Traditional Chinese medicinal material production place determination method based on principal component analysis and BP neural network

A BP neural network and principal component analysis technology, applied in the field of spectral recognition, can solve unapplied problems, achieve the effects of ensuring quality and safety, simplifying the detection process, and quickly identifying

Active Publication Date: 2018-02-09
CHONGQING UNIV OF POSTS & TELECOMM
View PDF7 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there are few studies on Chinese medicinal materials using laser-induced breakdown spectroscopy, and the method of applying principal components combined with neural networks has not been applied in the identification of traditional Chinese medicines.

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
  • Traditional Chinese medicinal material production place determination method based on principal component analysis and BP neural network
  • Traditional Chinese medicinal material production place determination method based on principal component analysis and BP neural network
  • Traditional Chinese medicinal material production place determination method based on principal component analysis and BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] The identification of the place of origin of embodiment 1 lovage root

[0027] This experiment is to identify the origin of Chinese herbal medicines from Chengkou, Wuxi and Wushan. In order to simplify the analysis process, the origins are numbered and marked as 1, 2, 3 in turn. Considering that the physical properties of the sample, such as the dryness of the sample, the uniformity and density of the grinding will affect the spectral signal to a certain extent, the sample is simply pretreated before the LIBS detection experiment. First, use an electric blast drying oven to dry all the Chinese herbal medicines at a temperature of 40°C for about 4 hours. Then use a pulverizer to pulverize the sample, and use a standard inspection sieve with an aperture of 0.075 mm to obtain a uniform and fine powder sample. Then the powder sample was added to the mold, and a mechanical tablet press was used to apply a pressure of about 10Mpa to the Chinese herbal medicine powder for 2 ...

Embodiment 2

[0032] The identification of embodiment 2 Codonopsis origin

[0033] This experiment is to verify the feasibility of principal component analysis combined with BP neural network method to identify the origin of other Chinese medicinal materials, and then do the same treatment on the roots of Codonopsis pilosula from the three origins. That is, the sample pretreatment of Chinese herbal medicines is to obtain the spectral data. After the preprocessing of the full-spectrum data, the principal component analysis is carried out. The first five principal components are taken, and the cumulative interpretation rate is 91.975%. The selected principal components are used as the input of the BP neural network to analyze the traditional Chinese medicine. The results are shown in Table 2.

[0034] It can be seen from Table 2 that the method of applying principal components combined with BP neural network can accurately judge Chinese herbal medicines. Among them, the average identificatio...

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 traditional Chinese medicinal material production place determination method based on principal component analysis and a BP neural network. The traditional Chinese medicinalmaterial production place determination method comprises the following steps of sample preparation, spectroscopic data acquisition of samples, principal component analysis, BP neural network modelingand production place determination. A novel LIBS detecting technology is used for detecting traditional Chinese medicinal material samples, and the detecting process is simplified. Dimensionality reduction is conducted on full spectrum data through principal component analysis, the principal component number having a certain accumulative contribution rate is extracted, and unnecessary noise background signals and the like can be removed. After BP neural network training, quick determination of traditional Chinese medicinal materials can be achieved, and the quality and safety of the traditional Chinese medicinal materials can be effectively ensured.

Description

technical field [0001] The invention relates to the technical field of spectrum identification, and relates to a method for identifying the origin of traditional Chinese medicinal materials based on principal component analysis and BP neural network. technical background [0002] Traditional Chinese medicine is the treasure of the Chinese nation. For thousands of years, Chinese medicine has occupied an irreplaceable position in the medical history of the Chinese nation and has made indelible contributions to the prosperity of the Chinese nation. Chinese medicinal materials are necessary materials for the treatment of traditional Chinese medicine in my country, and can be used to prevent, diagnose, treat diseases or regulate human body functions under the guidance of Chinese medicine theory. The medicinal properties of traditional Chinese medicine are affected by many aspects, especially the plant-based Chinese medicinal materials. Different origins, collection times, and dif...

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): G01N21/63
CPCG01N21/63
Inventor 王金梅廖香玉郑培超
Owner CHONGQING UNIV OF POSTS & TELECOMM
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap