Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Machine learning method for identifying origin of Wuyi rock tea automatically

A technology of machine learning and origin, applied in instruments, scientific instruments, material analysis through optical means, etc., can solve the problem that the detection data cannot represent the key information of origin traceability

Inactive Publication Date: 2017-04-12
CHINA JILIANG UNIV
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] The purpose of the present invention is to solve the problems that a single detection data cannot represent all the key information of origin traceability and the defects of traditional metrology methods, and provide a machine learning method that can automatically identify the origin of Wuyi rock tea. , stable isotopes, trace elements, amino acids, and electronic tongue data to identify the origin of Wuyi rock tea. ) Near-infrared characteristic spectrum data, stable isotope data, trace element data, amino acid, and electronic tongue data are fused together to establish an analysis model, and after extracting samples, use the model to objectively and accurately determine the origin of rock tea

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
  • Machine learning method for identifying origin of Wuyi rock tea automatically
  • Machine learning method for identifying origin of Wuyi rock tea automatically
  • Machine learning method for identifying origin of Wuyi rock tea automatically

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0080] A. Collect rock tea samples from different origins

[0081] The national standard (GB / T 18745-2006) stipulates the scope of geographical protection of Wuyi rock tea, that is, within the administrative division of Wuyishan City, Fujian Province, the present invention is located in Wuyi Street, Chong'an Street, Shangmei, and Xingxia in the Wuyi Rock Tea Geographical Indication Protection Area. Samples were collected in 11 administrative areas including Village, Wufu, Langu, Xinfeng Street, Yangzhuang, Xingtian, Xiamei, and Wutun, and 3 sampling points were randomly selected in each administrative area (respectively A, B, C to be marked), a total of 33 sampling points, the sampling range basically covers the main production areas, and each sampling point takes 15 samples (respectively marked with A-1, A-2...A-15), and obtained 495 samples of Wuyi rock tea in geographical indication protected areas, and other counties and cities in Fujian Province except Wuyishan City (Jian...

Embodiment 2

[0153] Adopt the modeling method identical with embodiment 1, data segmentation uses Kenstone segmentation procedure, with Monte Carlo interactive verification, set up neural network ELM, partial least squares (PLSDA), least squares support vector machine (LS-SVM) respectively In the model, the near-infrared data remains unchanged, and the stable isotopes, trace elements, amino acids, and electronic tongues are respectively classified according to hydrogen, oxygen, nitrogen, carbon, strontium, Cs, Cu, Ca, Rb, Sr, Ba, asparagine, proline, The model recognition rates of tryptophan, phosphoethanolamine, urea, valine, ZZ, BA, BB, CA, GA, HA, and JB spliced ​​in near-infrared data were 90.5%, 86.7%, and 78.9%, respectively.

Embodiment 3

[0155] Using the same modeling method as in Example 1, the data segmentation uses the Kenstone segmentation program, and uses the Monte Carlo interactive verification to establish the neural network ELM, PLSDA, and LS-SVM discriminant models respectively. The near-infrared data is unchanged, and stable isotopes and trace elements , amino acid, electronic tongue data according to hydrogen, oxygen, nitrogen, carbon, strontium, Cs, Cu, Ca, Rb, Sr, Ba, asparagine, proline, tryptophan, phosphoethanolamine, ZZ, BA, BB, After splicing CA, GA, HA, and JB into near-infrared data, the model recognition rates are 91.2%, 87.9%, and 82.3%, respectively.

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 a machine learning method for identifying origin of Wuyi rock tea automatically. The method combines five data types including near infrared, stable isotope, trace element, amino acid and electronic tongue and the like to establish a neural net ELM Wuyi rock tea origin analytic model. The present invention belongs to the technical field of geographical trademark product authenticity identification, and aims at solving the problem that a single test data type cannot represent all the key information of an origin, and different types of test data need to match when jointly used in a metrological method. The method is based on an ELM model with a machine learning function, and integrates five data types including the near infrared, stable isotope, trace element, animo acid and electronic tongue and the like. The ELM model combining all five data types has the highest identification rate which reaches 100.0%, andfar exceeds the identification results derived from a neural net comprising only a single data type, and the identification rate of blind samples can attain 100%, thus rendering the method with a promising application prospect.

Description

[0001] (1) Technical field [0002] The invention relates to a machine learning method that can automatically identify the origin of Wuyi rock tea. The method integrates near-infrared spectra, stable isotopes, trace elements, amino acids, and electronic tongue data to establish a neural network ELM identification model with deep learning functions, and serves as an identification model for Wuyi rock tea. The invention relates to a method for identifying a place of origin, which belongs to the technical field of authenticity identification of geographical indication products. [0003] (2) Background technology [0004] According to the definition of GB / T 17924-2008, a geographical indication product refers to the use of raw materials produced in a specific region and produced in a specific region according to traditional techniques. The quality, characteristics or reputation are essentially determined by the geographical characteristics of the region of origin , and products nam...

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): G01N21/359G01N21/3563G01N27/62G01N30/02G01N27/00
CPCG01N21/3563G01N21/359G01N27/00G01N27/62G01N30/02
Inventor 俞晓平叶子弘付贤树崔海峰张雅芬
Owner CHINA JILIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com