Electronic nose signal feature fusion method based on separability degree and dissimilarity degree

A signal feature and fusion method technology, applied in character and pattern recognition, instruments, computer parts and other directions, can solve the problems of electronic nose signal feature redundancy, biological optimization algorithm time-consuming, etc., to improve classification and recognition performance, improve classification recognition rate, avoiding time-consuming effects

Active Publication Date: 2016-11-16
SOUTHWEST UNIVERSITY
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application not only solves the redundancy problem among electronic nose signal features in the prior art, but also avoids the time-consuming technical problem of biological optimization algorithm by providing a method of fusion of electronic nose signal features based on separability and dissimilarity , and greatly improved the classification and recognition performance of the electronic nose

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
  • Electronic nose signal feature fusion method based on separability degree and dissimilarity degree
  • Electronic nose signal feature fusion method based on separability degree and dissimilarity degree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] An electronic nose signal feature fusion method based on separability and dissimilarity, characterized in that it includes the following steps:

[0040] S1: Perform feature extraction on the electronic nose signal to obtain the original pattern sample. The original feature matrix is: X = {X 1 ,X 2 ,...,X M }, where X j (j=1, 2,...,M) is a subset of the matrix X, M is the dimension of the original pattern samples, the total number of electronic nose signals is C, and the number of samples of the nth type is K n , N=1,2,...,C, the total number of samples The m-th dimension feature of the i-th sample of the nth type is X mn (i), where i=1,2,...,K n , M=1,2,...,M;

[0041] S2: Feature selection:

[0042] S21: Calculate the separability CS of each feature, select the feature with the largest separability as the optimal one-dimensional feature, and calculate the classification recognition rate of the feature;

[0043] The specific calculation method of separability is:

[0044] The me...

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 an electronic nose signal feature fusion method based on the separability degree and the dissimilarity degree and belongs to the technical field of electronic noise signal and information processing. The method comprises a step one of subjecting an electronic nose signal to feature extraction, a step two of performing feature selection and a step three of performing feature weighted fusion. The invention reserves classification information to the greatest degree while reducing dimensions and eliminating redundancy, and thus the classification identification rate is greatly improved, and the classification identification performance of an electronic nose is improved further.

Description

Technical field [0001] The invention relates to the technical field of electronic nose signal and information processing, in particular to an electronic nose signal feature fusion method based on separability and dissimilarity. Background technique [0002] As an intelligent device that imitates the biological olfactory system, the electronic nose can reliably and quickly realize the identification of simple or complex odors. Compared with the traditional gas chromatograph and other expensive gas analysis instruments, it is easy to operate, reliable and suitable for analysis results. On-site testing has been widely used in food, agriculture, medical, environmental testing and other fields. [0003] There are three main types of existing electronic nose signal feature fusion methods: 1. Use multiple types of sensors to form an array and acquire signals, and then perform feature extraction on these signals, such as the maximum value in the time domain, the maximum slope, the curve in...

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): G06K9/62G06K9/00
CPCG06F2218/12G06F2218/08G06F18/253
Inventor 彭超闫嘉段书凯王丽丹贾鹏飞
Owner SOUTHWEST UNIVERSITY
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