Support vector machine wetland remote sensing classification method optimized by co-evolutionary algorithm

A support vector machine and co-evolution technology, applied in the field of support vector machine wetland remote sensing classification, can solve the problem that support vector machine and co-evolution algorithm have not yet appeared, achieve good execution efficiency and classification performance, improve evolution speed, low population diversity sexual effect

Active Publication Date: 2018-04-20
HARBIN NORMAL UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Zang Shuying, Zhang Ce, Zhang Lijuan, Zhang Yuhong. Genetic Algorithm-optimized Support Vector Machine for Wetland Remote Sensing Classification. Geographical Science [J] 2012, 32(4): 434-441 Proposed Genetic Algorithm-optimized Support Vector Machine for Remote Sensing Classification. The combination of support vector machine and co-evolutionary algorithm has not yet appeared in remote sensing classification research

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
  • Support vector machine wetland remote sensing classification method optimized by co-evolutionary algorithm
  • Support vector machine wetland remote sensing classification method optimized by co-evolutionary algorithm
  • Support vector machine wetland remote sensing classification method optimized by co-evolutionary algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0042] 1. Basic principle and performance analysis

[0043] 1.1 Support Vector Machine Classification Principle

[0044] The mechanism of support vector machine (SVM) is to find an optimal classification hyperplane that meets the classification requirements, so that the hyperplane can maximize the blank area on both sides of the hyperplane while ensuring the classification accuracy; For example, given a training sample set (x i ,y i ), i=1,...,l; x∈R n , y∈{+1,-1}, the hyperplane is denoted as (w x)+b=0, in order to make the classification face all samples correctly classified and have a classification interval, it is required to meet the following constraints:

[0045] the y i [(w·x i )+b]≥1 i=1, 2, ..., l (1)

[0046] In the above formula (1), w represents the normal vector of the hyperplane, and b represents the bias;

[0047]It can be calculated that the classification interval is 2 / ||w||, so the problem of constructing the optimal hyperplane is transformed into fin...

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

A support vector machine wetland remote sensing classification method optimized by a co-evolutionary algorithm belongs to the field of remote sensing technology. The method comprises the following steps: 1, individual coding mode; 2, calculate individual fitness function; 3, PSO-GA collaborative evolution algorithm: (1) initialization population and parameters; (2) PSO evolution strategy; (3) GA evolution strategy; (4) select offspring; (5) update the selection probability of the strategy. In this paper, the PSO-GA co-evolutionary algorithm is used to optimize the selection of the parameters of the SVM model. The algorithm combines PSO and GA to obtain the optimal parameters and high-precision classification as the design scheme, and the evolution strategy is selected probabilistically. The combination of the two evolution calculation methods not only ensures the global search ability to prevent falling into local optimum, but also improves the evolution speed.

Description

technical field [0001] The invention belongs to the technical field of remote sensing, and in particular relates to a support vector machine wetland remote sensing classification method optimized by a cooperative evolution algorithm. Background technique [0002] Support Vector Machine (SVM) is a new type of machine learning method based on statistical learning theory. This method is based on the principle of VC dimension and structural risk minimization in statistical learning theory, and converts linear inseparable problems into linearly separable problems with the help of kernel functions. problem, so that the problem is finally transformed into solving a convex quadratic programming problem, which overcomes the "curse of dimensionality" and "over-learning", and has outstanding advantages in small sample, nonlinear and high-dimensional pattern recognition, and has been obtained in many application fields It has a good effect and has become a research hotspot in the field ...

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): G06K9/62G06K9/00
CPCG06V20/13G06F18/2411G06F18/214
Inventor 于晓冬夏天
Owner HARBIN NORMAL 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