Identification method for producing area of Wuyi rock tea and with deep learning function
A deep learning and functional technology, applied in chemical machine learning, scientific instruments, chemical statistics, etc., can solve problems such as unable to represent origin traceability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0074] A. Collect rock tea samples from different origins
[0075] 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 marked), a total of 33 sampling points, the sampling range basically covers the main production areas, each sampling point sampling 15 copies (respectively marked with A-1, A-2...A-15), obtained 495 Wuyi rock tea samples from the Geographical Indication Protection Area, and other counties and cities in Fujian Province except Wuyishan City (Jianyang, Jia...
Embodiment 2
[0127] Adopt the same modeling method as embodiment 1, use Kenstone segmentation program for data segmentation, use K-fold interactive verification, set up neural network ELM, partial least squares PLSDA and least squares support vector machine LS-SVM model respectively, near infrared The data remains unchanged, and stable isotopes, trace elements, and electronic tongues are spliced according to hydrogen, oxygen, nitrogen, carbon, strontium, Cs, Cu, Ca, Rb, Sr, Ba, ZZ, BA, BB, CA, GA, HA, and JB, respectively After near-infrared data, its model recognition rate is 94.2%, 87.4%, 88.1%, respectively.
Embodiment 3
[0129] Adopt the same modeling method as embodiment 1, use Kenstone segmentation program for data segmentation, use K-fold interactive verification, set up neural network ELM, partial least squares PLSDA and least squares support vector machine LS-SVM model respectively, near infrared The data remains unchanged, and the stable isotopes, trace elements, and electronic tongues are spliced in the near-infrared data according to hydrogen, oxygen, nitrogen, carbon, strontium, Cs, Cu, Ca, Rb, ZZ, BA, BB, CA, GA, HA, and JB, respectively. After that, the model recognition rates were 98.1%, 88.6%, and 89.7%, respectively.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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