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

Data mining method of electronic noses based on Wayne prediction

A data mining and electronic nose technology, which is applied in the fields of electrical digital data processing, special data processing applications, instruments, etc., can solve problems such as lack of information for subsequent decision-making, failure to provide probability intervals of predicted results, etc.

Active Publication Date: 2015-11-25
逻腾(台州)科技有限公司
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This scheme cannot provide the probability interval for the correct prediction result, and lacks necessary information for subsequent decision-making

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
  • Data mining method of electronic noses based on Wayne prediction
  • Data mining method of electronic noses based on Wayne prediction
  • Data mining method of electronic noses based on Wayne prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] Example: The electronic nose data used in this example were collected from 5 kinds of ginseng samples, namely Chinese red ginseng from Ji’an, Chinese red ginseng from Fusong, Korean ginseng from Ji’an, Chinese white ginseng from Ji’an and Fusong ginseng. Pine Chinese white ginseng.

[0035] Data collection: Five kinds of ginseng were crushed into powders with particle diameter less than 0.5mm. For each test, take 5g of sample and put it into a 100ml glass bottle. After putting the glass bottle in a 50°C incubator for 30 minutes, take 5ml of top air for testing. Each type of ginseng was tested 35 times, and a total of 175 sets of data were obtained.

[0036] Such as figure 1 As shown, this embodiment adopts the following technical solution to process the collected electronic nose signal, and the steps are as follows:

[0037] Step 1: According to 175 sets of data collected by 16 sensors, the original sample matrix M is expressed as

[0038] M ...

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 data mining method of an electronic nose based on Wayne prediction. Concretely, the data mining method comprises following steps of: firstly, carrying out feature extraction of original data in order to generate data sets of feature space; secondly, establishing a Wayne prediction algorithm framework and selecting a support vector machine and a k average clustering ensemble algorithm as a classifier in order to perform mode recognition; assuming that test samples are of a category y, forming data sets by test samples and training samples and utilizing a division method to model and predict all samples; traversing all y values in order to obtain a probability prediction matrix; and giving prediction types of all predicted samples and the probability interval for prediction correction. By adoption of the above scheme, the data mining method of the electronic noses based on Wayne prediction has following beneficial effects: the defect that a conventional pattern recognition algorithm can only predict types of samples is overcome; types of samples are predicted while an accurate prediction range is given in order to provide more effective information to a decision; and the data mining method of electronic nose based on Wayne prediction is suitable for processing of data of all the electronic noses.

Description

technical field [0001] The invention relates to electronic nose data processing, in particular to an electronic nose data mining method based on Wayne prediction. Background technique [0002] The electronic nose is a new type of bionic detection instrument that simulates the working principle of biological smell. It uses a sensor array composed of several non-specific gas sensors to accurately detect and distinguish target gases, and has the advantages of rapid identification, easy operation, strong objectivity, high reliability and low cost. Electronic noses have been widely used in environmental monitoring, food quality assessment, medical diagnosis and other research. [0003] Data mining is an important part of the development of the electronic nose. Traditional data mining pays more attention to data preprocessing, feature extraction, feature optimization, and classifier design. Traditional classifiers such as linear discriminant analysis (LDA) and support vector mac...

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): G06F19/24
Inventor 王酉苗加成李光
Owner 逻腾(台州)科技有限公司