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

A method of extreme learning machine spectrum model to judge the origin of fresh leaves of Enshi Yulu tea

A technology of extreme learning machines and fresh tea leaves, applied in scientific instruments, material analysis through optical means, instruments, etc., can solve the problems of reducing model prediction effect, unfavorable model robustness, long modeling time, etc., to improve modeling Rate and forecast effects, objective forecasts, effects of simplified model structure

Active Publication Date: 2022-04-08
INST OF FRUIT & TEA HUBEI ACAD OF AGRI SCI
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Chinese patent (publication number CN 106568741A) discloses a method for quickly determining the origin of fresh tea leaves by near-infrared spectroscopy. This method preliminarily realizes the rapid identification of fresh leaves from different origins. Component analysis, and then use the principal component as the input value to establish an artificial neural network prediction model of fresh leaf origin with multiple information transmission methods to determine the origin of fresh leaves. Because the characteristic spectral range of fresh leaves and noise information are not screened during modeling, it is easy to cause excessive The fitting phenomenon is not conducive to the robustness of the model. Moreover, there are a lot of interference information and group frequency and multiplier information between the sample spectra, which will inevitably reduce the prediction effect of the model, and the modeling time is longer

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
  • A method of extreme learning machine spectrum model to judge the origin of fresh leaves of Enshi Yulu tea
  • A method of extreme learning machine spectrum model to judge the origin of fresh leaves of Enshi Yulu tea
  • A method of extreme learning machine spectrum model to judge the origin of fresh leaves of Enshi Yulu tea

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0036] A method of extreme learning machine spectrum model to distinguish the origin of fresh leaves of Enshi Yulu tea. It scans and obtains the near-infrared spectra of fresh tea leaves samples from different origins, and then preprocesses the spectra of the samples to remove noise information, and then converts the spectra of the samples into pairs The data points are saved in the excel table; then the spectral data are divided into 20 spectral sub-intervals, and the ant colony algorithm is used to accurately screen the spectral information sub-interval bands reflecting the origin of fresh leaves; finally, the best spectral information sub-interval information is input In the extreme learning machine algorithm, by continuously and repeatedly optimizing the number of neurons and activation functions of the extreme learning machine, th...

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

A method for identifying the origin of fresh leaves of Enshi Yulu tea with an extreme learning machine spectral model, which relates to the field of agricultural product origin identification technology, and is characterized in that: the near-infrared spectra of fresh tea leaf samples from different origins are obtained by scanning, and then the sample spectra are preprocessed to remove noise After information, the sample spectrum is converted into paired data points, and then the spectral data are divided into 20 spectral sub-intervals, and the ant colony algorithm is used to screen the spectral information sub-interval bands reflecting the origin of fresh leaves; finally, the best spectral information The subinterval information is input into the extreme learning machine algorithm, and the extreme learning machine spectral model is established to predict the origin of fresh leaf samples. The invention realizes the rapid and accurate prediction of the origin of the fresh leaves of Enshi Yulu tea.

Description

technical field [0001] The invention relates to the technical field of identifying the origin of agricultural products, in particular to a method for quickly identifying the origin of fresh leaves of Enshi Yulu tea. Background technique [0002] Enshi Yulu is a famous steamed green tea in my country, and it is also a product protected by the National Geographical Indication. It is required that the fresh tea leaves processed must be collected from its protected areas. The protected areas are mainly Baiyangping Township, Tunbao Township and Sunhe Township in Enshi City. . Due to the huge market influence of the Enshi Yulu brand, tea farmers in surrounding tea areas are driven by interests, often pick fresh tea leaves from non-protected areas and pretend to be fresh leaves from protected areas, and sell them to Enshi Yulu tea processing factories at a higher price To earn extra benefits, when purchasing fresh leaves, tea purchasers often use their own feelings and work experie...

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): G01N21/359
CPCG01N21/359
Inventor 王胜鹏高士伟滕靖叶飞郑琳桂安辉
Owner INST OF FRUIT & TEA HUBEI ACAD OF AGRI SCI
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