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

Clustering fusion method based on optimized cluster correlation matrix

A technology of correlation matrix and fusion method, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems affecting the accuracy of clustering fusion and discreteness, so as to eliminate discreteness and sparsity, improve accuracy, Effects that improve accuracy and precision

Inactive Publication Date: 2017-07-28
NANJING UNIV OF INFORMATION SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the general binary cluster correlation matrix is ​​sparse and discrete, either 0 or 1, which obviously affects the accuracy of cluster fusion

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
  • Clustering fusion method based on optimized cluster correlation matrix
  • Clustering fusion method based on optimized cluster correlation matrix

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Below in conjunction with accompanying drawing, the implementation of technical scheme is described in further detail:

[0021] The cluster fusion method based on the optimized cluster correlation matrix according to the present invention will be further described in detail in conjunction with the flow chart and the implementation case.

[0022] In this implementation case, the clustering fusion algorithm is improved by optimizing the general binary cluster correlation matrix, thereby improving the accuracy of the algorithm. Such as figure 1 As shown, this method includes the following steps:

[0023] Step 10, use the K-means algorithm to select different initial clustering centers each time or set different K value parameters, for a set X with N D-dimensional feature data ND Carry out M times of clustering, and finally get the cluster member set Π={Π 1 ,Π 2 ,…Π M}.

[0024] Step 20, according to the cluster member set obtained in step 10, calculate the cluster-to...

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 clustering fusion method based on an optimized cluster correlation matrix, which is mainly based on the sparseness and discreteness characteristics of a general binary cluster correlation matrix to optimize the matrix. Based on M clustering members that are obtained, the relationship between clusters among the clustering members, the relationship between clusters in the clustering members and the stability of the clusters are calculated. The relationship between the cluster where data are located and other clusters represents the probability that the data appear in the other clusters. The discreteness and sparseness of a binary cluster correlation matrix is improved to reduce the occurrence of 0 value. Meanwhile, the stability of the clusters is increased to optimize a basic binary cluster correlation matrix, so as to make better use of the characteristics of the clustering members and improve the accuracy and precision of clustering fusion.

Description

technical field [0001] The invention belongs to the field of data mining, and specifically relates to a cluster fusion method for optimizing a binary cluster correlation matrix by using the relationship between cluster members and the stability of the clusters. Background technique [0002] In recent decades, with the rapid development of science and technology in the information age, data storage technology and data acquisition technology have also been rapidly improved. As a result, various types of data have accumulated massively, and the phenomenon of "information explosion and lack of knowledge" has emerged. How to extract useful knowledge from massive data is currently facing a huge challenge. For the term data mining, there is not yet a complete definition. The definition we recommend is Han Jiawei (Han Jiawei, Campbell. Data Mining Concept and Technology (2nd Edition of the original book) (Computer Science Series) [M]. Mechanical Industry Publishing Society, 2008.)...

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): G06K9/62
CPCG06F18/23213G06F18/25
Inventor 徐占洋郑克长周成兵
Owner NANJING UNIV OF INFORMATION SCI & TECH
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