Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Local and global consistence classifying method based on sparse decomposition of figure 10

A technology of sparse decomposition and classification method, applied in the field of semi-supervised classification based on graph, which can solve the problems of large amount of calculation and inapplicability to obtain the most similar nodes of the graph, and achieve the effect of improving the generalization ability and classification accuracy.

Inactive Publication Date: 2012-06-20
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this process is not suitable for obtaining the most similar nodes of the graph, and because the basis tracking

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
  • Local and global consistence classifying method based on sparse decomposition of figure 10
  • Local and global consistence classifying method based on sparse decomposition of figure 10
  • Local and global consistence classifying method based on sparse decomposition of figure 10

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0037] Step 1: Sparse decomposition l 0 graph construction

[0038] Step a: Use the KMEANS clustering algorithm to divide the entire data X to be classified into k subsets, where k is the number of categories;

[0039] Step b: Define an n×n adjacency matrix W, whose elements are initialized to 0, and n is the total number of data to be classified;

[0040] Step c: Take the i-th data x to be classified i For the signal to be decomposed, the sparse decomposition dictionary D i by x i The cluster subsets to which it belongs, x i not included in D i Among them, 1≤i≤n, n is the total number of data to be classified;

[0041] Step d: The preset maximum number of iterations is T=5, and the iteration termination error is ε stop =0.001, the current iteration number t is initialized to 0, and the decomposition signal x i , based on the dictionary D i use

[0042...

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 relates to a local and global consistence classifying method based on sparse decomposition of a figure 10. Sparse decomposition is thoroughly used for effectively capturing the substantive characteristics of a signal, the characteristics of an interior structure and a greedy selection principle of matching pursuit; and an adjoining structure and a weight value of the figure 10 are determined according to a sparse decomposition coefficient and are applied to the local and global consistence classifying method. Indicated by an experimental result, a better classifying result is obtained in the local and global consistence classifying method compared with a traditional figure composition method and a 11 figure composition method.

Description

technical field [0001] The present invention relates to a method based on sparse decomposition l 0 The invention provides a local global consistency classification method for graphs, which belongs to a graph-based semi-supervised classification method. Background technique [0002] In recent years, semi-supervised learning using a small amount of labeled data and a large amount of unlabeled data has been deeply studied. This method can improve the performance of the classifier while reducing the cost of manual labeling. Its research results have been widely used in web page retrieval and image classification. and other fields. Existing semi-supervised learning methods include: Self-training algorithm, Co-training algorithm, semi-supervised SVM, and graph-based semi-supervised classification methods. [0003] Graph-based semi-supervised learning methods usually define a graph first. The nodes on the graph are a collection of labeled and unlabeled data. The weight of the edg...

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): G06K9/62
Inventor 李映张晓洁
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com