Wheat quality THz spectral classification method based on DS evidence theory

A technology for spectral classification and wheat quality, applied in the field of wheat quality detection, can solve the problems of large differences in the recognition rate of model classification, and achieve the effect of improving the recognition rate

Inactive Publication Date: 2017-05-31
HENAN UNIVERSITY OF TECHNOLOGY
View PDF1 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The recognition rate of normal wheat and germinated wheat is relatively high, while most of the misjudged samples are moldy wheat and insect-infested wheat, and the classification recognition rate of different models is quite different

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
  • Wheat quality THz spectral classification method based on DS evidence theory
  • Wheat quality THz spectral classification method based on DS evidence theory
  • Wheat quality THz spectral classification method based on DS evidence theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in further detail below, so that those skilled in the art can implement it with reference to the description.

[0025] The present invention provides a kind of wheat quality THz spectral classification method based on DS evidence theory, described method comprises:

[0026] Step 1, set up the wheat classification probability output for different quality wheat absorption spectrum: set up the absorption spectrum SVM classifier of the wheat sample of different quality, thereby calculate the training set of different quality wheat sample and the probability output of test set;

[0027] Step 2, establishing the wheat classification probability output for different quality wheat refractive index spectra: establishing the refractive index spectrum SVM classifier of different quality wheat samples, thereby calculating the probability output of different quality wheat sample training sets and test sets;

[0028] Step 3: Establish DS eviden...

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 discloses a wheat quality THz spectral classification method based on a DS evidence theory. The method comprises the following steps that: establishing a wheat classification probability output which aims at different-quality wheat absorption spectrums; establishing a wheat classification probability output which aims different-quality wheat refractive index spectrums; and establishing a DS evidence fusion rule. A multi-information fusion technology is adopted to fuse the adsorption spectrum information and the refractive index spectrum information of different-quality wheat samples, a wheat quality nondestructive testing model based on the multi-information fusion technology is established, and the DS evidence theory is adopted to fuse the output results of sub-classifiers and verify the output results for quality discriminatory analysis so as to lay a foundation for applying a THz technology to stored grain quality detection. By use of the method, an identification rate for different-quality wheat samples is improved.

Description

technical field [0001] The invention relates to a wheat quality detection method, in particular to a wheat quality THz spectral classification method based on DS evidence theory. Background technique [0002] Domestic and foreign reports on the quality detection methods of stored wheat mainly include: chemical methods (measurement of main components), electronic nose, machine vision, spectral detection (infrared spectroscopy) and other methods. limited ability. Due to its unique advantages such as low single-photon energy and spectral "fingerprint", THz is an effective non-contact measurement method for analyzing the internal composition information of substances. THz-TDS is currently the most representative THz technology and has important applications in the fields of biomedicine, material science, national defense security, and quality control. [0003] In terms of qualitative and quantitative analysis of substances by THz waves, many scholars have carried out the measu...

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): G06K9/62
CPCG06F18/2411G06F18/214
Inventor 葛宏义蒋玉英张元廉飞宇李智马海华李鹏鹏
Owner HENAN UNIVERSITY OF TECHNOLOGY
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap