Recovery of block-structured sparse signal using block-sparse adaptive algorithms via dynamic grouping

Chen Ye, Guan Gui, Li Xu, Tomoaki Ohtsuki

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

A key point for the recovery of a block-sparse signal is how to treat the different sparsity distributed on the different parts of the considered signal. It has been shown recently that grouping the signal, i.e., partitioning the original signal into different groups or segments, and conducting the recovery for these groups separately provides an effective method to deal with the block-structured sparsity and can generate much better performance than the conventional sparse signal recovery (SSR) algorithms. In order to further improve the recovery performance, instead of the fixed grouping method used in the recent results, a novel dynamic grouping method will be first proposed in this paper, which classifies the segments due to the different levels of sparsity in a dynamic way. Then, by incorporating this technique into the block version of adaptive SSR algorithms. we developed recently, i.e., the block zero-attracting least-mean-square (BZA-LMS) algorithm and the block ℓ0-norm LMS (B ℓ0-LMS) algorithm, the corresponding new algorithms, i.e., the BZA-LMS-D and B ℓ0-LMS-D algorithms, will be established. The performance superiorities and the robustness against different block-sparsity and/or noise interference for the new algorithms based on dynamic grouping will be demonstrated by both analytic discussions and numerical simulations for a variety of scenarios.

Original languageEnglish
Article number8476546
Pages (from-to)56069-56083
Number of pages15
JournalIEEE Access
Volume6
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Adaptive algorithms
Recovery
Computer simulation

Keywords

  • Adaptive filter
  • Block-sparsity
  • Compressive sensing
  • Sparse constraint

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Recovery of block-structured sparse signal using block-sparse adaptive algorithms via dynamic grouping. / Ye, Chen; Gui, Guan; Xu, Li; Ohtsuki, Tomoaki.

In: IEEE Access, Vol. 6, 8476546, 01.01.2018, p. 56069-56083.

Research output: Contribution to journalArticle

@article{a12e23ed7f274bdb8c6a90c37d470767,
title = "Recovery of block-structured sparse signal using block-sparse adaptive algorithms via dynamic grouping",
abstract = "A key point for the recovery of a block-sparse signal is how to treat the different sparsity distributed on the different parts of the considered signal. It has been shown recently that grouping the signal, i.e., partitioning the original signal into different groups or segments, and conducting the recovery for these groups separately provides an effective method to deal with the block-structured sparsity and can generate much better performance than the conventional sparse signal recovery (SSR) algorithms. In order to further improve the recovery performance, instead of the fixed grouping method used in the recent results, a novel dynamic grouping method will be first proposed in this paper, which classifies the segments due to the different levels of sparsity in a dynamic way. Then, by incorporating this technique into the block version of adaptive SSR algorithms. we developed recently, i.e., the block zero-attracting least-mean-square (BZA-LMS) algorithm and the block ℓ0-norm LMS (B ℓ0-LMS) algorithm, the corresponding new algorithms, i.e., the BZA-LMS-D and B ℓ0-LMS-D algorithms, will be established. The performance superiorities and the robustness against different block-sparsity and/or noise interference for the new algorithms based on dynamic grouping will be demonstrated by both analytic discussions and numerical simulations for a variety of scenarios.",
keywords = "Adaptive filter, Block-sparsity, Compressive sensing, Sparse constraint",
author = "Chen Ye and Guan Gui and Li Xu and Tomoaki Ohtsuki",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2018.2872671",
language = "English",
volume = "6",
pages = "56069--56083",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Recovery of block-structured sparse signal using block-sparse adaptive algorithms via dynamic grouping

AU - Ye, Chen

AU - Gui, Guan

AU - Xu, Li

AU - Ohtsuki, Tomoaki

PY - 2018/1/1

Y1 - 2018/1/1

N2 - A key point for the recovery of a block-sparse signal is how to treat the different sparsity distributed on the different parts of the considered signal. It has been shown recently that grouping the signal, i.e., partitioning the original signal into different groups or segments, and conducting the recovery for these groups separately provides an effective method to deal with the block-structured sparsity and can generate much better performance than the conventional sparse signal recovery (SSR) algorithms. In order to further improve the recovery performance, instead of the fixed grouping method used in the recent results, a novel dynamic grouping method will be first proposed in this paper, which classifies the segments due to the different levels of sparsity in a dynamic way. Then, by incorporating this technique into the block version of adaptive SSR algorithms. we developed recently, i.e., the block zero-attracting least-mean-square (BZA-LMS) algorithm and the block ℓ0-norm LMS (B ℓ0-LMS) algorithm, the corresponding new algorithms, i.e., the BZA-LMS-D and B ℓ0-LMS-D algorithms, will be established. The performance superiorities and the robustness against different block-sparsity and/or noise interference for the new algorithms based on dynamic grouping will be demonstrated by both analytic discussions and numerical simulations for a variety of scenarios.

AB - A key point for the recovery of a block-sparse signal is how to treat the different sparsity distributed on the different parts of the considered signal. It has been shown recently that grouping the signal, i.e., partitioning the original signal into different groups or segments, and conducting the recovery for these groups separately provides an effective method to deal with the block-structured sparsity and can generate much better performance than the conventional sparse signal recovery (SSR) algorithms. In order to further improve the recovery performance, instead of the fixed grouping method used in the recent results, a novel dynamic grouping method will be first proposed in this paper, which classifies the segments due to the different levels of sparsity in a dynamic way. Then, by incorporating this technique into the block version of adaptive SSR algorithms. we developed recently, i.e., the block zero-attracting least-mean-square (BZA-LMS) algorithm and the block ℓ0-norm LMS (B ℓ0-LMS) algorithm, the corresponding new algorithms, i.e., the BZA-LMS-D and B ℓ0-LMS-D algorithms, will be established. The performance superiorities and the robustness against different block-sparsity and/or noise interference for the new algorithms based on dynamic grouping will be demonstrated by both analytic discussions and numerical simulations for a variety of scenarios.

KW - Adaptive filter

KW - Block-sparsity

KW - Compressive sensing

KW - Sparse constraint

UR - http://www.scopus.com/inward/record.url?scp=85054378684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054378684&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2872671

DO - 10.1109/ACCESS.2018.2872671

M3 - Article

AN - SCOPUS:85054378684

VL - 6

SP - 56069

EP - 56083

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8476546

ER -