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

Odor analysis method and device

An analysis method and technology of an analysis device, applied in the field of data analysis, can solve problems such as peak drift, analysis result deviation, feature deviation, etc., and achieve the effect of improving the accuracy rate

Active Publication Date: 2019-08-20
SHANGHAI UNIV
View PDF11 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is that the peak value of the odor analysis method in the prior art may be affected by factors such as temperature and humidity to produce a drift phenomenon, thereby causing deviations in the characteristics, resulting in the final There is a large deviation in the analysis results, or in the field of traditional Chinese medicine identification, using some chemical components that can be detected by the sensor, it is cumbersome and troublesome to query the corresponding drug type according to the chemical composition table

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
  • Odor analysis method and device
  • Odor analysis method and device
  • Odor analysis method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Such as figure 1 Shown, a kind of odor analysis method comprises the following steps:

[0050] Step 100, collect the gas to be tested, make the gas to be tested interact with the sensor to collect data, and obtain the original odor data collected by the sensor;

[0051] Step 200, according to the original odor data, input it into the trained convolutional neural network for analysis and processing, and obtain the classification result;

[0052] Step 300, displaying the classification result on a display device according to the classification result.

[0053] In this embodiment, the gas to be measured first passes through the gas collection equipment and reacts with the collection equipment. After the action is over, a series of discrete response values ​​are obtained, that is, the original odor data. The obtained original data is used as input and input to the In the trained CNN network, after analysis and processing, the final classification result is obtained. The ...

Embodiment 2

[0128] The disclosure of the present invention provides an odor analysis device, comprising:

[0129] The collection module is used to collect the gas to be tested, and make the gas to be tested interact with the sensor to collect data, so as to obtain the original odor data collected by the sensor;

[0130] The analysis module is used to input the trained convolutional neural network into the trained convolutional neural network for analysis and processing to obtain classification results according to the original odor data;

[0131] A display module, configured to display the classification result on a display device according to the classification result.

[0132] Further, it also includes

[0133] The distinguishing module is used to divide the original odor data into two parts, a training set and a test set.

[0134] Further, the acquisition module includes

[0135] Collating unit for collating each original odor data as x=[s 1 ,s 2 ,s 3 ,...,s d ], where s i For ...

Embodiment 3

[0143] Embodiment 3 of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the program, any one of the methods above is implemented.

[0144] The computer device in this embodiment includes: a processor, a memory, and a computer program stored in the memory and operable on the processor, such as a resource allocation program. When the processor executes the computer program, the steps in the above-mentioned embodiment of an odor analysis method are realized. Alternatively, when the processor executes the computer program, the functions of the modules / units in the above device embodiments are realized.

[0145] Exemplarily, the computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may...

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 an odor analysis method and device. The method comprises the following steps that: a to-be-measured gas is collected, the to-be-measured gas interacts with a sensor, and data are collected, so that original odor data collected by the sensor can be obtained; the original odor data are inputted into a trained convolutional neural network, so that the convolutional neural network performs analysis and processing on the original odor data, and a classification result is obtained; and the classification result is displayed on a display device according to the classificationresult. According to the odor analysis method and device disclosed by the invention, a deep learning method is adopted to automatically learn characteristics; when the network is trained, network parameters can be automatically adjusted, so that the types of characteristic extraction are diversified, and therefore, the accuracy of an analysis result can be improved; and a final analysis result ina chemical composition table is combined with actual use background, so that an odor analysis result with practical significance can be obtained.

Description

technical field [0001] The invention relates to the field of data analysis, in particular to an odor analysis method and device. Background technique [0002] Traditional gas analysis and identification methods usually process high-dimensional gas data through steps such as dimensionality reduction, feature extraction, and feature selection, and then complete the task of gas identification through classification, regression, or clustering, and give the gas to be measured. main ingredient. In traditional gas analysis, commonly used dimensionality reduction methods include principal component analysis, linear discriminant analysis, etc., and commonly used classification algorithms include support vector machines, random forests, etc. [0003] Tianjin University invented a portable liquor identification device based on electronic nose technology in patent ZL201410847791.1, which identifies liquor through manually designed features. In the invention, 10 relevant information on...

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): G01N31/00G06N3/04G06N3/08
CPCG01N31/00G06N3/084G06N3/045
Inventor 严壮志张瑶雯沈婷蒋皆恢胡俊炜
Owner SHANGHAI UNIV