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

A Method of Optimizing Fuzzy Identification Vector Extraction for Vinegar Variety Identification by Electronic Nose

An optimal identification vector and electronic nose technology, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of high cost and pattern recognition algorithm affecting classification accuracy, etc., to improve classification accuracy and improve classification accuracy , the effect of easy classification

Active Publication Date: 2020-06-09
吉安集睿科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the current problems that the cost of vinegar classification is too high, and the selection of different pattern recognition algorithms will affect the classification accuracy, the present invention proposes a method of optimizing the extraction of fuzzy identification vectors for electronic nose identification of vinegar varieties to improve the accuracy of vinegar category classification. Rate

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 Optimizing Fuzzy Identification Vector Extraction for Vinegar Variety Identification by Electronic Nose
  • A Method of Optimizing Fuzzy Identification Vector Extraction for Vinegar Variety Identification by Electronic Nose
  • A Method of Optimizing Fuzzy Identification Vector Extraction for Vinegar Variety Identification by Electronic Nose

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] Step 1. Use the electronic nose to collect samples of different varieties of vinegar:

[0051] The electronic nose was energized, and the five types of vinegar were collected 51 times, a total of 255 times were collected, and 255 samples were obtained, and the experimental data collection results were saved. The total sample is a 255×10 data matrix, and the total sample is divided into training samples and test samples: the first 25 of the 51 samples of each type of vinegar are used as training samples, and the last 26 are used as test samples. The number of training samples is 125, each sample is a vector of 1×10, and a data matrix of 125×10 is obtained; the number of test samples is 130, and each sample is a vector of 1×10, and a data matrix of 130×10 is obtained.

[0052] Step 2. Optimizing the vinegar sample data:

[0053] 1. Randomly select b sensors from a sensor without sorting. situation. In this example, a takes 10, and b takes 8. There are 45 situations in...

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 method for identifying vinegar varieties with an electronic nose that optimizes fuzzy identification vector extraction. Several sensors are randomly selected from the sensors of the electronic nose, and the data corresponding to these sensors are extracted from the training samples as a new method. Training samples, calculate the class mean of the new training samples and the total mean of the new training samples, the inter-class scatter matrix and the intra-class scatter matrix of the new training samples, the traces of the inter-class scatter matrix and the trace of the intra-class scatter matrix, and the final The optimal value, the new training sample corresponding to the sensor selected when the optimal value is the largest is used as the optimal training sample, the identification information of the optimal training sample is extracted, the optimal identification vector set is obtained, and the optimal identification vector set is linearly transformed, The projection sample set is obtained, the projection sample set is classified, and the identification of vinegar varieties is completed. The invention reduces the dimension of data without losing main information, reduces the influence of noise, and improves the classification accuracy of vinegar varieties.

Description

technical field [0001] The invention relates to a method for identifying vinegar varieties, in particular to a method for identifying vinegar varieties by using an electronic nose. Background technique [0002] Vinegar is an essential condiment in family life. There are many types of vinegar on the market, and their flavors are different due to different places of origin, ingredients, and fermentation methods. Flavor is one of the important indicators of vinegar classification and one of the main factors of consumer acceptance. However, there are many vinegar products on the market. During the production process, the fermentation temperature, the depth of fermented grains, and the fermentation time are mostly controlled by the experience of the master workers, so it is easy to cause uneven quality of vinegar. Not one. For a long time, gas chromatography has been used to objectively measure odor, but gas chromatography has harsh requirements on the experimental environment ...

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): G06K9/62
CPCG06F18/24137G06F18/214
Inventor 武小红嵇港傅海军孙俊武斌田潇瑜戴春霞
Owner 吉安集睿科技有限公司