Discrimination of Radix Pseudostellariae according to geographical origins using NIR spectroscopy and support vector data description.

Near infrared (NIR) spectroscopy combined with support vector data description (SVDD) was attempted to identify geographical origins of Radix Pseudostellariae. Original spectra of eggs in wavelength range of 10000-4000 cm(-1) were acquired. SVDD was performed to calibrate discrimination model, and some parameters of SVDD model were optimized. Meanwhile, conversional two-class classification method-support vector machine (SVM) was used comparatively for classification. Compared with SVM classification, SVDD model showed its superior ability in dealing with imbalance training samples. When the proportion of the number of Radix Pseudostellariae from Anhui province (the area where genuine crude Radix Pseudostellariae was cultivated) and other provinces was one to sixteen, the identification rate of SVDD model was 92.5% in prediction set. This work indicates that NIR spectroscopy combined with SVDD is an excellent choice in building one-class calibration model for discrimination of genuine crude Radix Pseudostellariae.