Notice of Retraction Growing area determination of Tremella fuciformis using visible and near-infrared spectroscopy

Visible and near infrared (NIR) spectroscopy was utilized to determine the growing areas of Tremella fuciformis. Principal component analysis (PCA) obtained the cluster plot which shows the difficulty to determine the growing area by the first three principal components. Least-square support vector machine (LS-SVM) was used to establish the calibration model. Successive projections algorithm (SPA) was applied to select the effective variables from the full-spectrum (FS) which have 675 spectra variables. Finally eleven variables were selected. Effective variables based LS-SVM model obtain 100% determination correct rate. It was proved that SPA was an effective algorithm for spectra variable selection. As a conclusion, Vis-NIR spectroscopy could be used to determine the growing areas of Tremella fuciformis fast and accurately.