A deep heterogeneous optimization framework for Bayesian compressive sensing

被引:5
作者
Qin, Le [1 ]
Cao, Yuanlong [1 ]
Shao, Xun [2 ]
Luo, Yong [1 ]
Rao, Xinping [1 ]
Yi, Yugen [1 ]
Lei, Gang [1 ]
机构
[1] Jiangxi Normal Univ, Sch Software, Nanchang 330022, Jiangxi, Peoples R China
[2] Kitami Inst Technol, Sch Reg Innovat & Social Design Engn, Kitami, Hokkaido, Japan
基金
中国国家自然科学基金;
关键词
Bayesian compressive sensing (BCS); Deep learning; Compressed sensing (CS); Data compression; CHANNEL ESTIMATION; RECOVERY; RECONSTRUCTION;
D O I
10.1016/j.comcom.2021.07.011
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The Bayesian compressive sensing (BCS) is an available approach for data compressions based on compressed sensing framework. Moreover, the priors of sparse signals play a key role in BCS. Various studies that exploit the priors only via models generating, which exist the low prior utilizations. Therefore, to fully use the priors for signals recovering, we propose a novel deep heterogeneous optimization framework which can completely express the priors in a data-model double driven manner. Our work can be briefly summarized by the following aspects. As the heterogeneous handles benefiting recovery solutions, we firstly exploit the available heterogeneous arrangements for traditional BCS recovery models. Secondly, inspired by the deep neural networks (DNNs), we do researches on adding a deep optimization scheme for the scale parameters of heterogeneous prior functions via supervised learning. In addition to developing the three complete algorithms with that merge the prior parameters learning and signal recoveries. Finally, Experimental results show that for both synthetic data and images data our proposed double driven framework achieves the superior performances compared with that of the other well-known compressed recovery algorithms no matter in noise-free or noisy measurement environments.
引用
收藏
页码:74 / 82
页数:9
相关论文
共 34 条
  • [1] Bayesian Compressive Sensing Using Laplace Priors
    Babacan, S. Derin
    Molina, Rafael
    Katsaggelos, Aggelos K.
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2010, 19 (01) : 53 - 63
  • [2] Localization of more sources than sensors via jointly-sparse bayesian learning
    Balkan, Ozgur
    Kreutz-Delgado, Kenneth
    Makeig, Scott
    [J]. IEEE Signal Processing Letters, 2014, 21 (02) : 131 - 134
  • [3] Robust uncertainty principles:: Exact signal reconstruction from highly incomplete frequency information
    Candès, EJ
    Romberg, J
    Tao, T
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (02) : 489 - 509
  • [4] Compressed sensing
    Donoho, DL
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (04) : 1289 - 1306
  • [5] Pattern-Coupled Sparse Bayesian Learning for Recovery of Block-Sparse Signals
    Fang, Jun
    Shen, Yanning
    Li, Hongbin
    Wang, Pu
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2015, 63 (02) : 360 - 372
  • [6] Type I and Type II Bayesian Methods for Sparse Signal Recovery Using Scale Mixtures
    Giri, Ritwik
    Rao, Bhaskar
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2016, 64 (13) : 3418 - 3428
  • [7] Tree-Structured Compressive Sensing With Variational Bayesian Analysis
    He, Lihan
    Chen, Haojun
    Carin, Lawrence
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2010, 17 (03) : 233 - 236
  • [8] Distributed Jointly Sparse Bayesian Learning With Quantized Communication
    Hua, Junhao
    Li, Chunguang
    [J]. IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS, 2018, 4 (04): : 769 - 782
  • [9] Enhanced radio tomographic imaging with heterogeneous Bayesian compressive sensing
    Huang, Kaide
    Tan, Shengbo
    Luo, Yubin
    Guo, Xuemei
    Wang, Guoli
    [J]. PERVASIVE AND MOBILE COMPUTING, 2017, 40 : 450 - 463
  • [10] Bayesian compressive sensing
    Ji, Shihao
    Xue, Ya
    Carin, Lawrence
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2008, 56 (06) : 2346 - 2356