University of Oulu

M. Leinonen and M. Codreanu, "Low-Complexity Vector Quantized Compressed Sensing via Deep Neural Networks," in IEEE Open Journal of the Communications Society, vol. 1, pp. 1278-1294, 2020, doi: 10.1109/OJCOMS.2020.3020131

Low-complexity vector quantized compressed sensing via deep neural networks

Saved in:
Author: Leinonen, Markus1,2; Codreanu, Marian3,2
Organizations: 1Centre for Wireless Communications–Radio Technologies, University of Oulu, 90014 Oulu, Finland
2Linköping University, Linköping, Sweden
3Centre for Wireless Communications–Radio Technologies, University of Oulu, Oulu, Finland
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 1.2 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2020
Publish Date: 2020-10-01


Sparse signals, encountered in many wireless and signal acquisition applications, can be acquired via compressed sensing (CS) to reduce computations and transmissions, crucial for resource-limited devices, e.g., wireless sensors. Since the information signals are often continuous-valued, digital communication of compressive measurements requires quantization. In such a quantized compressed sensing (QCS) context, we address remote acquisition of a sparse source through vector quantized noisy compressive measurements. We propose a deep encoder-decoder architecture, consisting of an encoder deep neural network (DNN), a quantizer, and a decoder DNN, that realizes low-complexity vector quantization aiming at minimizing the mean-square error of the signal reconstruction for a given quantization rate. We devise a supervised learning method using stochastic gradient descent and backpropagation to train the system blocks. Strategies to overcome the vanishing gradient problem are proposed. Simulation results show that the proposed non-iterative DNN-based QCS method achieves higher rate-distortion performance with lower algorithm complexity as compared to standard QCS methods, conducive to delay-sensitive applications with large-scale signals.

see all

Series: IEEE open journal of the Communications Society
ISSN: 2644-125X
ISSN-E: 2644-125X
ISSN-L: 2644-125X
Volume: 1
Pages: 1278 - 1294
DOI: 10.1109/OJCOMS.2020.3020131
Type of Publication: A1 Journal article – refereed
Field of Science: 213 Electronic, automation and communications engineering, electronics
Funding: This work was supported in part by Infotech Oulu, in part by the Academy of Finland under Grant 323698, and in part by the Academy of Finland 6Genesis Flagship under Grant 318927. The work of Markus Leinonen was supported in part by the Academy of Finland under Grant 319485. The work of Marian Codreanu was supported by the European Union’s Horizon 2020 Research and Innovation Programme through the Marie Skłodowska-Curie Grant under Agreement 793402 (COMPRESS NETS).
Academy of Finland Grant Number: 323698
Detailed Information: 323698 (Academy of Finland Funding decision)
318927 (Academy of Finland Funding decision)
319485 (Academy of Finland Funding decision)
Dataset Reference: Matlab codes to implement the DeepVQCS method proposed in "Low-Complexity Vector Quantized Compressed Sensing via Deep Neural Networks" (M. Leinonen and M. Codreanu)
Copyright information: © The Authors 2020. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see