Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Wuyi rock tea production place identification method based on deep learning

A deep learning, origin technology, applied in scientific instruments, character and pattern recognition, material analysis by optical means, etc., can solve the problem that the detection data cannot represent all the key information of origin traceability.

Pending Publication Date: 2017-04-12
CHINA JILIANG UNIV
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to solve the problem that a single type of detection data cannot represent all the key information of origin traceability, and also solve the problems of joint use of different types of detection data in metrology methods, analysis of existing data matching, etc., and provide a stable isotope Based on the neural network model of deep learning, the method integrates the stable isotopes, trace elements and electronic tongue of rock tea in and outside the origin of geographical indications, and establishes an analysis method. 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
  • Wuyi rock tea production place identification method based on deep learning
  • Wuyi rock tea production place identification method based on deep learning
  • Wuyi rock tea production place identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] A. Collect rock tea samples from different origins

[0076] 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 of Village, Wufu, Langu, Xinfeng Street, Yangzhuang, Xingtian, Xiamei, and Wutun, and 3 sampling points were randomly selected in each administrative area (in the order of A, B, C marked), a total of 33 sampling points, the sampling range basically covers the main production areas, each sampling point took 15 samples (marked with A-1, A-2...A-15), and obtained 495 copies Wuyi rock tea samples in the geographical indication protected area, and other counties and cities in Fujian Province except Wuyishan City (Jianyang, Jianou, Zhangzh...

Embodiment 2

[0131] Adopt the modeling method identical with embodiment 1, data segmentation uses Duplex segmentation procedure, with Monte Carlo interactive verification, set up neural network ELM, partial least squares (PLSDA), least squares support vector machine (LS-SVM) respectively Model, stable isotope (hydrogen, oxygen, nitrogen, carbon, strontium), trace elements (Cs, Cu, Ca, Rb, Sr, Ba, Mg, Mn, Ti, Cr, Co, Ni, Zn, Cd), electronic tongue (ZZ, BA, BB, CA, GA, HA, JB) data were spliced ​​together in the above order, and the model recognition rates were 89.5%, 86.3%, and 78.6%, respectively.

Embodiment 3

[0133] Adopt the modeling method identical with embodiment 1, data segmentation uses Duplex segmentation procedure, with Monte Carlo interactive verification, set up neural network ELM, partial least squares (PLSDA), least squares support vector machine (LS-SVM) respectively Model, stable isotope (hydrogen, oxygen, nitrogen, carbon), trace elements (Cs, Cu, Ca, Rb, Sr, Ba, Mg, Mn, Ti, Cr, Co, Ni, Zn, Cd), electronic tongue (ZZ , BA, BB, CA, GA, HA, JB) spliced ​​together according to the above sequence, the model recognition rates are 90.5%, 86.7%, 78.9% 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 Wuyi rock tea production place identification method based on deep learning, and belongs to the technical field of authenticity identification of geographical indication products. The method aims at solving the problems that a single kind of detection data can not represent complete key information about production place tracing, and different kinds of detection data are not matched when used in combination in a metrological method. According to the method, based on a neural network ELM model with a deep learning function, an ELM analysis model is established for stable isotope data, microelement data, electronic tongue data and fused data of the three kinds of data of rock tea from different production places with the same method; after sample extraction, the production places of the rock tea are subjectively and accurately judged with the model. The model established with the fused data of the three kinds of data has the highest identification rate which reaches 100.0% and is far higher than that of the discrimination result of a neural network model established with a single kind of data; besides, the identification rate on blind samples reaches 100%. The method has good application prospects and can serve as a technical method for tracing identification of Wuyi rock tea production places.

Description

[0001] (1) Technical field [0002] The invention relates to a method for identifying the origin of Wuyi rock tea based on deep learning. The method involves stable isotopes, trace elements and characteristic data of the origin of electronic tongues, and belongs to the technical field of authenticity identification of geographical indication products. [0003] (2) Background technology [0004] Geographical indication products refer to products whose quality, reputation or other characteristics are essentially determined by the natural and human factors of the place of origin, and which are named after examination and approval with geographical names. Tea is a typical geographical indication protected product, and its quality and taste are closely related to the geographical conditions, climate factors, environment and other factors of the place of origin. Wuyi rock tea is one of the representative tea products. [0005] At present, domestic and foreign finished tea origin iden...

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): G06K9/62G06N3/02G01N21/31G01N27/00G01N27/62
CPCG06N3/02G01N21/3103G01N27/00G01N27/62G06F18/2411G06F18/214
Inventor 付贤树叶子弘俞晓平崔海峰张雅芬
Owner CHINA JILIANG UNIV
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
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