ATR-FTIR and NIR spectra combined with chemometrics and convolutional neural networks for identification of polygonati rhizome

Considering the high similarity among various rhizomes, the issue of adulteration and mixed use of polygonati rhizome (PR) in the market is widespread. Nowadays, the PR polysaccharides are the main pharmacological active ingredient. To ensure the uniformity of the product quality, it is essential to establish an effective and rapid method for PR identification. Herein, the polysaccharides content was determined via ATR-FTIR and NIR spectra of PR. The correlation between polysaccharides content and spectra were analyzed. Additionally, the partial least squares discriminant analysis (PLS-DA), support vector machines (SVM), and convolutional neural networks (CNN) were established using the data of ATR-FTIR spectra, NIR spectra, characteristic bands and feature variables. The obtained difference of the polysaccharides content was particularly large. By extracting latent variables and combining data fusion to establish PLS-DA, SVM and CNN, PR can be accurately identified. The content of PR polysaccharides can be predicted based on the absorbance according to ATR-FTIR and NIR spectra.