Quantitative Analysis of Protein and Polysaccharide in Lilium Lanzhou Based on Near Infrared Spectroscopy

Abstract

In order to quickly detect the nutritional components of Lilium Lanzhou, a national geographical indication product, a quantitative analysis model of protein and polysaccharide was established by near infrared spectroscopy and chemometrics. A total of 81 samples of Lilium Lanzhou were collected. SG smoothing + first derivative + MSc spectral preprocessing method was selected to establish the spectral model of protein and polysaccharide quantitative detection of Lilium Lanzhou Based on partial least square method. The correlation coefficient (R2) of protein model is 0.844, RMSEP is 0.268, the correlation coefficient (R2) of polysaccharide model is 0.715, RMSEP is 0.273. The experimental results show that NIRS technology is feasible for the rapid detection of key quality of Lilium Lanzhou, which is expected to provide a new method for the rapid evaluation of key nutritional quality of Lilium Lanzhou.

A rapid and non‐destructive identification for paper cup evidence based on shifted‐excitation Raman difference spectroscopy and SOM clustering

“…Each input sample finds a node that best matches it in the hidden layer, called its active node, also called “wining neuron”. Then, the parameters of the active node updated with the random gradient descent method [34]. At the same time, the points close to the active node also update the parameters appropriately according to their distance from the active node.…”

“…Each input sample finds a node that best matches it in the hidden layer, called its active node, also called "wining neuron". Then, the parameters of the active node updated with the random gradient descent method [34].…”