Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-view clustering method based on non-negative matrix factorization and partition adaptive fusion

A technology of non-negative matrix decomposition and clustering method, which is applied in the field of multi-view clustering based on non-negative matrix decomposition and partition adaptive fusion, which can solve the problems of destroying independence and unsatisfactory global clustering results.

Active Publication Date: 2020-05-22
ARMY ENG UNIV OF PLA
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method may destroy the independence of the original objects under different attributes, resulting in unsatisfactory global clustering results

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-view clustering method based on non-negative matrix factorization and partition adaptive fusion
  • Multi-view clustering method based on non-negative matrix factorization and partition adaptive fusion
  • Multi-view clustering method based on non-negative matrix factorization and partition adaptive fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The invention belongs to an unsupervised clustering method in a big data environment, and is an efficient multiplication update method.

[0040] The present invention introduces Shannon entropy regularization term. As an uncertainty measure, Shannon entropy is effectively used for clustering. When dividing uncertainty, it is generally believed that when the entropy reaches the maximum and there is no prior information, the division is optimal. On the other hand, when other information is available, it is expected that there is a trade-off between the indeterminate partition obtained from the available information and the partition obtained in the maximum entropy case.

[0041] The present invention will be further described below in conjunction with the accompanying drawings of the description.

[0042] In order to verify the effectiveness of the present invention, in this invention, an attempt is made to prove the effectiveness of the proposed multi-view clustering a...

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 multi-view clustering method based on non-negative matrix factorization and partition adaptive fusion. A new visual angle fusion strategy is provided for solving the problemof how to better realize inter-view learning of a multi-view clustering task, the strategy firstly sets a division for each visual angle, then a fusion weight matrix is obtained through adaptive learning to perform adaptive fusion on the division of each visual angle, and finally a global division result is obtained by using a visual angle integration method. The strategy is applied to a classicalFCM (Fuzzy Clustering Model) fuzzy clustering framework, and solving is conducted by adopting an ADMM (Alternating Direction Method of Multipliers). Compared with several related clustering algorithms, the method provided by the invention has better adaptability and clustering when processing multi-view clustering tasks.

Description

technical field [0001] The invention relates to the technical fields of data mining and pattern recognition and the fields of data analysis and artificial intelligence, in particular to a multi-view clustering method based on non-negative matrix decomposition and partition adaptive fusion. Background technique [0002] In recent years, Internet information technology has been rapidly developed and widely used in real life, resulting in explosive growth of information and data. In the process of describing some practical problems, the same thing can be described in different ways, from different angles or in different forms. Various descriptions are called multiple views of things, and data is called multi-view data [1]. Each individual view is sufficient to mine knowledge, and combining valuable information from multiple views can improve performance and quality. However, the main challenge is how to integrate independently compatible and complementary information provided...

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): G06K9/62G06F16/26
CPCG06F16/26G06F18/23213G06F18/214
Inventor 陶性留俞璐王晓莹姚艳艳
Owner ARMY ENG UNIV OF PLA