Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for acquiring ratio of total sugar to reducing sugar of tobacco based on support vector machine

A technology of support vector machine and acquisition method, applied in the field of tobacco sample analysis and testing, can solve the problems of high technical level requirements, poor precision, time-consuming and labor-intensive, etc., and achieve the effects of comprehensive and accurate data, simple model and low cost

Inactive Publication Date: 2017-09-01
上海帆阳信息科技有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditionally, the method for determining the content of sugar components in tobacco is alcohol extraction-copper reduction-potassium permanganate back titration. This method is very cumbersome to operate, time-consuming and labor-intensive, requires high technical level of personnel, and has low precision. it is good

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
  • Method for acquiring ratio of total sugar to reducing sugar of tobacco based on support vector machine
  • Method for acquiring ratio of total sugar to reducing sugar of tobacco based on support vector machine
  • Method for acquiring ratio of total sugar to reducing sugar of tobacco based on support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] Example 1: The modeling results of the support vector machine model of the ratio of two sugars in 114 tobacco leaves

[0085] Such as figure 2 As shown, using the support vector machine algorithm to perform regression modeling on the preprocessed tobacco electronic nose data, the electronic nose support vector machine prediction model for the ratio of two sugars in tobacco was established. The correlation coefficient between the calculated value of the ratio of two sugars and the experimental detection value was 0.904, The average relative error is 3.16%.

Embodiment 2

[0086] Embodiment 2: The prediction result of two sugar ratios to 56 new tobacco samples

[0087] Such as image 3 As shown, the new 56 tobacco samples were predicted by using the established support vector machine model of the ratio of two sugars in tobacco leaves, and good prediction results were obtained. The correlation coefficient between the calculated value and the experimentally detected value of the ratio of two sugars was 0.893, and the average relative error was 4.19%.

[0088] In recent years, electronic nose technology has been paid attention to due to its advantages of simplicity, rapidity, low cost, no pollution, non-destructive sample and simultaneous determination of multiple components. And there is no report on the application of electronic nose technology to determine the ratio of two sugars in tobacco. Therefore, the present invention relates to a method for detecting the ratio of two sugars in tobacco leaves based on tobacco leaf electronic nose technol...

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 method for acquiring ratio of total sugar to reducing sugar of tobacco based on a support vector machine, comprising the following steps: 1) acquiring various known tobacco samples, pre-treating and scanning through an electronic nose so as to obtain electronic nose data of each known tobacco sample, and acquiring each tobacco's corresponding data of ratio of total sugar to reducing sugar; 2) carrying out dimensionality reduction on the electronic nose data by a principal component analysis method, and acquiring types and data of multiple principal components of the known tobacco samples; 3) establishing a prediction model of tobacco ratio of total sugar to reducing sugar by support vector machine regression algorithm according to the types and data of multiple principal components of the known tobacco samples; and 4) acquiring the ratio of total sugar to reducing sugar of tobacco varieties to be detected according to the prediction model of the tobacco ratio of total sugar to reducing sugar and the principal components data of tobacco varieties to be detected. In comparison with the prior art, the method of the invention is simple and fast and has advantages of low cost, complete and accurate data, no pollution, simple testing and the like.

Description

technical field [0001] The invention relates to the technical field of analysis and testing of tobacco samples, in particular to a support vector machine-based method for obtaining the ratio of two sugars in tobacco leaves. Background technique [0002] The intrinsic quality of tobacco leaves is affected by many natural factors such as climate environment, planting area and other factors. The content of various chemical components in tobacco leaves is complex, and various chemical components in tobacco such as sugars, phenols, nitrogen heterocycles, nicotine, etc. will vary with the growing geographical environment and climatic conditions. The content of these chemical components is not only related to the quality of tobacco, but also affects the taste of tobacco. [0003] Sugar is one of the important macronutrient elements in the growth of tobacco leaves. It plays a pivotal role in the production of flue-cured tobacco and is an important factor affecting the quality of to...

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): G01N21/3563G01N1/28
CPCG01N1/286G01N21/3563G01N2021/3572
Inventor 刘太昂刘太行刘振昌朱峰周晶晶
Owner 上海帆阳信息科技有限公司