Honey detection method using grid optimization-based selection of parameters of support vector machine classifier

A technology of support vector machine and parameter selection, which can be used in instruments, measuring devices, scientific instruments, etc., and can solve problems such as weakness

Active Publication Date: 2014-01-01
CHINA NAT INST OF STANDARDIZATION
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is still weak in differential information mining, which

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
  • Honey detection method using grid optimization-based selection of parameters of support vector machine classifier
  • Honey detection method using grid optimization-based selection of parameters of support vector machine classifier
  • Honey detection method using grid optimization-based selection of parameters of support vector machine classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019]

[0020] 1 About sample collection and preparation

[0021] In order to make the nectar source differences studied representative, according to the division of my country's geographical regions (Western China, South China, North China, East China, and Northeast China), 5 different nectar sources were selected as research samples, namely: 1) Rapeseed honey, collected from the western region 2) Lychee honey, collected from Nanning, Guangxi in South China; 3) Vitex honey, collected from Beijing Miyun and other places in North China; 4) Acacia honey, collected from Laiyang, Shandong in East China; 5) Linden tree honey is collected from Dunhua, Jilin, and Harbin, Heilongjiang, in northeast China. In order to ensure the authenticity and accuracy of the experimental samples and avoid the interference of commercial honey processing technology in the market, the samples were directly purchased from beekeepers through the Bee Research Institute of the Chinese Academy of Agricu...

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 provides a honey detection method using grid optimization-based selection of parameters of a support vector machine classifier. The invention is characterized in that the method of exhaustion is employed in grid optimization, all the points in a range are searched one by one according to certain step length in a pre-estimated value range to determine final optimal parameters, and exhaustive search is carried out on r and c in a range of 2<-4> to 2<10>, with 2 as a base number. According to the invention, when c is equal to 5.2780 and r is equal to 0.1088, highest discrimination accuracy, 96.25%, of samples in a training set is realized, and under such a condition, a model is established and a prediction set is used for inspection; final discrimination accuracy is 96.20%, and discrimination accuracy of the samples is 76/79, wherein honey of rape flowers is 23/23, basswood honey is 16/17, and acacia honey is 37/39.

Description

technical field [0001] This application relates to a honey detection method based on parameter selection of a support vector machine classifier based on grid optimization. Background technique [0002] my country's honey production ranks first in the world. In recent years, the output has maintained a rapid growth trend, from 252,000 tons in 2001 to 402,000 tons in 2009, accounting for more than 30% of the world's total output from nearly 20%. However, due to the drive of economic interests, the current honey market is seriously adulterated, resulting in adulterated honey accounting for 20% to 30% of the honey market. In some areas, adulterated and fake bee products account for about 50%, seriously damaging the interests of consumers and affecting The healthy development of the honey industry and the fight against foreign exchange earnings from export trade. [0003] Due to the lack of detection methods, it is difficult to crack down on adulteration. The fundamental reasons...

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
IPC IPC(8): G01N27/00
Inventor 史波林刘宁晶赵镭支瑞聪汪厚银裴高璞张璐璐解楠李烜
Owner CHINA NAT INST OF STANDARDIZATION
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