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

Multi-label AdaBoost integration method based on label correlation

An integration method and multi-label technology, applied in the field of multi-label AdaBoost integration, can solve the problem that the label correlation information cannot promote the second-step operation, etc., and achieve the effect of simple construction method, easy implementation, and improved efficiency

Inactive Publication Date: 2016-02-10
CAS OF CHENGDU INFORMATION TECH CO LTD
View PDF6 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, splitting the two steps in this way results in label correlation information that does not facilitate the second step

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
  • Multi-label AdaBoost integration method based on label correlation
  • Multi-label AdaBoost integration method based on label correlation
  • Multi-label AdaBoost integration method based on label correlation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] A multi-label AdaBoost ensemble method based on label correlation, such as figure 1 shown, including the following steps:

[0033] Step 1. Obtain training sample set X={(x 1 ,Y 1 ),...,(x m ,Y m )}, x i =(x i1 ,...x id )∈R d , indicating that the sample space has d attributes, Y i is the sample x i label set, if l∈Y i , then Y i (l)=1, otherwise Yi (l)=-1.

[0034] Step 2. Determine the type of problem. If it is a multi-classification problem, go to step 4; if it is a multi-label classification problem, go to step 3;

[0035] Step 3. Use cosine similarity to calculate the label correlation matrix R and the fuzzy label matrix

[0036] S31. Obtain the original label matrix W=(W(i,l)) m×K , where, if l∈Y i , then W(i,l)=1, otherwise W(i,l)=0;

[0037] S32. Order Calculate the label correlation matrix R=(R(l 1 , l 2 )) m×K ,in, If R(l 1 , l 2 )>thresh1 means label l 1 and l 2 is the relevant label, otherwise the label l 1 and l 2 irrelevant. ...

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 present invention discloses a multi-label AdaBoost integration method based on a label correlation. A stump decision tree method based on a sample weight is used as a weak classifier; an output of the weak classifier is confidence of a sample label; the confidence size closely depends on the sample weight; and the construction method is simple and efficient. According to the present invention, aiming at the mulit-classification problem, the similarity between labels is judged according to a classification result and is fused into the iterative training of a multi-label AdaBoost algorithm; the label correlation analysis is merged into training of a classification model, the label correlation analysis and training of the classification model are mutually promoted and mutually influenced, and finally, the performance of a strong classifier is promoted. Aiming at the multi-label classification problem, a cosine similarity is adopted to calculate a label correlation matrix, an original label is converted to a fuzzy label, and a fuzzy label matrix and classifier model training are combined. The method disclosed by the present invention is easy to implement, the efficiency of a multi-label classification system can be improved, and the method has a better classification effect.

Description

technical field [0001] The invention relates to a multi-label AdaBoost integration method based on label correlation. Background technique [0002] Compared with binary classification problems, multi-label classification problems are more in line with the real world. In multi-classification problems, an example has only one label, such as digit recognition problems. In multi-label classification problems, an example may have multiple different labels at the same time, for example, an image may have multiple semantics. [0003] Schapire et al. introduced confidence in the article "Improved boosting algorithms using confidence-rated predictions" (Machine Learning, 1999, 37(3): 297-336) in 1999, and extended the binary classification AdaBoost algorithm to multi-label classification. Jiang Yunliang and others proposed an ELM-based multi-class AdaBoost ensemble learning method in the patent application with the application number CN201510036010.5, which can be directly applied ...

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
CPCG06F18/24
Inventor 王莉莉付忠良姚宇纪祥虎张丹普
Owner CAS OF CHENGDU INFORMATION TECH CO LTD
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