Method for constructing liquorice near-infrared spectrum analysis model based on kernel function optimization and liquorice quality evaluation method

A near-infrared spectrum and analysis model technology, which is applied in the field of near-infrared spectrum detection and analysis model construction of licorice medicinal materials, can solve the problems of large influence of subjective factors, large consumption of reagents, and influence on treatment effect, and achieve rapid evaluation and analysis, which is not easy trapped in a local optimum

Inactive Publication Date: 2019-10-01
CHINA UNIV OF MINING & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most of the licorice medicinal materials on the market are artificially planted. Due to the diversification of planting methods and the differences in the planting environment, the quality of licorice is uneven, which affects the therapeutic effect.
At present, the quality evaluation methods of licorice mainly include artificial experience method, ultramicromorphological method, DNA barcode identification method, high-performance liquid chromatography and other methods, which have disadvantages such as being greatly affected by subjective factors, complicated operation, long analysis cycle, and the need to consume a large amount of reagents.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for constructing liquorice near-infrared spectrum analysis model based on kernel function optimization and liquorice quality evaluation method
  • Method for constructing liquorice near-infrared spectrum analysis model based on kernel function optimization and liquorice quality evaluation method
  • Method for constructing liquorice near-infrared spectrum analysis model based on kernel function optimization and liquorice quality evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings, but the content of the present invention is not limited thereto.

[0035] The invention provides a near-infrared quantitative analysis model and establishment method of licorice medicinal materials, which can quickly and non-destructively detect licorice medicinal materials, specifically including the following steps:

[0036] Licorice samples were collected from different producing areas and numbered.

[0037] Ammonium glycyrrhizinate was selected as the quality control index of licorice medicinal material, and it was determined by high performance liquid chromatography.

[0038] Using near-infrared spectroscopy technology, the spectral scanning range is 10001.03cm -1 -3999.6400cm -1 , with a resolution of 4cm -1 , each sample was scanned 64 times, and the average value was used as the original near-infrared spectrum of the sample to obtai...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for constructing a liquorice near-infrared spectrum analysis model based on kernel function optimization and a liquorice quality evaluation method. The method comprises the following steps of establishing a sample database according to collected liquorice spectrum data and a sample reference value; selecting a radial basis, a polynomial and a generalized T studentfunction as kernel functions of kernel principal component analysis to realize feature extraction of high-dimensional spectrum data; and based on this, selecting a radial basis function as a kernel function of a kernel partial least squares model. At the same time, a genetic algorithm is used to optimize relevant hyper-parameters of the kernel function, the liquorice near-infrared spectrum analysis model is established, a quality evaluation problem is transformed into a regression problem, and the quality of liquorice is analyzed. The method for constructing the liquorice near-infrared spectrum analysis model based on the kernel function optimization provided by the invention not only has the advantages of being simple in operation and lossless, but also ensures the safety and effectiveness of the quality of the liquorice.

Description

technical field [0001] The invention belongs to the technical field of near-infrared spectrum analysis and detection, and relates to a method for constructing a near-infrared spectrum detection and analysis model of licorice medicinal materials. Background technique [0002] Licorice, also known as sweet grass root and honey grass, is the root and rhizome of the leguminous plant Glycyrrhiza uralensis Fisch. At present, most of the licorice medicinal materials on the market are artificially planted. Due to the diversification of planting methods and the differences in planting environments, the quality of licorice is uneven, which affects the therapeutic effect. At present, the quality evaluation methods of licorice mainly include artificial experience method, ultramicromorphological method, DNA barcode identification method, high-performance liquid chromatography and other methods, which have disadvantages such as being greatly affected by subjective factors, complicated ope...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01N21/359
CPCG01N21/359
Inventor 雷萌於鑫慧邹亮饶中钰李明
Owner CHINA UNIV OF MINING & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products