Research Article

Rapid Characterization of Tanshinone Extract Powder by Near Infrared Spectroscopy

Table 6

Comparison of different preprocessing methods of partial least squares model for content of cryptotanshinone/mg·g−1.

Preprocessing methodLVsCalibration setValidation set
RMSECRMSECVBIAScalRMSEPRPDBIASpre

Raw 100.99220.00260.00490.00190.97980.00274.40.0021
S-G smooth100.99210.00260.00490.00190.97960.00274.40.0022
Normalization 110.99630.00180.00330.00130.99690.00138.90.0011
S-T110.99550.00200.00410.00150.99220.00148.10.0011
MSC140.99830.00120.00290.00100.99210.00157.90.0012
S-G 1st 60.98830.00320.00410.00230.99490.00205.90.0016
S-G 2nd 60.99340.00240.00430.00160.99100.00157.70.0014
Baseline 80.98450.00360.00550.00250.98820.00215.60.0017
SNV110.99620.00180.00370.00150.99630.00158.10.0010
WDS80.97990.00410.00590.00290.98140.00235.10.0020

Raw means using the original spectra without any pretreatment; LVs means numbers of latent factors of the PLS model. and represent correlation coefficients for calibration and validation sets, respectively. RMSEC, RMSECV, and RMSEP represent the root mean square error of calibration, cross validation, and prediction, respectively. BIAScal and BIASpre represent bias for calibration and validation, respectively. RPD means relative predictive deviation.
S-G smooth means Savitzky-Golay smoothing; S-T represents spectroscopic transformation; MSC means multiplicative scatter correction; S-G 1st is Savitzky-Golay smoothing plus first-order derivatives for short; S-G 2nd means Savitzky-Golay smoothing plus first-order derivatives; baseline means baseline correction; SNV represents standard normal variate transformation and WDS is wavelet denoise of spectra for short.