Supervised principal components: a new method for multivariate spectral analysis

Abstract

The supervised principal components (SPC) method was proposed by Bair and Tibshirani for statistics regression problems where the number of variables greatly exceeds the number of samples. This case is extremely common in multivariate spectral analysis. The objective of this research is to apply SPC to near‐infrared and Raman spectral calibration. SPC is similar to traditional principal components analysis except that it selects the most significant part of wavelength from the high‐dimensional spectral data, which can reduce the risk of overfitting and the effect of collinearity in modeling according to a semi‐supervised strategy. In this study, four conventional regression methods, including principal component regression, partial least squares regression, ridge regression, and support vector regression, were compared with SPC. Three evaluation criteria, coefficient of determination (R2), external correlation coefficient (Q2), and root mean square error of prediction, were calculated to evaluate the performance of each algorithm on both near‐infrared and Raman datasets. The comparison results illustrated that the SPC model had a desirable ability of regression and prediction. We believe that this method might be an alternative method for multivariate spectral analysis. Copyright © 2013 John Wiley & Sons, Ltd.

Recent Advances in Supervised Dimension Reduction: A Survey

“…Bin et al [24] compared the supervised PCA with four traditional regression methods and illustrated the superiority of supervised PCA. Roberts and Martin [25] applied supervised PCA proposed in [20] to assess multiple pollutant effects.…”

Chemometrics in instrumental analysis of complex systems—in honor and memory of Yi‐Zeng Liang

“…It was found that ULDA was able to successfully extract discriminating information, suggesting its potential use for biomarker discovery. Bin et al proposed supervised components and explored their application in NIR and Raman data modeling . Shrunken centroids regularized discriminant analysis (SCRDA) has been introduced and applied in the exploration of metabolomic datasets, representing a supervised method for variable selection, discriminant analysis, and biomarker screening .…”

IRT for NDT: 2050 Horizon

“…There are many data processing algorithms and the selection of the method depends on the objectives of the research. Some of the most useful techniques are [54][55][56][57][58][59][60][61][62][63][64][65][66][67]: Thermal signal reconstruction (TSR), Differential absolute contrast (DAC), Pulsed phase thermography (PPT), Principal component thermography (PCT), Partial least square thermography (PLST) and Supervised principal component analysis (SPCA). Thermal infrared NDT data processing techniques have some advantages and limitations such as defect detection enhancement on one hand, but sometimes exhibit slow computing or require interactions with an operator to select algorithm parameters on the other hand (ex: selection of a non-defect area which could affect final results).…”