Hybrid Matrix Completion Model for Improved Images Recovery and Recommendation Systems

Matrix completion methods have been widely applied in images recovery and recommendation systems. Most of them are only based on the low-rank characteristics of matrices to predict the missing entries. However, these methods lack consideration of local information. To further improve the performance...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kai Xu, Ying Zhang, Zhurong Dong, Zhanyu Li, Bopeng Fang
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Matrix completion images recovery recommendation systems adaptive local filtering Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/59df01a50f12415ab26bdb8440bc89bf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:59df01a50f12415ab26bdb8440bc89bf
record_format	dspace
spelling	oai:doaj.org-article:59df01a50f12415ab26bdb8440bc89bf2021-11-18T00:03:45ZHybrid Matrix Completion Model for Improved Images Recovery and Recommendation Systems2169-353610.1109/ACCESS.2021.3125152https://doaj.org/article/59df01a50f12415ab26bdb8440bc89bf2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9599718/https://doaj.org/toc/2169-3536Matrix completion methods have been widely applied in images recovery and recommendation systems. Most of them are only based on the low-rank characteristics of matrices to predict the missing entries. However, these methods lack consideration of local information. To further improve the performance of matrix completion. In this paper, we propose a novel model based on matrix decompositions and matrix local information. Specifically, we update a number of rank-one matrices, which circumvented the rank estimation in matrix decomposition. And a penalty function is designed to punish singular values without introducing additional parameters. The local information component extracts similar information by an adaptive filter via convolution operation which kernel is obtained by the minimum variance. Finally, we integrate matrix decomposition and local information components via different weights. We apply the proposed method to real-world image datasets and recommendation system datasets. The experimental results demonstrate the proposed model has a lower error and better robustness than several competing matrix completion methods.Kai XuYing ZhangZhurong DongZhanyu LiBopeng FangIEEEarticleMatrix completionimages recoveryrecommendation systemsadaptive local filteringElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 149349-149359 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Matrix completion images recovery recommendation systems adaptive local filtering Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Matrix completion images recovery recommendation systems adaptive local filtering Electrical engineering. Electronics. Nuclear engineering TK1-9971 Kai Xu Ying Zhang Zhurong Dong Zhanyu Li Bopeng Fang Hybrid Matrix Completion Model for Improved Images Recovery and Recommendation Systems
description	Matrix completion methods have been widely applied in images recovery and recommendation systems. Most of them are only based on the low-rank characteristics of matrices to predict the missing entries. However, these methods lack consideration of local information. To further improve the performance of matrix completion. In this paper, we propose a novel model based on matrix decompositions and matrix local information. Specifically, we update a number of rank-one matrices, which circumvented the rank estimation in matrix decomposition. And a penalty function is designed to punish singular values without introducing additional parameters. The local information component extracts similar information by an adaptive filter via convolution operation which kernel is obtained by the minimum variance. Finally, we integrate matrix decomposition and local information components via different weights. We apply the proposed method to real-world image datasets and recommendation system datasets. The experimental results demonstrate the proposed model has a lower error and better robustness than several competing matrix completion methods.
format	article
author	Kai Xu Ying Zhang Zhurong Dong Zhanyu Li Bopeng Fang
author_facet	Kai Xu Ying Zhang Zhurong Dong Zhanyu Li Bopeng Fang
author_sort	Kai Xu
title	Hybrid Matrix Completion Model for Improved Images Recovery and Recommendation Systems
title_short	Hybrid Matrix Completion Model for Improved Images Recovery and Recommendation Systems
title_full	Hybrid Matrix Completion Model for Improved Images Recovery and Recommendation Systems
title_fullStr	Hybrid Matrix Completion Model for Improved Images Recovery and Recommendation Systems
title_full_unstemmed	Hybrid Matrix Completion Model for Improved Images Recovery and Recommendation Systems
title_sort	hybrid matrix completion model for improved images recovery and recommendation systems
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/59df01a50f12415ab26bdb8440bc89bf
work_keys_str_mv	AT kaixu hybridmatrixcompletionmodelforimprovedimagesrecoveryandrecommendationsystems AT yingzhang hybridmatrixcompletionmodelforimprovedimagesrecoveryandrecommendationsystems AT zhurongdong hybridmatrixcompletionmodelforimprovedimagesrecoveryandrecommendationsystems AT zhanyuli hybridmatrixcompletionmodelforimprovedimagesrecoveryandrecommendationsystems AT bopengfang hybridmatrixcompletionmodelforimprovedimagesrecoveryandrecommendationsystems
_version_	1718425226711138304

Hybrid Matrix Completion Model for Improved Images Recovery and Recommendation Systems

Ejemplares similares