Application of Wavelet Packet Transform-Radial Basis Function Neural Network in NIR Spectroscopy for Non-destructive Determination of Tricholoma Matsutake

A novel calibration model has been proposed for synchronous, rapid and non-destructive determination the content of polysaccharide and protein in medical fungi Tricholoma matsutake by near infrared reflectance (NIR) spectroscopy. This model is a combination of wavelet packet transform (WPT) data disposal with multi-scale analysis and radial basis function neural network (WPT-RBFNN). Via using principal component analysis (PCA) method for analyzing these reconstructed spectra matrix, the anterior 15 PC scores of principal components (PC) were obtained, which were used as input data in RBFNN. The network parameters including number of input nodes, number of hidden layer neurons and spread constant (SC) were investigated. WPT-RBFNN model which reconstructed the spectra data, removed the noise and the interference of background, and reduced the randomness, the capabilities of prediction is well optimized. Both precision of prediction and calculation speed are well improved. The root mean square errors of prediction (RMSEP) for determination of polysaccharide and protein obtained from the optimum WPT-RBFNN model are 0.00956 and 0.00943, which are superior to those that obtained by the optimum RBFNN models with origin spectra. Regression coefficient (R) between NIR predicted values and actual values for polysaccharide and protein are 0.98638 and 0.98292. It is verified that WPT-RBFNN model with multi-scale analysis is a suitable approach to deal with NIR spectroscopy and model this complex non-linearity. The proposed method which is convenient, rapid, no pretreatment and non-destructive for more precise determination of Tricholoma matsutake could be popularized in the in situ measurement and the on-line quality control for medical fungi.