Tensor mutual information and its application

Huang, ML; Lu, L; Ren, X; Cui, C; Luo, Y

Tensor mutual information and its application

Huang, ML

Lu, L Ren, X Cui, C Luo, Y

Permalink

Publisher:: Wiley & Sons, Ltd
Publication Type:: Journal Article
Citation:: Concurrency and Computation: Practice and Experience, 2020, 2020 pp. 1 - 10 (10)
Issue Date:: 2020-02-20

Closed Access

	Filename	Description	Size
	Tensor+mutual+information+and+its+applications.pdf	Published Version	644.54 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Huang, ML https://orcid.org/0000-0002-6896-6480	en_US
dc.contributor.author	Lu, L	en_US
dc.contributor.author	Ren, X	en_US
dc.contributor.author	Cui, C	en_US
dc.contributor.author	Luo, Y	en_US
dc.date.accessioned	2020-03-22T23:58:43Z
dc.date.available	2020-03-22T23:58:43Z
dc.date.issued	2020-02-20	en_US
dc.identifier.citation	Concurrency and Computation: Practice and Experience, 2020, 2020 pp. 1 - 10 (10)	en_US
dc.identifier.uri	http://hdl.handle.net/10453/139469
dc.description.abstract	Correlation analysis has long been a question of great interest in measuring the relationship among different variables and has been applied in many fields, such as dimension reduction, classification, and so on. However, current methods of correlation analysis take into account the linear relationship between multiple variables and only few works on nonlinear interaction of two variables have been considered. In this article, we first present a nonlinear analysis method of multiple (two or more) variables based on mutual information for tensor analysis (MITA). In addition, we extend the mutual‐information matrix analysis directly to MITA and show the multivariable mutual information formula based on Venn diagram. Experiments on multiview dimension reduction, including attacking internet traffic prediction, advertisement classification, and biometric structure prediction illustrate the effectiveness of the proposed method, especially in the case of low‐dimensional subspace.	en_US
dc.publisher	Wiley & Sons, Ltd	en_US
dc.relation.ispartof	Concurrency and Computation: Practice and Experience	en_US
dc.relation.isbasedon	10.1002/cpe.5686	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Distributed Computing	en_US
dc.title	Tensor mutual information and its application	en_US
dc.type	Journal Article
utslib.citation.volume	2020	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0803 Computer Software	en_US
utslib.for	0805 Distributed Computing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - INEXT - Innovation in IT Services and Applications
utslib.copyright.status	closed_access	*
pubs.consider-herdc	true	en_US
pubs.volume	2020	en_US

Abstract:

Correlation analysis has long been a question of great interest in measuring the relationship among different variables and has been applied in many fields, such as dimension reduction, classification, and so on. However, current methods of correlation analysis take into account the linear relationship between multiple variables and only few works on nonlinear interaction of two variables have been considered. In this article, we first present a nonlinear analysis method of multiple (two or more) variables based on mutual information for tensor analysis (MITA). In addition, we extend the mutual‐information matrix analysis directly to MITA and show the multivariable mutual information formula based on Venn diagram. Experiments on multiview dimension reduction, including attacking internet traffic prediction, advertisement classification, and biometric structure prediction illustrate the effectiveness of the proposed method, especially in the case of low‐dimensional subspace.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/139469