Unlock instant, AI-driven research and patent intelligence for your innovation.

Detection method of Nansha ginseng medicinal materials based on neural network

A neural network and detection method technology, applied in the field of traditional Chinese medicine identification, can solve problems such as difficult to distinguish between Adenophora or Adenophora verticillum, difficult to judge, etc., achieve the effect of improving accuracy and efficiency, and improving identification efficiency

Active Publication Date: 2022-07-29
GUANGDONG YIFANG PHARMA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult to distinguish between Adenophora verticillum and Adenophora verticillum from the perspective of the apparent properties of the medicinal materials. From the perspective of chemical composition, it is also difficult to judge due to the similarity of chemical components of the same phytochemicals.

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
  • Detection method of Nansha ginseng medicinal materials based on neural network
  • Detection method of Nansha ginseng medicinal materials based on neural network
  • Detection method of Nansha ginseng medicinal materials based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] A method for detecting Nansha ginseng medicinal materials based on neural network, comprising:

[0031] S101. Obtain a certain amount of the apparent properties of Radix Radix et Rhizoma, the similarity with the reference medicinal material of Radix Radix Radix et Rhizoma, and the type of Radix Radix Rhizoma Radix as a sample set;

[0032] S102. extract the feature of apparent character, described feature comprises stem color, stem horizontal grain number, stem maximum diameter, branching situation, stem swelling situation, the length of stem swelling distance node, stem vertical grain number, the apparent The characteristics of the traits and the similarity with the reference medicinal materials of Radix Radix are input into the neural network, so as to train the neural network to obtain the neural network used to detect the types of Radix Rhizoma Radix;

[0033] S11. Obtain the apparent properties of the Nansha ginseng medicinal material to be tested, and establish th...

Embodiment 2

[0038] A method for detecting Nansha ginseng medicinal materials based on neural network, comprising:

[0039] S101. Obtain a certain amount of the apparent properties of the medicinal materials of Nansha ginseng and the type of the ginseng as a sample set;

[0040] S102. Extract the features of apparent traits, the features include stem color, number of horizontal stripes on the stem, input the features of apparent traits into a neural network, and obtain a neural network for detecting Nansha ginseng categories with a training neural network;

[0041] S11. Obtain the apparent properties of Nansha ginseng to be tested, and establish the UPLC fingerprint of Nansha ginseng medicinal materials;

[0042] S12. Extract the features of apparent properties, the features include stem color, number of horizontal stripes on the stem, standardize the features of apparent properties, obtain the similarity with the fingerprints of the reference medicinal materials of Rhizoma Radix, and compar...

Embodiment 3

[0046] A method for detecting Nansha ginseng medicinal materials based on neural network, comprising:

[0047] S101. Obtain the apparent properties of a certain number of Nansha ginseng medicinal materials, the similarity with the reference medicinal materials of Sha ginseng, and the type of Sha ginseng as a sample set;

[0048] S102. Extract the features of apparent traits, the features include stem color (1=yellow-white; 2=light yellow; 3=yellow; 4=yellow-brown), the number of horizontal stripes on the stem, and the maximum diameter of the stem. The characteristics of the traits are input into the neural network, so as to train the neural network to obtain the neural network for detecting the species of Nansha ginseng;

[0049] S11. Obtain the apparent properties of the Nansha ginseng medicinal material to be tested, and establish the UPLC fingerprint of the Nansha ginseng medicinal material;

[0050] S12. Extract the features of apparent traits, the features include stem c...

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 relates to the field of traditional Chinese medicine identification, and provides a neural network-based rapid identification and detection method for Nansha ginseng medicinal materials, which is used for detecting and distinguishing Nansha ginseng medicinal materials of different origins. The invention provides a method for detecting Nansha ginseng medicinal materials based on a neural network, comprising: S11. Obtaining the apparent properties of the Nansha ginseng medicinal materials to be tested, and establishing a UPLC fingerprint of the Nansha ginseng medicinal materials; S12. Extracting the characteristics of the apparent properties, Standardize the characteristics of the apparent traits, and obtain the similarity of the fingerprints of the reference medicinal materials of Panax Radix, and each index is used as the input layer of the neural network; S13. Obtain the output results of the neural network, and obtain the classification results of the medicinal materials of Panax Radix. The above classification result is Radix Radix or Radix Radix. The trained neural network can effectively identify Rhizoma Angustifolia or Rhizoma Rhizoma, and improve the identification efficiency.

Description

technical field [0001] The invention relates to the field of traditional Chinese medicine identification, in particular to a neural network-based detection method for Nansha ginseng medicinal materials. Background technique [0002] Nansha ginseng is a plant of the Platycodonaceae Adenophora tetraphylla (Thunb.) Fisch. Adenophora stricta The dried root of Miq. Excavate in spring and autumn, remove fibrous roots, wash and scrape off rough skin while fresh, wash and dry. At present, there are many counterfeit medicinal materials of Nansha ginseng circulating on the market, including apricot leaf ginseng, Huanan ginseng, etc., the appearance of the medicinal materials has little difference, and there are few documents on the classification of different origins of Nansha ginseng. [0003] According to the Chinese Pharmacopoeia, Nansha ginseng has only two sources: Radix Radix et Rhizoma and Radix Rhizoma Radix. However, it is difficult to distinguish Radix Radix et Rhizoma...

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 Patents(China)
IPC IPC(8): G01N30/02G01N30/88G06N3/04
CPCG01N30/02G01N30/88G01N2030/8813G06N3/045
Inventor 罗宇琴梁慧潘礼业陈向东孙冬梅杨晓东王碧君魏梅程学仁
Owner GUANGDONG YIFANG PHARMA