NIR model transfer of alkali-soluble polysaccharides in Poria cocos with piecewise direct standardization

Abstract

Objective To investigate the feasibility for establishing near-infrared spectra model transfer with traditional Chinese medicine. Method Poria cocos, a kind of fungi (called “ Fuling” in Chinese), was used as an investigative object. NIR quantification model transfer of alkali-soluble polysaccharides in Poria cocos was studied. Spectra were obtained from Thermo Antaris II (master device) and Buchi NIRFlex N-500 (slave device), respectively. Procedures and factors that may have effects on the performance of spectral standardization have been investigated. Spline interpolation was applied to align spectra from two different instruments, and piecewise direct standardization was employed to standardize spectra from slave instrument. Full cross-validation was used to evaluate the result of model transfer. Results Spectral pre-processing including multiplicative signal correction and wavelength selection played an important role in operating the model transfer. Spectra within the region of 9000–6500 cm−1 provided relatively good transfer result. In addition, increasing window size had positive effect on improving the spectral transfer. In this study, a window size of 13 provided the best spectra standardization result. Test validation with five samples produced the best full cross-validation result with the values of correlation coefficient of calibration ([Formula: see text]), correlation coefficient of prediction ([Formula: see text]) and root mean square error of prediction as 0.86, 0.73 and 2.3, respectively. Conclusion In this study, many factors influenced the quality of the transferred slave spectra. And it is hard to provide a pretty good quantitative model transfer result about alkali-soluble polysaccharide in Poria cocos. The following factors have great effects on the quality of model transfer: (i) multiplicative signal correction which is necessary for model building; (ii) increasing the window size which has a positive effect on slave spectra standardization; (iii) a proper wavelength region benefits for model building; (iv) a proper scale of standardization group including proper samples is necessary.