D, Kwiatkowski M J, Dambergs R G, et al. Analysis ofelements in wine using near infrared spectroscopy and partial leastsquares regression. Talanta,2008,74:711~716
[37] Kennard R W, Stone L A. Computer aided design of experiments.Technometrics,1969,11:137~148
[38] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[39] Shao X G, Ma C X. A general approach to derivative calculationusing wavelet transform. Chemometrics Intell Lab Syst,2003,69:157~165
[40] Ma C X, Shao X G. Continuous wavelet transform applied toremoving the fluctuating background in near-infrared spectra. JChem Inf Comp Sci,2004,44:907~911
[41] Chen D, Shao X G, Hu B, et al. A Background and noise eliminationmethod for quantitative calibration of near infrared spectra. AnalChim Acta,2004,511:37~45
[1]严衍禄,赵龙莲,韩东海等.近红外光谱分析基础与应用.北京:中国轻工业出版社,2005,286~563
[2]陆婉珍,袁洪福,徐广通等.现代近红外光谱分析技术.北京:中国石化出版社,2007,193~247
[3]刘建学.实用近红外光谱分析技术.北京:科学出版社,2008,158~239
[4] Massart D L. Chemometrics: a textbook. Amsterdam: ElsevierScience,1988,5~9
[5] Chau F. Chemometrics: from basics to wavelet transform. Hoboken:Wiley-Interscience,2004,5~12
[6] Brown S D, Tauler R, Walczak B. Comprehensive chemometrics:chemical and biochemical data analysis. Amsterdam: Elsevier,2009,459~463
[7] Martens H, Naes T. Multivariate calibration. Hoboken: John Wiley&Sons Inc,1992,1~30
[8] N s T, Isaksson T, Fearn T, et al. A user friendly guide to multivariatecalibration and classification. Chichester UK: NIR Publications,2002,11~17
[9] Brereton R G. Introduction to multivariate calibration in analyticalchemistry. Analyst,2000,125:2125~2154
[10] Williams P, Norris K. Near-infrared technology in the agriculturaland food industries. Minnesota: American Association of CerealChemists,1987
[11] Weisberg S. Applied linear regression, Third edition. Hoboken:Wiley Online Library,2005,211~230
[12] Hawkins D M. On the investigation of alternative regressions byprincipal component analysis. Appl Statist,1973,22:275~286
[13] N s T, Martens H. Principal component regression in NIR analysis:viewpoints, background details and selection of components. JChemometr,1988,2:155~167
[14] Sutter J M, Kalivas J H, Lang P M. Which principal components toutilize for principal component regression. J Chemometr,1992,6:217~225
[15] Depczynski U, Frost V J, Molt K. Genetic algorithms applied to theselection of factors in principal component regression. Anal ChimActa,2000,420:217~227
[16] Chang C W, Laird D A, Mausbach M J, Hurburgh Jr C R.Near-infrared reflectance spectroscopy-principal componentsregression analyses of soil properties. Soil Sci Soc Am J,2001.65:480~490
[17] Otsuka M. Comparative particle size determination of phenacetinbulk powder by using Kubelka-Munk theory and principalcomponent regression analysis based on near-infrared spectroscopy.Powder Technol,2004,141:244~250
[18]邵学广,蔡文生.化学信息学.北京:科学出版社,2005,206~207
[19] Vinzi V E, Chin W W, Henseler J. Handbook of partial least squares:Concepts, methods and applications. Berlin: Springer Verlag,2009,32~38
[20] Wold H. Partial least squares. Int J Cardiol,1985,147:581~591
[21] Geladi P, Kowalski B R. Partial least-squares regression: a tutorial.Anal Chim Acta,1986,185:1~17
[22] Wold S, Sjostrom M, Eriksson L. PLS-regression: a basic tool ofchemometrics. Chemometrics Intell Lab Syst,2001,58:109~130
[23] de Jong S. SIMPLS: an alternative approach to partial least squaresregression. Chemometrics Intell Lab Syst,1993,18:251~263
[24] Kvalheim O M, Karstang T V. Interpretation of latent variableregression models. Chemometrics Intell Lab Syst.1989,7:39~51
[25]Trygg J, Wold S. Orthogonal projections to latent structures (O-PLS).J Chemometr,2002,16:119~128
[26] Cloarec O, Dumas M E, Trygg J, et al. Evaluation of the orthogonalprojection on latent structure model limitations caused by chemicalshift variability and improved visualization of biomarker changes in1H NMR spectroscopic metabonomic studies. Anal Chem,2005,77:517~526
[27] Walczak B, Massart D L. The Radial Basis Functions--Partial LeastSquares approach as a flexible non-linear regression technique. AnalChim Acta,1996,331:177~185
[28] Rosipal R. Kernel partial least squares for nonlinear regression anddiscrimination. Neural Netw World,2003,13:291~300
[29] Chen D, Hu X G, Shao X G, et al. Variable selection by modifiedIPW (iterative predictor weighting)-PLS (partial least squares) incontinuous wavelet regression models. Analyst,2004,129:664~669
[30] Xu H, Cai W S, Shao X G. Weighted partial least squares regressionby variable grouping strategy for multivariate calibration of nearinfrared spectra. Anal Methods,2010,2:289~294
[31] Comon P. Independent component analysis, a new concept? SignalProcess,1994,36:287~314
[32] Hyvarinen A, Oja E. Independent component analysis: algorithmsand applications. Neural Netw,2000,13:411~430
[33] Wang G Q, Ding Q Z, Hou Z Y. Independent component analysisand its applications in signal processing for analytical chemistry.Trac-Trends Anal Chem,2008,27:368~376
[34] Shao X G, Liu Z C, Cai W S. Resolving multi-componentoverlapping GC-MS signals by immune algorithms. Trac-TrendsAnal Chem,2009,28:1312~1321
[35] Gustafsson M G. Independent component analysis yields chemicallyinterpretable latent variables in multivariate regression. J Chem InfModel,2005,45:1244~1255
[36] Shao X G, Wang W, Hou Z Y, et al. A new regression method basedon independent component analysis. Talanta,2006,69:676~680
[37] Zhang Y W, Zhang Y. Complex process monitoring using modifiedpartial least squares method of independent component regression.Chemometrics Intell Lab Syst,2009,98:143~148
[38] Al-Mbaideen A, Benaissa M. Coupling subband decomposition andindependent component regression for quantitative NIRspectroscopy. Chemometrics Intell Lab Syst,2011,108:112~122
[39] Parastar H, Jalali-Heravi M, Tauler R. Is Independent ComponentAnalysis appropriate for multivariate resolution in analyticalchemistry? Trac-Trends Anal Chem,2011.31:134~143
[40] Bouveresse D, Moya-González A, Ammari F, et al. Two novelmethods for the determination of the number of components inindependent components analysis models. Chemometrics Intell LabSyst,2012,112:24~32
[41] Candolfi A, De Maesschalck R, Jouan-Rimbaud D, et al. Theinfluence of data pre-processing in the pattern recognition ofexcipients near-infrared spectra. J Pharm Biomed Anal,1999,21:115~132
[42] Azzouz T, Puigdoménech A, Aragay M, et al. Comparison betweendifferent data pre-treatment methods in the analysis of foragesamples using near-infrared diffuse reflectance spectroscopy andpartial least-squares multivariate calibration method. Anal ChimActa,2003,484:121~134
[43] Rinnan A, van den Berg F, Engelsen S B. Review of the mostcommon pre-processing techniques for near-infrared spectra.Trac-Trends Anal Chem,2009,28:1201~1222
[44] Geladi P, Macdougall D, Martens H. Linearization andscatter-correction for near-infrared reflectance spectra of meat. ApplSpectrosc,1985,39:491~500
[45] Martens H, Stark E. Extended multiplicative signal correction andspectral interference subtraction: new preprocessing methods fornear infrared spectroscopy. J Pharm Biomed Anal,1991,9:625~635
[46] Martens H, Nielsen J P, Engelsen S B. Light scattering and lightabsorbance separated by extended multiplicative signal correction.Application to near-infrared transmission analysis of powdermixtures. Anal Chem,2003,75:394~404
[47] Barnes R, Dhanoa M, Lister S J. Standard normal variatetransformation and de-trending of near-infrared diffuse reflectancespectra. Appl Spectrosc,1989,43:772~777
[48] Dhanoa M S, Lister S J, Sanderson R, et al. The link betweenmultiplicative scatter correction (MSC) and standard normal variate(SNV) transformations of NIR spectra. J Near Infrared Spectrosc,1994,2:43~47
[49] Fearn T, Riccioli C, Garrido-Varo A, et al. On the geometry of SNVand MSC. Chemometrics Intell Lab Syst,2009,96:22~26
[50] Savitzky A, Golay M J E. Smoothing and differentiation of data bysimplified least squares procedures. Anal Chem,1964,36:1627~1639
[51] Steinier J, Termonia Y, Deltour J. Smoothing and differentiation ofdata by simplified least square procedure. Anal Chem,1972,44:1906~1909
[52] Shao X G, Pang C Y, Su Q D. A novel method to calculate theapproximate derivative photoacoustic spectrum using continuouswavelet transform. Fresen J Anal Chem,2000,367:525~529
[53] Shao X G, Cai W S. Wavelet analysis in analytical chemistry. RevAnal Chem,1998,17:235~285
[54] Shao X G, Leung A K M, Chau F T. Wavelet: A new trend inchemistry. Accounts Chem Res,2003,36:276~283
[55] Shao X G, Gu H, Cai W S, et al. Studies on data compression of1-DNMR spectra using wavelet transform. Spectrosc Spectr Anal,1999,19:139~141
[56] Wang L S, Yang X Y, Xi S F, et al. Wavelet Smoothing andDenoising to Process Capillary Electrophoresis Signals. Chem JChin Univ,1999,3:383~386
[57] Shao X G, Cai W S, Pan Z X. Wavelet transform and its applicationsin high performance liquid chromatography (HPLC) analysis.Chemometrics Intell Lab Syst,1999,45:249~256
[58] Shao X G, Shao L M, Zhao G W. Extraction of extended X-rayabsorption fine structure information from the experimental datausing the wavelet transform. Anal Commun1998,35:135~137
[59] Wolkenstein M, Hutter H, Nikolov S G, Grasserbauer M.Improvement of SIMS image classification by means of waveletde-noising. Fresenius J Anal Chem,1997,357:783~788
[60] Wold S, Antti H, Lindgren F, et al. Orthogonal signal correction ofnear-infrared spectra. Chemometrics Intell Lab Syst,1998,44:175~185
[61] Chen D, Wang F, Shao X G, et al. Elimination of interferenceinformation by a new hybrid algorithm for quantitative calibrationof near infrared spectra. Analyst,2003,128:1200~1203
[62] Woody N A, Feudale R N, Myles A J, et al. Transfer of multivariatecalibrations between four near-infrared spectrometers usingorthogonal signal correction. Anal Chem,2004,76:2595~2600
[63] Ni W, Brown S D, Man R. Wavelet Orthogonal SignalCorrection-Based Discriminant Analysis. Anal Chem,2009,81:8962~8967
[64] Westerhuis J A, de Jong S, Smilde A K. Direct orthogonal signalcorrection. Chemometrics Intell Lab Syst,2001,56:13~25
[65] Faber N M, Rajko R. How to avoid over-fitting in multivariatecalibration-The conventional validation approach and an alternative.Anal Chim Acta,2007,595:98~106
[66] Wold S. Cross-validatory estimation of the number of componentsin factor and principal components models. Technometrics,1978:397~405
[67] Burman P. A comparative study of ordinary cross-validation, v-foldcross-validation and the repeated learning-testing methods.Biometrika,1989,76:503~514
[68] Xu Q S, Liang Y Z. Monte Carlo cross validation. ChemometricsIntell Lab Syst,2001,56:1~11
[69] Xu Q S, Liang Y Z, Du Y P. Monte Carlo cross-validation forselecting a model and estimating the prediction error in multivariatecalibration. J Chemometr,2004,18:112~120
[70] Osten D W. Selection of optimal regression models viacross-validation. J Chemometr,1988,2:39~48
[71] Rutledge D N, Barros A, Delgadillo I. PoLiSh--smoothed partialleast-squares regression. Anal Chim Acta,2001,446:279~294
[72] Gourvenec S, Pierna J A F, Massart D L, et al. An evaluation of thePoLiSh smoothed regression and the Monte Carlo Cross-Validationfor the determination of the complexity of a PLS model.Chemometrics Intell Lab Syst,2003,68:41~51
[73] Durbin J, Watson G S. Testing for serial correlation in least squaresregression: I. Biometrika,1950,37:409~428
[74] van der Voet H. Comparing the predictive accuracy of models usinga simple randomization test. Chemometrics Intell Lab Syst,1994,25:313~323
[75] Wiklund S, Nilsson D, Eriksson L, et al. A randomization test forPLS component selection. J Chemometr,2007,21:427~439
[76] Liu Z C, Ma X, Wen Y D, et al. A practical approach for nearinfrared spectral quantitative analysis of complex samples usingpartial least squares modeling. Sci China Ser B-Chem,2009,52:1021~1027
[77] Rousseeuw P J, Leroy A M, Wiley J. Robust regression and outlierdetection. Hoboken: Wiley Online Library,1987,1~18
[78] Liang Y Z, Kvalheim O M. Robust methods for multivariateanalysis-a tutorial review. Chemometrics Intell Lab Syst,1996,32:1~10
[79] Pierna J A F, Wahl F, de Noord O E, et al. Methods for outlierdetection in prediction. Chemometrics Intell Lab Syst,2002,63:27~39
[80] Belsley D A, Kuh E, Welsch R E. Regression diagnostics. Hoboken:Wiley Online Library;1980.6~84
[81] De Maesschalck R, Jouan-Rimbaud D, Massart D L. Themahalanobis distance. Chemometrics Intell Lab Syst,2000,50:1~18
[82] Hotelling H. Analysis of a complex of statistical variables intoprincipal components. J Educ Psychology,1933,24:417~441
[83] Rousseeuw P J, Van Zomeren B C. Unmasking multivariate outliersand leverage points. J Am Stat Assoc,1990,85:633~639
[84] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[85] Liu Z C, Cai W S, Shao X G. Outlier detection in near-infraredspectroscopic analysis by using Monte Carlo cross-validation. SciChina Ser B-Chem,2008,51:751~759
[86] Bian X H, Cai W S, Shao X G, et al. Detecting influentialobservations by cluster analysis and Monte Carlo cross-validation.Analyst,2010,135:2841~2847
[87] Cao D S, Liang Y Z, Xu Q S, et al. A new strategy of outlierdetection for QSAR/QSPR. J Comput Chem,2010,31:592~602
[88] Daszykowski M, Kaczmarek K, Vander Heyden Y V, et al. Robuststatistics in data analysis-A review: Basic concepts. ChemometricsIntell Lab Syst,2007,85:203~219
[89] Serneels S, Croux C, Filzmoser P, et al. Partial robust M-regression.Chemometrics Intell Lab Syst,2005,79:55~64
[90] Hubert M, Branden K V. Robust methods for partial least squaresregression. J Chemometr,2003,17:537~549
[91] Hubert M, Rousseeuw P J, Verboven S. A fast method for robustprincipal components with applications to chemometrics.Chemometrics Intell Lab Syst,2002,60:101~111
[92] Guyon I, Elisseeff A. An introduction to variable and featureselection. Journal of Machine Learning Research2003,3:1152~1182
[93] Andersen C M, Bro R. Variable selection in regression-a tutorial. JChemometr,2010,24:728~737
[94] Xiaobo Z, Jiewen Z, Povey M J W, et al. Variables selectionmethods in near-infrared spectroscopy. Anal Chim Acta,2010,667:14~32
[95] Lindgren F, Geladi P, R nnar S, et al. Interactive variable selection(IVS) for PLS. Part1: Theory and algorithms. J Chemometr,1994,8:349~363
[96] Lindgren F, Geladi P, Berglund A, et al. Interactive variableselection (IVS) for PLS. Part II: Chemical applications. JChemometr,1995,9:331~342
[97] Norgaard L, Saudland A, Wagner J, et al. Interval partialleast-squares regression (iPLS): A comparative chemometric studywith an example from near-infrared spectroscopy. Appl Spectrosc,2000,54:413~419
[98] Zou X B, Zhao J W, Huang X Y, et al. Use of FT-NIR spectrometryin non-invasive measurements of soluble solid contents (SSC) of'Fuji' apple based on different PLS models. Chemometrics Intell LabSyst,2007,87:43~51
[99] Jiang J H, Berry R J, Siesler H W, et al. Wavelength intervalselection in multicomponent spectral analysis by moving windowpartial least-squares regression with applications to mid-infrared andhear-infrared spectroscopic data. Anal Chem,2002,74:3555~3565
[100] Kasemsumran S, Du Y P, Murayama K, et al. Near-infraredspectroscopic determination of human serum albumin,gamma-globulin, and glucose in a control serum solution withsearching combination moving window partial least squares. AnalChim Acta,2004,512:223~230
[101] Bro R, De Jong S. A fast non-negativity-constrained least squaresalgorithm. J chemometr,1997,11:393~401
[102] Du Y P, Liang Y Z, Jiang J H, et al. Spectral regions selection toimprove prediction ability of PLS models by changeable sizemoving window partial least squares and searching combinationmoving window partial least squares. Anal Chim Acta,2004,501:183~191
[103] Gareth J, Peter W, Robert C G, et al. Development and validation ofa genetic algorithm for flexible docking. J Mol Bio1999,267:727~748
[104] Haupt Randy L, Haupt S E. Practical genetic algorithms. Hoboken:Wiley,2004,27~47
[105] Leardi R, Gonzalez A L. Genetic algorithms applied to featureselection in PLS regression: how and when to use them.Chemometrics Intell Lab Syst,1998,41:195~207
[106] Koljonen J, Nordling T E M, Alander J T. A review of geneticalgorithms in near infrared spectroscopy and chemometrics: past andfuture. J Near Infrared Spectrosc,2008,16:189~197
[107] Galvao R K H, Pimentel M F, Araujo M C U, et al. Aspects of thesuccessive projections algorithm for variable selection inmultivariate calibration applied to plasma emission spectrometry.Anal Chim Acta,2001,443:107~115
[108] Araujo M C U, Saldanha T C B, Galvao R K H, et al. Thesuccessive projections algorithm for variable selection inspectroscopic multicomponent analysis. Chemometrics Intell LabSyst,2001,57:65~73
[109] Centner V, Massart D L, de Noord O E, et al. Elimination ofuninformative variables for multivariate calibration. Anal Chem,1996,68:3851~3858
[110] Shao X G, Wang F, Chen D, et al. A method for near-infraredspectral calibration of complex plant samples with wavelettransform and elimination of uninformative variables. Anal BioanalChem,2004,378:1382~1387
[111] Chen D, Shao X G, Hu B, et al. A Background and noiseelimination method for quantitative calibration of near infraredspectra. Anal Chim Acta,2004,511:37~45
[112] Cai W S, Li Y K, Shao X G. A variable selection method based onuninformative variable elimination for multivariate calibration ofnear-infrared spectra. Chemometrics Intell Lab Syst,2008,90:188~194
[113] Han Q J, Wu H L, Cai C B, et al. An ensemble of Monte Carlouninformative variable elimination for wavelength selection. AnalChim Acta,2008,612:121~125
[114] Moros J, Kuligowski J, Quintas G, et al. New cut-off criterion foruninformative variable elimination in multivariate calibration ofnear-infrared spectra for the determination of heroin in illicit streetdrugs. Anal Chim Acta,2008,630:150~160
[115] Ye S, Wang D, Min S. Successive projections algorithm combinedwith uninformative variable elimination for spectral variableselection. Chemometrics Intell Lab Syst,2008,91:194~199
[116] Wu D, Chen X, Zhu X, et al. Uninformative variable eliminationfor improvement of successive projections algorithm on spectralmultivariable selection with different calibration algorithms for therapid and non-destructive determination of protein content in driedlaver. Anal Methods,2011,3:1790~1796
[117] Xu H, Liu Z C, Cai W S, et al. A wavelength selection methodbased on randomization test for near-infrared spectral analysis.Chemometrics Intell Lab Syst,2009,97:189~193
[118] Li H D, Liang Y Z, Xu Q S, et al. Key wavelengths screening usingcompetitive adaptive reweighted sampling method for multivariatecalibration. Anal Chim Acta,2009,648:77~84
[119] Zheng K Y, Li Q Q, Wang J J, et al. Stability competitive adaptivereweighted sampling (SCARS) and its applications to multivariatecalibration of NIR spectra. Chemometrics Intell Lab Syst,2012,112:48~54
[120] Teofilo R F, Martins J P A, Ferreira M M C. Sorting variables byusing informative vectors as a strategy for feature selection inmultivariate regression. J Chemometr,2009,23:32~48
[121] Gosselin R, Rodrigue D, Duchesne C. A Bootstrap-VIP approachfor selecting wavelength intervals in spectral imaging applications.Chemometrics Intell Lab Syst,2010,100:12~21
[122] Ferre J, Faber N M. Net analyte signal calculation for multivariatecalibration. Chemometrics Intell Lab Syst,2003,69:123~136
[123] Brown P J. Wavelength selection in multicomponent near‐infraredcalibration. J Chemometr,1992,6:151~161
[124] Shao X G, Bian X H, Liu J J, et al. Multivariate calibration methodsin near infrared spectroscopic analysis. Anal Methods,2010,2:1662~1666
[125] Li H D, Liang Y Z, Xu Q S, et al. Model population analysis forvariable selection. J Chemometr,2010,24:418~423
[126] Su Z Q, Tong W D, Shi L M, et al. A partial least squares-basedconsensus regression method for the analysis of near-infraredcomplex spectral data of plant samples. Anal Lett,2006,39,2073~2083
[127] Li Y K, Shao X G, Cai W S. Partial least squares regression methodbased on consensus modeling for quantitative analysis ofnear-infrared spectra. Chem J Chin Univ,2007,28:246~249
[128] Chen D, Cai W S, Shao X G. Removing uncertain variables basedon ensemble partial least squares. Anal Chim Acta,2007,598:19~26
[129] Chen D, Cai W S, Shao X G. A strategy for enhancing thereliability of near-infrared spectral analysis. Vib Spectrosc,2008,47:113~118
[130] Li Y K, Shao X G, Cai W S. A consensus least squares supportvector regression (LS-SVR) for analysis of near-infrared spectra ofplant samples. Talanta,2007,72:217~222
[131] Cao D S, Xu Q S, Liang Y Z, et al. The boosting: A new idea ofbuilding models. Chemometrics Intell Lab Syst,2010,100:1~11
[132] Zhang M H, Xu Q S, Massart D L. Boosting partial least squares.Anal Chem,2005,77:1423~1431
[133] Zhou Y P, Cai C B, Huan S, et al. QSAR study of angiotensin IIantagonists using robust boosting partial least squares regression.Anal Chim Acta,2007,593:68~74
[134] Shao X G, Bian X H, Cai W S. An improved boosting partial leastsquares method for near-infrared spectroscopic quantitative analysis.Anal Chim Acta,2010,666:32~37
[135] Shinzawa H, Jiang J H, Ritthiruangdej P, et al. Investigations ofbagged kernel partial least squares (KPLS) and boosting KPLS withapplications to near-infrared (NIR) spectra. J Chemometr,2006,20:436~444
[136] Zhou Y P, Jiang J H, Wu H L,et al. Dry film method withytterbium as the internal standard for near infrared spectroscopicplasma glucose assay coupled with boosting support vectorregression. J Chemometr,2006,20:13~21
[137] Jing M, Cai W S, Shao X G. Quantitative Determination of theComponents in Corn and Tobacco Samples by Using Near-InfraredSpectroscopy and Multiblock Partial Least Squares. Anal Lett,2010,43:1910~1921
[138] Tan C, W J Y, Wu T, et al. Determination of nicotine in tobaccosamples by near-infrared spectroscopy and boosting partial leastsquares. Vib Spectrosc,2010,54:35~41
[139] Ni W, Brown S D, Man R. Stacked partial least squares regressionanalysis for spectral calibration and prediction. J Chemometr,2009,23:505~517
[140] Melssen W, Ustun B, Buydens L. SOMPLS: A supervisedself-organising map-partial least squares algorithm for multivariateregression problems. Chemometrics Intell Lab Syst,2007,86:102~120
[141] Ballabio D, Consonni V, Todeschini R. The Kohonen and CP-ANNtoolbox: A collection of MATLAB modules for Self OrganizingMaps and Counterpropagation Artificial Neural Networks.Chemometrics Intell Lab Syst,2009,98:115~122
[142] Tan C, Qin X, Li M L. Subspace Regression Ensemble MethodBased on Variable Clustering for Near-Infrared SpectroscopicCalibration. Anal Lett,2009,42:1693~1710
[143] Tan H, Brown S D. Dual-domain regression analysis for spectralcalibration models. J Chemometr,2003,17:111~122
[144] Jing M, Cai W S, Shao X G. Multiblock partial least squaresregression based on wavelet transform for quantitative analysis ofnear infrared spectra. Chemometrics Intell Lab Syst,2010,100:22~27
[145] Liu Z C, Cai W S, Shao X G. A weighted multiscale regression formultivariate calibration of near infrared spectra. Analyst,2009,134:261~266
[146] Chen D, Chen Z W, Grant E R. Adaptive multiscale regression forreliable Raman quantitative analysis. Analyst,2012,137:237~244
[147] Siesler H W, Ozaki Y, Kawata S, et al. Near-infrared spectroscopy,principles, instruments, applications. Wiley, New York,2002,11~35
[148] Roggo Y, Chalus P, Maurer L, et al. A review of near infraredspectroscopy and chemometrics in pharmaceutical technologies. JPharm Biomed Anal,2007,44:683~700
[149] Geladi P. Chemometrics in spectroscopy. Part1. Classicalchemometrics. Spectroc Acta Pt B-Atom Spectr,2003,58:767~782
[150] Chu X L, Yuan H F, Lu W Z. Progress and application of spectraldata pretreatment and wavelength selection methods in NIRanalytical technique. Prog Chem,2004,16:528~542
[151] Guo Q, Wu W, Massart D L. The robust normal variate transformfor pattern recognition with near-infrared data. Anal Chim Acta,1999,382:87~103
[152] Fearn T. On orthogonal signal correction. Chemometrics Intell LabSyst,2000,50:47~52
[153] Shao X G, Ma C X. A general approach to derivative calculationusing wavelet transform. Chemometrics Intell Lab Syst,2003,69:157~165
[154] Leardi R. Application of genetic algorithm-PLS for featureselection in spectral data sets. J Chemometr,2000,14:643~655
[155] Galvao R K H, Araujo M C U, Fragoso W D, et al. A variableelimination method to improve the parsimony of MLR models usingthe successive projections algorithm. Chemometrics Intell Lab Syst,2008,92:83~91
[156] Lorber A. Error propagation and figures of merit for quantificationby solving matrix equations. Anal Chem,1986,58:1167~1172
[157] Rajalahti T, Arneberg R, Berven F S, et al. Biomarker discovery inmass spectral profiles by means of selectivity ratio plot.Chemometrics Intell Lab Syst,2009,95:35~48
[158] Roger J M, Palagos B, Bertrand D, et al. CovSel: Variable selectionfor highly multivariate and multi-response calibration Application toIR spectroscopy. Chemometrics Intell Lab Syst,2011,106:216~223
[159] Kuenstner J T, Norris K H, McCarthy W F. Measurement ofhemoglobin in unlysed blood by near-infrared spectroscopy. ApplSpectrosc,1994,48:484~488
[160] Kalivas J H. Two data sets of near infrared spectra. ChemometricsIntell Lab Syst,1997,37:255~259
[161] Kennard R W, Stone L A. Computer aided desigh of experiments.Technometrics,1969,11:137~148
[162] Bosco G L. Symposium2009on near-infrared spectroscopy.Trac-Trends Anal Chem,2010,29:197~208
[163] Bro R. Multivariate calibration-What is in chemometrics for theanalytical chemist? Anal Chim Acta,2003,500:185~194
[164] Cummins D J, Andrews C W. Iteratively reweighted partial leastsquares: A performance analysis by monte carlo simulation. JChemometr,1995,9:489~507
[165] Breiman L. Bagging predictors. Mach Learn,1996,24:123~140
[166] Carney J, Cunningham P. Tuning diversity in bagged ensembles.Int J Neural Syst,2000,10:267~280
[167] Durand A, Devos O, Ruckebusch C, et al. Genetic algorithmoptimisation combined with partial least squares regression andmutual information variable selection procedures in near-infraredquantitative analysis of cotton-viscose textiles. Anal Chim Acta,2007,595:72~79
[168] Arakawa M, Yamashita Y, Funatsu K. Genetic algorithm-basedwavelength selection method for spectral calibration. J Chemometr,2011,25:10~19
[169] Shamsipur M, Zare-Shahabadi V, Hemmateenejad B, et al. Antcolony optimisation: a powerful tool for wavelength selection. JChemometr,2006,20:146~157
[170] Fu G H, Xu Q S, Li H D, et al. Elastic Net Grouping VariableSelection Combined with Partial Least Squares Regression(EN-PLSR) for the Analysis of Strongly Multi-collinearSpectroscopic Data. Appl Spectrosc,2011,65:402~408
[171] Chun H, Keles S. Sparse partial least squares regression forsimultaneous dimension reduction and variable selection. J R STATSOC B,2010,72:3~25
[172] McWilliams B, Montana G. Sparse partial least squares regressionfor on-line variable selection with multivariate data streams. StatAnal Data Mining,2010,3:170~193
[173] Lee D, Lee W, Lee Y, et al. Sparse partial least-squares regressionand its applications to high-throughput data analysis. ChemometricsIntell Lab Syst,2011,109:1~8
[174] Massart D L, Vandeginste B G M, Buydens L M C, et al. Handbookof chemometrics and Qualimetrics: Part A, Elsevier, Amsterdam,1997
[175] Wold S, Ruhe A, Wold H, et al. The collinearity problem in linearregression. The partial least squares (PLS) approach to generalizedinverses. SIAM J Sci Stat Comput,1984,5:735~743
[176] Barman I, Kong C R, Dingari N C, et al. Development of RobustCalibration Models Using Support Vector Machines forSpectroscopic Monitoring of Blood Glucose. Anal Chem,2010,82:9719~9726
[177] Belousov A I, Verzakov S A, von Frese J. Applicational aspects ofsupport vector machines. J of Chemometr,2002,16:482~489
[178] Jin L, Pierna J A F, Xu Q, et al. Delaunay triangulation method formultivariate calibration. Anal Chim Acta,2003,488:1~14
[179] Perez Marin D C, Garrido Varo A, Guerrero J E. Non-linearregression methods in NIRS quantitative analysis. Talanta,2007,72:28~42
[180] Cao D S, Wang B, Zeng M M, et al. A new strategy of exploringmetabolomics data using Monte Carlo tree. Analyst,2011,136:947~954
[181] Ma C X, Shao X G. Continuous wavelet transform applied toremoving the fluctuating background in near-infrared spectra. JChem Inf Comp Sci,2004,44:907~911
[182] Chen D, Hu B, Shao X G, et al. A new hybrid strategy forconstructing a robust calibration model for near-infrared spectralanalysis. Anal Bioanal Chem,2005,381:795~805
[183] Leardi R, Norgaard L. Sequential application of backward intervalpartial least squares and genetic algorithms for the selection ofrelevant spectral regions. J Chemometr,2004,18:486~497
[184] Rousseeuw P J, van Zomeren B C. Unmasking MultivariateOutliers and Leverage Points. J Am Stat Assoc,1990,85:871~880
[185] Fung W K. Unmasking outliers and leverage points: A confirmation.J Am Stat Assoc,1993:515~519
[186] Walczak B, Massart D L. Multiple outlier detection revisited.Chemometrics Intell Lab Syst,1998,41:1~15
[187] Hadi A S. Identifying multiple outliers in multivariate data. J R StatSoc B,1992,54:761~771
[188] De Vries S, Ter Braak C J F. Prediction error in partial least squaresregression: a critique on the deviation used in the Unscrambler.Chemometrics Intell Lab Syst,1995,30:239~245
[189] Hoy M, Steen K, Martens H. Review of partial least squaresregression prediction error in Unscrambler. Chemometrics Intell LabSyst,1998,44:123~133
[190] Pierna J A F, Jin L, Daszykowski M, et al. A methodology to detectoutliers/inliers in prediction with PLS. Chemometrics Intell LabSyst,2003,68:17~28
[191] Liebmann B, Filzmoser P, Varmuza K. Robust and classical PLSregression compared. J Chemometr,2010,24:111~120
[192] Vanden Branden K, Hubert M. Robustness properties of a robustpartial least squares regression method. Anal Chim Acta,2004,515:229~241
[193] Serneels S, Filzmoser P, Croux C, et al. Robust continuumregression. Chemometrics Intell Lab Syst,2005,76:197~204
[194] Breunig M M, Kriegel H P, Ng R T, et al. LOF: Identifyingdensity-based local outliers. Sigmod Rec,2000,29:93~104
[195] Li W, Goovaerts P, Meurens M. Quantitative analysis of individualsugars and acids in orange juices by near~infrared spectroscopy ofdry extract. J arg food chem,1996,44:2252~2259
[196] Rickert W S, Joza P J, Sharifi M, et al. Reductions in the tobaccospecific nitrosamine (TSNA) content of tobaccos taken fromcommercial Canadian cigarettes and corresponding reductions inTSNA deliveries in mainstream smoke from such cigarettes. RegulToxicol Pharm,2008,51:306~310
[197] Zhou J, Bai R S, Zhu Y F. Determination of four tobacco-specificnitrosamines in mainstream cigarette smoke by gaschromatography/ion trap mass spectrometry. Rapid Commun MassSp,2007,21:4086~4092
[198] Wu W J, Ashley D L, Watson C H. Simultaneous determination offive tobacco-specific nitrosamines in mainstream cigarette smoke byisotope dilution liquid chromatography/electrospray ionizationtandem mass spectrometry. Anal Chem,2003,75:4827~4832
[199] Wagner K A, Finkel N H, Fossett J E, et al. Development of aquantitative method for the analysis of tobacco-specificnitrosamines in mainstream cigarette smoke using isotope dilutionliquid chromatography/electrospray ionization tandem massspectrometry. Anal Chem,2005,77:1001~1006
[200] Wu J C, Joza P, Sharifi M, et al. Quantitative method for theanalysis of tobacco-specific nitrosamines in cigarette tobacco andmainstream cigarette smoke by use of isotope dilution liquidchromatography tandem mass spectrometry. Anal Chem,2008,80:1341~1345
[201] Wu W J, Song S Q, Ashley D L, et al. Assessment oftobacco-specific nitrosamines in the tobacco and mainstream smokeof Bidi cigarettes. Carcinogenesis,2004,25:283~287
[202] Clayton P M, Cunningham A, van Heemst J D H. Quantification offour tobacco-specific nitrosamines in cigarette filter tips using liquidchromatography-tandem mass spectrometry. Anal Methods,2010,2:1085~1094
[203] Kavvadias D, Scherer G, Urban M, et al. Simultaneousdetermination of four tobacco-specific N-nitrosamines (TSNA) inhuman urine. J Chromatogr B,2009,877:1185~1192
[204] Stepanov I, Hecht S S, Mirvish S S, et al. Comparative analysis oftobacco-specific nitrosamines and total N-nitroso compounds inMoldovan cigarette tobacco. J Agr Food Chem,2005,53:8082~8086
[205] Sleiman M, Maddalena R L, Gundel L A, et al. Rapid and sensitivegas chromatography-ion-trap tandem mass spectrometry method forthe determination of tobacco-specific N-nitrosamines in secondhandsmoke. J Chromatogr A,2009,1216:7899~7905
[206] Moros J, Garrigues S, de la Guardia M. Vibrational spectroscopyprovides a green tool for multi-component analysis. Trac-TrendsAnal Chem,2010,29:578~591
[207] Du C G, Zhou J M. Evaluation of soil fertility using infraredspectroscopy: a review. Environ Chem Lett,2009,7:97~113
[208] Cozzolino D. Near Infrared Spectroscopy in Natural ProductsAnalysis. Planta Med,2009,75:746~756
[209] Feng Y C, Zhang X B, Hu C Q. Construction of identificationsystem for non-invasive analysis of macrolides tablets using nearinfrared diffuse reflectance spectroscopy. J Pharm Biomed Anal,2010,51:12~17
[210] Liu J J, Xu H, Cai W S, et al. Discrimination of industrial productsby on-line near infrared spectroscopy with an improved dendrogram.Chin Chem Lett,2011,22:1241~1244
[211] Huang H B, Yu H Y, Xu H R, et al. Near infrared spectroscopy foron/in-line monitoring of quality in foods and beverages: A review. JFood Eng,2008,87:303~313
[212] Nordon A, Littlejohn D, Dann A S, et al. In situ monitoring of theseed stage of a fermentation process using non-invasive NIRspectrometry. Analyst,2008,133:660~666
[213] Roychoudhury P, O'Kennedy R, McNeil B, et al. Multiplexing fibreoptic near infrared (NIR) spectroscopy as an emerging technology tomonitor industrial bioprocesses. Anal Chim Acta,2007,590:110~117
[214] Liu J J, Ma X, Wen Y D, et al. Online near-Infrared SpectroscopyCombined with Alternating Trilinear Decomposition for ProcessAnalysis of Industrial Production and Quality Assurance. Ind EngChem Res,2011,50:7677~7681
[215] Egan W J, Mogan S L. Outlier detection in multivariate analyticalchemical data. Anal Chem,1998,70:2372~2379
[216] Huang Z X, Tao W, Fang J J, et al. Multivariate calibration ofon-line enrichment near-infrared (NIR) spectra and determination oftrace lead in water. Chemometrics Intell Lab Syst,2009,98:195~200
[217] Sheng N, Cai W S, Shao X G. An approach by using near-infrareddiffuse reflectance spectroscopy and resin adsorption for thedetermination of copper, cobalt and nickel ions in dilute solution.Talanta,2009,79:339~343
[218] Li J H, Zhang Y, Cai W S, et al. Simultaneous determination ofmercury, lead and cadmium ions in water using near-infraredspectroscopy with preconcentration by thiol-functionalizedmagnesium phyllosilicate clay. Talanta,2011,84:679~683
[219] Moros J, Llorca I, Cervera M L, et al. Chemometric determinationof arsenic and lead in untreated powdered red paprika by diffusereflectance near-infrared spectroscopy. Anal Chim Acta,2008,613:196~206
[220] Font R, Del Rio-Celestino M, Velez D, et al. Visible andnear-infrared spectroscopy as a technique for screening the inorganicarsenic content in the red crayfish (Procambarus clarkii Girard).Anal Chem,2004,76:3893~3898
[221] Font R, Velez D, Del Rio-Celestino M, et al. Screening inorganicarsenic in rice by visible and near-infrared spectroscopy. MicrochimActa,2005,151:231~239
[222] Cozzolino D, Kwiatkowski M J, Dambergs R G, et al. Analysis ofelements in wine using near infrared spectroscopy and partial leastsquares regression. Talanta,2008,74:711~716