Direct calibration transfer to principal components via canonical correlation analysis

Abstract

In order to solve the calibration transfer problem in near-infrared (NIR) spectroscopy, a fast and efficient method named principal components canonical correlation analysis (PC-CCA) has been proposed. PC-CCA can extract principal components of spectra from slave instrument with principal component analysis (PCA), and then transfer the slave principal components toward latent variables of partial least squares (PLS) model with canonical correlation analysis directly. Two NIR datasets of corn and tobacco samples measured with three and two spectrometers, respectively, were used to test the reliability of this method. The piecewise direct standardization (PDS), spectral space transformation (SST) and calibration transfer method based on canonical correlation analysis (CTCCA) methods were performed for comparative study of the proposed model transfer technique. The results of both datasets reveal that PC-CCA can drastically reduce time of transfer and lead to dozens-fold speedup. It can also reduce prediction errors and achieve the smallest root mean square errors of prediction (RMSEPs). For example, the spectra transfer from M5 to MP5, the comparative experiment results show that RMSEP with the proposed method PC-CCA is reduced from 2.5641 (without transfer) to 0.0934, and much smaller than that with PDS (0.1999), CTCCA (0.1377) and SST (0.1296) at N = 50. These advantages make PC-CCA a promising calibration transfer method in NIR application.