Measurement of total flavone content in snow lotus (Saussurea involucrate) using near infrared spectroscopy combined with interval PLS and genetic algorithm

NIR spectroscopy technique was attempted to measure total flavone content in snow lotus in this work. Interval partial least square with genetic algorithm (iPLS-GA) was used to select the efficient spectral regions and variables in model calibration. The performance of the final model was back-evaluated according to root mean square error of calibration (RMSEC) and correlation coefficient (R-c) in calibration set, and tested by mean square error of prediction (RMSEP) and correlation coefficient (R-p) in prediction set. The optimal iPLS-GA model was obtained with 6 PLS factors, when 5 spectral regions and 53 variables were selected. The measurement results of final model were achieved as follow: RMSEC (%) = 0.8347/R-c = 0.9444 in the calibration set, and RMSEP (%) = 1.0766/R-p = 0.9006 in the prediction set. Finally, iPLS-GA moded showed its excellent performance, when compared with other 5 different PLS models. This work demonstrated that total flavone content in snow lotus could be measured by NIR spectroscopy technique, and iPLS-GA revealed its superiority in model calibration. (C) 2010 Elsevier B.V. All rights reserved.