Robust modeling for multivariate calibration transfer by the successive projections algorithm

Honorato, Fernanda Araújo; Galvão, Roberto Kawakami Harrop; Pimentel, Maria Fernanda; Neto, Benício de Barros; Araújo, Mário César Ugulino de; Carvalho, Florival Rodrigues de

doi:10.1016/j.chemolab.2004.09.006

Cited by 49 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A potentially interesting topic is to combine the fused LASSO and elastic net by appending an additional`2 penalty on b in Equation (14). This helps with the rank deficiency of the data but would require an additional penalty parameter.…”

Section: Outlier Accommodation and Detectionmentioning

confidence: 99%

“…Therefore, a new effective and efficient algorithm is in great need to meet the computational challenges in high-dimensional RFL. We first study the fused LASSO (corresponding to = 0 in Equation (14) and develop a new algorithm on the basis of a newly advocated technique called alternating direction method of multipliers (ADMM) [43]. For ADMM's computational advantages for high-dimensional problems, see References [43][44][45].…”

Section: Computationmentioning

confidence: 99%

“…Clearly, RFL includes LASSO, the fused LASSO, and ‚ HR -IPOD as particular instances. A general robust framework following Equation (14) can be similarly given to allow for other penalties (possibly non-convex) imposed on b and . For example, we can enforce an`2 penalty on b to replace the fused LASSO penalty, as suggested by an anonymous referee:…”

Section: Outlier Accommodation and Detectionmentioning

confidence: 99%

“…This section shows how to design a strategy to tune the parameters ( 2 , ) in the estimate of in the RFL problem (14) and then tune ( 1 , ) for b. We propose a novel alternating tuning scheme that is integrated into the optimization process till convergence.…”

Section: Parameter Selectionmentioning

confidence: 99%

See 3 more Smart Citations

Multivariate calibration maintenance and transfer through robust fused LASSO

Kunz

She

2013

Journal of Chemometrics

View full text Add to dashboard Cite

This article studies calibration maintenance and transfer to build a statistical model that is able to predict analyte concentrations by a set of spectra. Noticing that the wavelength atoms are naturally ordered in a meaningful way, we propose a novel robust fused LASSO (RFL) based on high-dimensional sparsity techniques and a recent ‚-IPOD technique for robustification. This new approach can attain simultaneous wavelength selection and grouping as well as outlier identification, without any human intervention. An efficient and scalable algorithm is developed on the basis of the alternating direction method of multipliers. The obtained RFL model is sparse and shows improved prediction performance over the LASSO and ridge regression. Our results reveal that wavelengths can be combined into blocks, in a smart manner, to enhance the interpretability and reliability for super-resolution spectral analysis.

show abstract

Section: Outlier Accommodation and Detectionmentioning

confidence: 99%

Section: Computationmentioning

confidence: 99%

Section: Outlier Accommodation and Detectionmentioning

confidence: 99%

Section: Parameter Selectionmentioning

confidence: 99%

See 2 more Smart Citations

Multivariate calibration maintenance and transfer through robust fused LASSO

Kunz

She

2013

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…[29][30][31][32] By using Eq. 7, we hope to immunize the primary calibration model against spectral noise while simultaneously performing wavelength selection.…”

Section: Calibration Maintenance Andmentioning

confidence: 99%

Sparse Methods in Spectroscopy: An Introduction, Overview, and Perspective

Andries

Martin

2013

Appl Spectrosc

View full text Add to dashboard Cite

Multivariate calibration methods such as partial least-squares build calibration models that are not parsimonious: all variables (either wavelengths or samples) are used to define a calibration model. In high-dimensional or large sample size settings, interpretable analysis aims to reduce model complexity by finding a small subset of variables that significantly influences the model. The term ''sparsity'', as used here, refers to calibration models having many zerovalued regression coefficients. Only the variables associated with non-zero coefficients influence the model. In this paper, we briefly review the regression problems associated with sparse models and discuss their spectroscopic applications. We also discuss how one can reappropriate sparse modeling algorithms that perform wavelength selection for purposes of sample selection. In particular, we highlight specific sparse modeling algorithms that are easy to use and understand for the spectroscopist, as opposed to the overly complex ''blackbox'' algorithms that dominate much of the statistical learning literature. We apply these sparse modeling approaches to three spectroscopic data sets.

show abstract

Calibration transfer of near‐IR partial least squares property models of fuels using virtual standards

Cooper

Larkin

Abdelkader

2011

Journal of Chemometrics

View full text Add to dashboard Cite

a Partial least squares (PLS) models of 10 important jet and diesel fuel properties were built using spectra from a master near-IR dispersive instrument and then subsequently transferred to a secondary dispersive instrument via a novel calibration transfer method using virtual standards and a slope-bias correction. Implementation of the transfer requires that only seven spectra of neat solvents be acquired on the master and secondary instruments. The spectra of the neat solvents are then used to digitally replicate spectra from the calibration set to generate virtual standards. Comparison of PLS predictions for the master and secondary instrument virtual standards provides a simple but effective slope-bias correction for transfer. The transferred fuel properties include American Petroleum Institute gravity, % aromatics, cetane index, flashpoint, hydrogen content, % saturates, and distillation temperatures at 10%, 20%, 50%, and 90% volume recovered. Transfer error was lower than using either the pure solvents with a slope-bias correction or than using a piecewise direct standardization calibration transfer using fuel spectra. Transfer error was higher than when using actual fuels to transfer the calibration. The use of virtual standards eliminates the need to maintain either complex fuel standards or the master instrument for future instrument calibration transfers.

show abstract

Robust modeling for multivariate calibration transfer by the successive projections algorithm

Cited by 49 publications

References 19 publications

Multivariate calibration maintenance and transfer through robust fused LASSO

Multivariate calibration maintenance and transfer through robust fused LASSO

Sparse Methods in Spectroscopy: An Introduction, Overview, and Perspective

Calibration transfer of near‐IR partial least squares property models of fuels using virtual standards

Contact Info

Product

Resources

About