Abstract
Model prediction ability mainly refers to the performance of robustness and accuracy. They are unified in some cases but contradictory in others. For example, for liquid samples, the conditions of spectroscopic acquisition (such as temperature and pressure) can be strictly controlled. A quantitative calibration model can be established accordingly. The model has high prediction accuracy for samples within the bounds under the same conditions. However, if the spectral acquisition conditions change moderately, the prediction accuracy of the model will become significantly worse. A hybrid calibration model can be established on the spectra collected under different conditions to improve the robustness (or adaptability) of the model. Yet, the model accuracy would be decreased in this case. In practice, it is often necessary to seek a balance between robustness and accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Tulsyan A, Schorner G, Khodabandehlou H, et al. A machine-learning approach to calibrate generic raman models for real-time monitoring of cell culture processes. Biotechnol Bioeng. 2019;116(10):2575–86.
Chu XL, Yuan HF, Wang YB, et al. Developing robust near infrared calibration models. Spectroscopy Spectral Anal. 2004;24(6):666–71.
Hetrick E, Shi ZQ, Barnes L, et al. Development of near infrared (NIR) spectroscopy-based process monitoring methodology for pharmaceutical continuous manufacturing using an offline calibration approach. Anal Chem. 2017;89:9175–83.
Bakeev KA. Process analytical technology: spectroscopic tools and implementation strategies for the chemical and pharmaceutical industries. Oxford: Blackwell Publishing; 2005.
Blanco M, Coello J, Iturriaga H, et al. Strategies for constructing the calibration set in the determination of active principles in pharmaceuticals by near infrared diffuse reflectance spectrometry. Analyst. 1997;122:761–5.
Farrell JA, Higgins K, Kalivas JH. Updating a near-infrared multivariate calibration model formed with lab-prepared pharmaceutical tablet types to new tablet types in full production. J Pharm Biomed Anal. 2012;61:114–21.
Mehdizadeh H, Lauri D, Karry KM, et al. Generic raman-based calibration models enabling real-time monitoring of cell culture bioreactors. Biotechnol Prog. 2015;31(4):1004–13.
Santos RM, Kessler JM, Salou P, et al. Monitoring mAb cultivations with in-situ Raman spectroscopy: the influence of spectral selectivity on calibration models and industrial use as reliable PAT tool. Biotechnol Prog. 2018;34(3):659–70.
Zhang S, Xiong H, Zhou L, et al. Development and validation of in-line near-infrared spectroscopy based analytical method for commercial production of a botanical drug product. J Pharm Biomed Anal. 2019;174:674–82.
Shenk JS, Westerhaus MO. Near infrared reflectance analysis with single and multiproduct calibrations. Crop Sci. 1993;33:582–4.
Luo X, Ye ZZ, Xu HR, et al. Robustness improvement of NIR-based determination of soluble solids in apple fruit by local calibration. Postharvest Biol Technol. 2018;139:82–90.
Davies AMC, Fearn T. Quantitative analysis via near infrared databases: comparison analysis using restructured near infrared and constituent data-deux (CARNAC-D). J Near Infrared Spectrosc. 2006;14(6):403–11.
Næs T, Isaksson T, Kowalski BR. Locally weighted regression and scatter correction for near-infrared reflectance data. Anal Chem. 1990;62(7):664–73.
Centner V, Massart DL. Optimization in locally weighted regression. Anal Chem. 1998;70(19):4206–11.
Shenk JS, Westerhaus MO. Investigation of a LOCAL calibration procedure for near infrared instruments. J Near Infrared Spectrosc. 1997;5(4):223–32.
Dambergs RG, Cozzolino D, Cynkar WU, et al. The determination of red grape quality parameters using the LOCAL algorithm. J Near Infrared Spectrosc. 2006;14(2):71–9.
Perez-Marin D, Garrido-Varo A, Guerrero JE. Implementation of LOCAL algorithm with near-infrared spectroscopy for compliance assurance in compound feeding stuffs. Appl Spectrosc. 2005;59(1):69–77.
Fearn T, Davies AMC. Locally-biased regression. J Near Infrared Spectrosc. 2003;11(6):467–78.
Chung H, Cho S, Toyoda Y, et al. Moment combined partial least squares (MC-PLS) as an improved quantitative calibration method: application to the analyses of petroleum and petrochemical products. Analyst. 2006;131(5):684–91.
He KX, Cheng H, Du WL, et al. Online updating of NIR model and its industrial application via adaptive wavelength selection and local regression strategy. Chemom Intell Lab Syst. 2014;134:79–88.
Zhang HG, Lu JG. Local regression algorithm based on net analyte signal and its application in near infrared spectral analysis. Spectroscopy Spectral Anal. 2016;36(2):384–7.
Yan Y, Zhang HG, Lu JG, et al. Spectral-information-divergence based local PLS modeling algorithm in near infrared spectroscopy. Comput Appl Chem. 2017;34(5):18–22.
Tulsyan A, Wang T, Schorner G, et al. Automatic real-time calibration, assessment, and maintenance of generic raman models for online monitoring of cell culture processes. Biotechnol Bioeng. 2019;117(2):406–16.
Chu XL, Yuan HF, Lu WZ. Determining four component contents in residues by partial least squares-ultraviolet-visible spectrophotometry. Chin J Anal Chem. 2000;28(12):1457–61.
Xu Y, Wu JZ, Wang YM, et al. Clustering method of unknown sort samples based on near infrared spectroscopy. Trans Chinese Soc Agricult Eng. 2011;27(8):345–9.
Ogen Y, Zaluda J, Francos N, et al. Cluster-based spectral models for a robust assessment of soil properties. Geoderma. 2019;340:175–84.
Fearn T. Bagging NIR news. 2006;17(8):15.
Boosting FT. NIR news. 2007;18(1):11–2.
Galvao RKH, Araujo MCU, Martins MD, et al. An application of subagging for the improvement of prediction accuracy of multivariate calibration models. Chemom Intell Lab Syst. 2006;81(1):60–7.
Viscarra Rossel RA. Robust modelling of soil diffuse reflectance spectra by bagging-partial least squares regression. J Near Infrared Spectrosc. 2007;15(1):39–47.
Li YK, Shao XG, Cai WS. Partial least squares regression method based on consensus modeling for quantitative analysis of near-infrared spectra. Chem J Chinese Univ. 2007;28(2):246–9.
Yao ZX, Yang JY, Zhang Q, et al. The application of boosting algorithm in chemical data mining. J Guangxi Univ Technol. 2006;17(4):13–8.
Zhang MH, Xu QS, Massart DL. Boosting partial least squares. Anal Chem. 2005;77(5):1423–31.
Drucker H. Improving regressors using boosting techniques. In: Proceedings of the 14th international conference on machine learning, 1997.
Luo RM, Tan SM, Zhou YP, et al. Quantitative analysis of tea using ytterbium-based internal standard near-infrared spectroscopy coupled with boosting least-squares support vector regression. J Chemom. 2013;27(7–8):198–206.
Wu XL, Li YJ, Wu TJ. A boosting-partial least squares method for ultraviolet spectroscopic analysis of water quality. Chin J Anal Chem. 2013;27(7–8):198–206.
Shao XG, Bian XH, Cai WS. An improved boosting partial least squares method for near-infrared spectroscopic quantitative analysis. Anal Chim Acta. 2010;666:32–7.
Chen Z, Wu ZS, Shi XY, et al. A study on model performance for ethanol precipitation process of Lonicera Japonica by NIR based on bagging-PLS and boosting-PLS algorithm. Chin J Anal Chem. 2014;42(11):1679–86.
Tan C, Li M, Qin X. Random subspace regression ensemble for near-infrared spectroscopic calibration of tobacco samples. Anal Sci. 2008;24(5):647–53.
Ni WD, Brown SD, Man RL. Stacked partial least squares regression analysis for spectral calibration and prediction. J Chemom. 2009;23(10):505–17.
Ni WD, Man RL. Stacked multivariate calibration analysis. Chin J Anal Chem. 2010;38(3):367–71.
Ji GL, Huang GZ, Yang ZJ, et al. Using consensus interval partial least square in near infrared spectra analysis. Chemom Intell Lab Syst. 2015;144:56–62.
Li YK, Jing J. A consensus PLS method based on diverse wavelength variables models for analysis of near-infrared spectra. Chemom Intell Lab Syst. 2014;130:45–9.
Liu K, Chen XJ, Li LM, et al. A consensus successive projections algorithm-multiple linear regression method for analyzing near infrared spectra. Anal Chim Acta. 2015;858:16–23.
Bi YM, Xie Q, Peng SL, et al. Dual stacked partial least squares for analysis of near-infrared spectra. Anal Chim Acta. 2013;792:19–27.
Cui JD. A stacked extreme learning machine algorithm based on nir spectroscopy and its application. Shenyang: Northeastern University; 2015.
Shan P, Zhao YH, Wang QY, et al. Stacked ensemble extreme learning machine coupled with partial least squares-based weighting strategy for nonlinear multivariate calibration. Spectrochim Acta Part A Mol Biomol Spectrosc. 2019;215:97–111.
Chen H, Tan C, Lin Z. Ensemble of extreme learning machines for multivariate calibration of near-infrared spectroscopy. Spectrochimica Acta Part A: Molecul Biomolecul Spectr. 2020; 229: 117982.
Mevik BH, Segtnan VH, Næs T. Ensemble methods and partial least squares regression. J Chemom. 2004;18(11):498–507.
Saiz-Abajo MJ, Mevik BH, Segtnan VH, et al. Ensemble methods and data augmentation by noise addition applied to the analysis of spectroscopic data. Anal Chim Acta. 2005;533(2):147–59.
Conlin AK, Martin EB, Morris AJ. Data augmentation: an alternative approach to the analysis of spectroscopic data. Chemom Intell Lab Syst. 1998;44(1):161–73.
Li ZG, Peng SL, Yang N, et al. Quantitative analysis method of infrared spectra based on derivative spectra fusion modeling. Chin J Anal Chem. 2016;44(3):437–43.
Li ZG, Lv JT, Si GY, et al. An improved ensemble model for the quantitative analysis of infrared spectra. Chemom Intell Lab Syst. 2015;146:211–20.
Bian X H, Wang K Y, Tan E X, et al. A selective ensemble preprocessing strategy for near-infrared spectral quantitative analysis of complex samples. Chemom Intell Laborat Syst. 2020; 197:103916.
Xu L, Zhou YP, Tang LJ, et al. Ensemble preprocessing of near-infrared (NIR) spectra for multivariate calibration. Anal Chim Acta. 2008;616(2):138–43.
Lascola R, O’Rourke PE, Kyser EA. A piecewise local partial least squares (PLS) method for the quantitative analysis of plutonium nitrate solutions. Appl Spectrosc. 2017;71(12):2579–94.
Tan C, Qin X, Li ML. Ensembe partial least squares algorithmn mutual information-induced subspace for near-infrared quantitative calibration. Chin J Anal Chem. 2009;37(12):1834–8.
Xie JB. 20 Lectures on visual machine learning. Beijing: Tsinghua University Press; 2015.
Lei M. Machine learning: principles, algorithms and applications. Beijing: Tsinghua University Press; 2019.
Yu S, Liu GH, Xia SY, et al. State recognition of solid fermentation process based on near infrared spectroscopy with adaboost and spectral regression discriminant analysis. Spectr Spectral Anal. 2016;36(1):51–4.
Jin X, Zhu X Z, Li S W, et al. Predicting soil available phosphorus by hyperspectral regression method based on gradient boosting decision tree. Laser Optoelectr Progr. 2019; 56(13):131102.
Xu K, Cui Y. Application of stacking learning in hyperspectral image classification. Appl Sci Technol. 2018;45(6):42–6.
Tao YQ, Peng Y, Jiang Q, et al. Remote detection of critical growth stages in rapeseed using vegetation spectral and stacking combination method. J Geomat. 2019;44(5):20–3.
Shen T, Yu H, Wang YZ. Discrimination of gentiana and its related species using IR spectroscopy combined with feature selection and stacked generalization. Molecules. 2020;25(6):1442.
Shi RJ, Xia FZ, Zeng WD, et al. Raman spectroscopic classification of foodborne pathogenic bacteria based on PCA-stacking model. Laser Optoelectr Progr. 2019;56(4):20–3.
Yu X, Yang J, Xie ZQ. Research on virtual sample generation technology. Comput Sci. 2011;38(3):16–9.
Tang J, Qiao JF, Chai TY, et al. Multi-component mechanical signal modeling based on virtual sample generation technology. Acta Autom Sin. 2018;44(9):1569–89.
Li DC, Wu CS, Tsai TI, et al. Using mega-trend-diffusion and artificial samples in small data set learning for early flexible manufacturing system scheduling knowledge. Comput Oper Res. 2007;34(4):966–82.
Zhu B. Virtual sample generation technology and modeling application research. Beijing: Beijing University of Chemical Technology; 2017.
Gao KX, Li ZG, Xu CM, et al. Virtual sample construction and blood spectrum analysis of mixed overall trend diffusion. Chinese J Sci Instrum. 2019;40(8):94–101.
Gong HF. Research on virtual sample generation technology and application of industrial modeling. Beijing: Beijing University of Chemical Technology; 2018.
Yi L, Lv ZY, Ding JL, et al. Data amplification preprocessing method for prediction of total hydrogen properties of crude oil. Control and Decision. 2018;33(2):44–51.
Ye YF, Zhang XR, Mei B, et al. Research on modeling methods based on automatic densification technology. Sci Technol Vis. 2017;2:34–34.
Li JY, Chu XL. Rapid determination of hydrocarbon composition of LTAG raw materials and products by virtual spectral identification method. Acta Petrol Sin (Petroleum Process Sect). 2019;35(2):283–8.
Qian J, Guo YK, Zhang Q, et al. High spectral classification modeling of heavy metal Pb and Cd pollution in soil of mining area. Bull Surv Map. 2019;9:82–4.
Yang YN, Qi LH, Wang H, et al. Research on small sample data generation technology based on generative adversarial network. Electric Power Construct. 2019;40(5):71–7.
Zhi SS, Zhao QH, Jin DH, et al. The gait virtual sample generation method based on CNN and DLTL. Appl Res Comput. 2020;37(1):291–5.
Cui X W, Shen T, Liu Y L, et al. Small sample terahertz spectroscopy identification. Laser Optoelectron Progr. 2020.
Liu JW, Liu Y, Luo XL. Semi-supervised learning methods. Chinese J Comput. 2015;38(8):1592–618.
Chen WJ. Summarization of semi-supervised learning. Comput Knowl Technol. 2011;7(16):3887–9.
Cai Y, Zhu XF, Sun ZL, et al. Semi-supervised ensemble learning review. Comput Sci. 2017;44(6A):7–14.
Zhou ZH. Machine learning and its application. Beijing: Tsinghua University Press; 2007.
Li L, Xu S, An X, et al. New method for quantitative analysis of near infrared spectroscopy: semi-supervised least squares support vector regression machine. Spectrosc Spectr Anal. 2011;31(10):2702–5.
Zhang R. Incremental learning algorithm based on support vector regression. J Shandong Univ Technol (Soc Sci Ed). 2010;24(3):56–9.
Lv CC. Research on ensemble learning algorithm for incremental NIR semi-supervised SVR. Shenyang: Northeastern University; 2014.
Liang M, Cai JY, Yang K, et al. The application of semi-supervised partial least squares method in near infrared sensory evaluation model of tobacco leaves. Chin J Anal Chem. 2014;42(11):1687–91.
Guo DS. Research on the updating method of agricultural product quality detection model. Wuxi: Jiangnan University; 2018.
Jing SB, Yang LM, Li JH, et al. Semi-supervised extreme learning machine and its application in near infrared spectral data analysis. J Comput Appl. 2016;36(2):387–91.
Wang J, Gao XR, Zhang R, et al. Multi-objective regression combined with target-specific characteristics and target relevance. Acta Electron Sin. 2020;48(11):2092–100.
Spyromitros-Xioufis E, Tsoumakas G, Groves W, et al. Multi-target regression via input space expansion: treating targets as inputs. Mach Learn. 2016;104(1):55–98.
Shukla AK. Spectroscopic techniques and artificial intelligence for food and beverage analysis. Singapore: Springer; 2020.
Santana EJ, Geronimo BC, Mastelini SM, et al. Predicting poultry meat characteristics using an enhanced multi-target regression method. Biosys Eng. 2018;171:193–204.
Junior SB, Mastelini SM, Barbon APAC, et al. Multi-target prediction of wheat flour quality parameters with near infrared spectroscopy. Inform Process Agricult. 2019;7:342–54.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Bian, X. (2022). Methods for Improving Prediction Ability of Model. In: Chemometric Methods in Analytical Spectroscopy Technology. Springer, Singapore. https://doi.org/10.1007/978-981-19-1625-0_14
Download citation
DOI: https://doi.org/10.1007/978-981-19-1625-0_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1624-3
Online ISBN: 978-981-19-1625-0
eBook Packages: Chemistry and Materials ScienceChemistry and Material Science (R0)