One-Bit Compressive Sensing: Can We Go Deep and Blind?

被引:0
|
作者
Zeng, Yiming [1 ]
Khobahi, Shahin [1 ]
Soltanalian, Mojtaba [1 ]
机构
[1] Univ Illinois, Dept Elect & Comp Engn, Chicago, IL 60607 USA
基金
美国国家科学基金会;
关键词
Sensors; Signal processing algorithms; Decoding; Sparse matrices; Neural networks; Compressed sensing; Training; Blind compressive sensing; deep-unfolded neural networks; interpretable deep learning; one-bit sampling; NETWORKS;
D O I
10.1109/LSP.2022.3187318
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
One-bit compressive sensing is concerned with the accurate recovery of an underlying sparse signal of interest from its one-bit noisy measurements. The conventional signal recovery approaches for this problem are mainly developed based on the assumption that an exact knowledge of the sensing matrix is available. In this work, however, we present a novel data-driven and model-based methodology that achieves blind recovery; i.e., signal recovery without requiring the knowledge of the sensing matrix. To this end, we make use of the deep unfolding technique and develop a model-driven deep neural architecture which is designed for this specific task. The proposed deep architecture is able to learn an alternative sensing matrix by taking advantage of the underlying unfolded algorithm such that the resulting learned recovery algorithm can accurately and quickly (in terms of the number of iterations) recover the underlying compressed signal of interest from its one-bit noisy measurements. In addition, due to the incorporation of the domain knowledge and the mathematical model of the system into the proposed deep architecture, the resulting network benefits from enhanced interpretability, has a very small number of trainable parameters, and requires very small number of training samples, as compared to the commonly used black-box deep neural network alternatives for the problem at hand.
引用
收藏
页码:1629 / 1633
页数:5
相关论文
共 50 条
  • [1] DEEP ONE-BIT COMPRESSIVE AUTOENCODING
    Khobahi, Shahin
    Bose, Arindam
    Soltanalian, Mojtaba
    [J]. 2021 IEEE STATISTICAL SIGNAL PROCESSING WORKSHOP (SSP), 2021, : 371 - 375
  • [2] Model-Based Deep Learning for One-Bit Compressive Sensing
    Khobahi, Shahin
    Soltanalian, Mojtaba
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2020, 68 : 5292 - 5307
  • [3] One-Bit Compressive Sensing With Norm Estimation
    Knudson, Karin
    Saab, Rayan
    Ward, Rachel
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2016, 62 (05) : 2748 - 2758
  • [4] Robust mixed one-bit compressive sensing
    Huang, Xiaolin
    Yang, Haiyan
    Huang, Yixing
    Shi, Lei
    He, Fan
    Maier, Andreas
    Yan, Ming
    [J]. SIGNAL PROCESSING, 2019, 162 : 161 - 168
  • [5] One-Bit Compressive Sensing with Partial Support
    North, Phillip
    Needell, Deanna
    [J]. 2015 IEEE 6TH INTERNATIONAL WORKSHOP ON COMPUTATIONAL ADVANCES IN MULTI-SENSOR ADAPTIVE PROCESSING (CAMSAP), 2015, : 349 - 352
  • [6] DEEP BLIND ONE-BIT SIGNAL RECOVERY
    Huang, Ruida
    Chen, Xu
    [J]. PROCEEDINGS OF THE 2020 IEEE 30TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2020,
  • [7] Improved Bounds for Universal One-bit Compressive Sensing
    Acharya, Jayadev
    Bhattacharyya, Arnah
    Kamath, Pritish
    [J]. 2017 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT), 2017, : 2353 - 2357
  • [8] A Combinatorial Approach to One-Bit Compressive Radar Sensing
    Esfeh, Mohammad Mahdi Kazemi
    Naghsh, Mohammad Mahdi
    Zahabi, Sayed Jalal
    Li, Jian
    [J]. 2018 CONFERENCE RECORD OF 52ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2018, : 920 - 923
  • [9] One-Bit Compressive Radar Sensing in the Presence of Clutter
    Zahabi, Sayed Jalal
    Naghsh, Mohammad Mahdi
    Modarres-Hashemi, Mahmoud
    Li, Jian
    [J]. IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2020, 56 (01) : 167 - 185
  • [10] Efficient Algorithms for Robust One-bit Compressive Sensing
    Zhang, Lijun
    Yi, Jinfeng
    Jin, Rung
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), 2014, 32 : 820 - 828