Cross components calibration transfer of NIR spectroscopy model through PCA and weighted ELM-based TrAdaBoost algorithm

Abstract With the rapid development of NIR spectroscopy technology and chemometrics, many previous studies have focused on calibration transfer of quantitative analysis model and lots of effectively methods have been proposed, such as slope and bias correction (SBC), piecewise direct standardization (PDS) etc., by which we can implement calibration transfer between different spectrometers. Furthermore, whether it is possible to realize calibration transfer cross different components or not? To answer this question, this paper proposed a novel method which combines principal component analysis (PCA), weighted extreme learning machine (ELM) and TrAdaBoost algorithm. Two public NIR spectroscopy datasets (Corn and Gasoline) are applied to validate the possibility and effectiveness of proposed algorithm through four different experimental protocols. The experimental results show that while the objects of source and target domains are same, whatever calibration transfer between different instruments or components (experimental protocol #2, #3 and #4), the generalization performance of target domain model will improve a lot, especially while target domain contains fewer samples. Particularly, compared with experimental protocol #2 and #3 (only instruments or components between source and target domains are different), there is a significant improvement while the instruments and components are all different (experimental protocol #4). However, while the objects, components and instruments between source and target domains are all different, the generalization performance of quantitative analysis model can not be improved after calibration transfer. The experimental results indicate that in the area of NIR spectroscopy calibration transfer area, the assumption of original TrAdaBoost algorithm can be relaxed so that the labels between source and target domains can different (cross components), but the features must be same.

[1]  B. Kowalski,et al.  Multivariate instrument standardization , 1991 .

[2]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[3]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[4]  Steven D. Brown,et al.  Stacked PLS for calibration transfer without standards , 2011 .

[5]  John H. Kalivas,et al.  Multivariate Calibration, an Overview , 2005 .

[6]  T. Fearn.  Standardisation and Calibration Transfer for near Infrared Instruments: A Review , 2001 .

[7]  Ji Haibo,et al.  Near-infrared calibration transfer via support vector machine and transfer learning , 2015 .

[8]  Jean-Michel Roger,et al.  Robust calibration using orthogonal projection and experimental design. Application to the correction of the light scattering effect on turbid NIR spectra , 2008 .

[9]  Yufeng Ge,et al.  Comparison of soil reflectance spectra and calibration models obtained using multiple spectrometers , 2011 .

[10]  J. Kalivas.  Two data sets of near infrared spectra , 1997 .

[11]  Pierre Dardenne.  Calibration Transfer in near Infrared Spectroscopy , 2002 .

[12]  Vincent Baeten,et al.  Calibration Transfer from Dispersive Instruments to Handheld Spectrometers , 2010, Applied spectroscopy.

[13]  S. Wold,et al.  Orthogonal signal correction of near-infrared spectra , 1998 .

[14]  Xinge You,et al.  Robust calibration model transfer , 2016 .

[15]  Thomas Natschläger,et al.  Standard-free calibration transfer - An evaluation of different techniques☆ , 2017 .

[16]  Foo-Tim Chau,et al.  Analysis of berberine and total alkaloid content in cortex phellodendri by near infrared spectroscopy (NIRS) compared with high-performance liquid chromatography coupled with ultra-visible spectrometric detection. , 2007, Analytica chimica acta.

[17]  Harris Drucker,et al.  Improving Regressors using Boosting Techniques , 1997, ICML.

[18]  Yan Liu,et al.  Linear model correction: A method for transferring a near-infrared multivariate calibration model without standard samples. , 2016, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[19]  Susan L. Rose-Pehrsson,et al.  Comparison of two multiplicative signal correction strategies for calibration transfer without standards , 2008 .

[20]  Steven D. Brown,et al.  Dual-Domain Calibration Transfer Using Orthogonal Projection , 2018, Applied spectroscopy.

[21]  Jerry Workman,et al.  A Review of Calibration Transfer Practices and Instrument Differences in Spectroscopy , 2018, Applied spectroscopy.

[22]  Steven D. Brown,et al.  Transfer of multivariate calibration models: a review , 2002 .

[23]  Tom Fearn,et al.  Transfer by orthogonal projection: making near-infrared calibrations robust to between-instrument variation , 2004 .

[24]  Steven D Brown,et al.  Transfer of multivariate calibrations between four near-infrared spectrometers using orthogonal signal correction. , 2004, Analytical chemistry.

[25]  T. B. Blank,et al.  Transfer of Near-Infrared Multivariate Calibrations without Standards. , 1996, Analytical chemistry.

[26]  P. Worsfold,et al.  The application of piecewise direct standardisation with variable selection to the correction of drift in inductively coupled atomic emission spectrometry , 2006 .

[27]  Marcelo Nascimento Martins,et al.  A comparative study of calibration transfer methods for determination of gasoline quality parameters in three different near infrared spectrometers. , 2008, Analytica chimica acta.

[28]  D. Massart,et al.  Standardization of near-infrared spectrometric instruments , 1996 .

[29]  Yiqiang Chen,et al.  Weighted extreme learning machine for imbalance learning , 2013, Neurocomputing.

[30]  Olof Svensson,et al.  Transfer of NIR calibrations for pharmaceutical formulations between different instruments. , 2006, Journal of pharmaceutical and biomedical analysis.

[31]  Alberto Ferrer,et al.  Calibration transfer between NIR spectrometers: New proposals and a comparative study , 2017 .