Determination of Total Flavonoid Content in Flos Sophorae Immaturus Using Near Infrared Spectroscopy

Near infrared spectroscopy combined with multivariate calibration methods was used to analyze the total flavonoid content in Flos Sophorae Immaturus in this paper. Principal component regression (PCR), partial least squares regression (PLSR) and support vector regression (SVR) were performed comparatively to develop calibration models. Data preprocessing methods and calibration model parameters were independently optimized for each case. The performance of SVR model was superior to PLSR and PCR models. The root mean square error of prediction (RMSEP) and correlation coefficient of prediction (Rp 2) of SVR model were 0.0025 and 0.9690, respectively. Results showed that NIR spectroscopy combined with SVR has significant potential in quantitative analysis of flavonoid content in Flos Sophorae Immaturus.