Single-Shot Sub-Nyquist RF Signal Reconstruction Based on Deep Learning Network

Shun Liu; Chaitanya K. Mididoddi; Huiyu Zhou; Baojun Li; Weichao Xu; Chao Wang

doi:10.1109/MWP.2018.8552894

Single-Shot Sub-Nyquist RF Signal Reconstruction Based on Deep Learning Network

Shun Liu, Chaitanya K. Mididoddi, Huiyu Zhou, Baojun Li, Weichao Xu, Chao Wang^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

Real-time detection of high-frequency RF signals requires sophisticated hardware with large bandwidth and high sampling rates. Existing microwave photonic methods have enabled sub-Nyquist sampling for bandwidth-efficient RF signal detection but fall short in single-shot reconstruction. Here we report a novel single-shot sub-Nyquist RF signal detection method based on a trained deep neural network. In a proof-of-concept demonstration, our system successfully reconstructs high frequency multi-toned RF signals from 5x down-sampled singleshot measurements by utilizing a deep convolutional neural network. The presented approach is a powerful digital accelerator to existing hardware detectors to significantly enhance the detection capability.

Original language	English
Title of host publication	MWP 2018 - 2018 International Topical Meeting on Microwave Photonics
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538652268
DOIs	https://doi.org/10.1109/MWP.2018.8552894
Publication status	Published - 03 Dec 2018
Externally published	Yes
Event	2018 International Topical Meeting on Microwave Photonics, MWP 2018 - Toulouse, France Duration: 22 Oct 2018 → 25 Oct 2018

Publication series

Name	MWP 2018 - 2018 International Topical Meeting on Microwave Photonics

Conference

Conference	2018 International Topical Meeting on Microwave Photonics, MWP 2018
Country/Territory	France
City	Toulouse
Period	22/10/2018 → 25/10/2018

Bibliographical note

Funding Information:
This work was supported in part by the EU FP7 Marie-Curie Career Integration Grant (631883), in part by the Royal Society (IE170007), in part by National Natural Science Foundation of China (Projects 61771148, 61571211 and U1501251), and in part by Guangzhou Science and Technology Plan (Project 201607010290).

Publisher Copyright:
© 2018 IEEE.

Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.

Keywords

Convolutional neural network
deep learning
Nyquist sampling
single-shot
under sampling

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Instrumentation
Atomic and Molecular Physics, and Optics

Access to Document

10.1109/MWP.2018.8552894Licence: Unspecified

Cite this

Liu, S., Mididoddi, C. K., Zhou, H., Li, B., Xu, W., & Wang, C. (2018). Single-Shot Sub-Nyquist RF Signal Reconstruction Based on Deep Learning Network. In MWP 2018 - 2018 International Topical Meeting on Microwave Photonics Article 8552894 (MWP 2018 - 2018 International Topical Meeting on Microwave Photonics). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MWP.2018.8552894

@inproceedings{0194c6c68d1844ccbd9d2ebd5ea188de,

title = "Single-Shot Sub-Nyquist RF Signal Reconstruction Based on Deep Learning Network",

abstract = "Real-time detection of high-frequency RF signals requires sophisticated hardware with large bandwidth and high sampling rates. Existing microwave photonic methods have enabled sub-Nyquist sampling for bandwidth-efficient RF signal detection but fall short in single-shot reconstruction. Here we report a novel single-shot sub-Nyquist RF signal detection method based on a trained deep neural network. In a proof-of-concept demonstration, our system successfully reconstructs high frequency multi-toned RF signals from 5x down-sampled singleshot measurements by utilizing a deep convolutional neural network. The presented approach is a powerful digital accelerator to existing hardware detectors to significantly enhance the detection capability.",

keywords = "Convolutional neural network, deep learning, Nyquist sampling, single-shot, under sampling",

author = "Shun Liu and Mididoddi, {Chaitanya K.} and Huiyu Zhou and Baojun Li and Weichao Xu and Chao Wang",

note = "Funding Information: This work was supported in part by the EU FP7 Marie-Curie Career Integration Grant (631883), in part by the Royal Society (IE170007), in part by National Natural Science Foundation of China (Projects 61771148, 61571211 and U1501251), and in part by Guangzhou Science and Technology Plan (Project 201607010290). Publisher Copyright: {\textcopyright} 2018 IEEE. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; 2018 International Topical Meeting on Microwave Photonics, MWP 2018 ; Conference date: 22-10-2018 Through 25-10-2018",

year = "2018",

month = dec,

day = "3",

doi = "10.1109/MWP.2018.8552894",

language = "English",

series = "MWP 2018 - 2018 International Topical Meeting on Microwave Photonics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "MWP 2018 - 2018 International Topical Meeting on Microwave Photonics",

address = "United States",

}

Liu, S, Mididoddi, CK, Zhou, H, Li, B, Xu, W & Wang, C 2018, Single-Shot Sub-Nyquist RF Signal Reconstruction Based on Deep Learning Network. in MWP 2018 - 2018 International Topical Meeting on Microwave Photonics., 8552894, MWP 2018 - 2018 International Topical Meeting on Microwave Photonics, Institute of Electrical and Electronics Engineers Inc., 2018 International Topical Meeting on Microwave Photonics, MWP 2018, Toulouse, France, 22/10/2018. https://doi.org/10.1109/MWP.2018.8552894

Single-Shot Sub-Nyquist RF Signal Reconstruction Based on Deep Learning Network. / Liu, Shun; Mididoddi, Chaitanya K.; Zhou, Huiyu et al.
MWP 2018 - 2018 International Topical Meeting on Microwave Photonics. Institute of Electrical and Electronics Engineers Inc., 2018. 8552894 (MWP 2018 - 2018 International Topical Meeting on Microwave Photonics).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Single-Shot Sub-Nyquist RF Signal Reconstruction Based on Deep Learning Network

AU - Liu, Shun

AU - Mididoddi, Chaitanya K.

AU - Zhou, Huiyu

AU - Li, Baojun

AU - Xu, Weichao

AU - Wang, Chao

N1 - Funding Information: This work was supported in part by the EU FP7 Marie-Curie Career Integration Grant (631883), in part by the Royal Society (IE170007), in part by National Natural Science Foundation of China (Projects 61771148, 61571211 and U1501251), and in part by Guangzhou Science and Technology Plan (Project 201607010290). Publisher Copyright: © 2018 IEEE. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.

PY - 2018/12/3

Y1 - 2018/12/3

N2 - Real-time detection of high-frequency RF signals requires sophisticated hardware with large bandwidth and high sampling rates. Existing microwave photonic methods have enabled sub-Nyquist sampling for bandwidth-efficient RF signal detection but fall short in single-shot reconstruction. Here we report a novel single-shot sub-Nyquist RF signal detection method based on a trained deep neural network. In a proof-of-concept demonstration, our system successfully reconstructs high frequency multi-toned RF signals from 5x down-sampled singleshot measurements by utilizing a deep convolutional neural network. The presented approach is a powerful digital accelerator to existing hardware detectors to significantly enhance the detection capability.

AB - Real-time detection of high-frequency RF signals requires sophisticated hardware with large bandwidth and high sampling rates. Existing microwave photonic methods have enabled sub-Nyquist sampling for bandwidth-efficient RF signal detection but fall short in single-shot reconstruction. Here we report a novel single-shot sub-Nyquist RF signal detection method based on a trained deep neural network. In a proof-of-concept demonstration, our system successfully reconstructs high frequency multi-toned RF signals from 5x down-sampled singleshot measurements by utilizing a deep convolutional neural network. The presented approach is a powerful digital accelerator to existing hardware detectors to significantly enhance the detection capability.

KW - Convolutional neural network

KW - deep learning

KW - Nyquist sampling

KW - single-shot

KW - under sampling

U2 - 10.1109/MWP.2018.8552894

DO - 10.1109/MWP.2018.8552894

M3 - Conference contribution

AN - SCOPUS:85060054387

T3 - MWP 2018 - 2018 International Topical Meeting on Microwave Photonics

BT - MWP 2018 - 2018 International Topical Meeting on Microwave Photonics

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 International Topical Meeting on Microwave Photonics, MWP 2018

Y2 - 22 October 2018 through 25 October 2018

ER -

Liu S, Mididoddi CK, Zhou H, Li B, Xu W, Wang C. Single-Shot Sub-Nyquist RF Signal Reconstruction Based on Deep Learning Network. In MWP 2018 - 2018 International Topical Meeting on Microwave Photonics. Institute of Electrical and Electronics Engineers Inc. 2018. 8552894. (MWP 2018 - 2018 International Topical Meeting on Microwave Photonics). doi: 10.1109/MWP.2018.8552894

Single-Shot Sub-Nyquist RF Signal Reconstruction Based on Deep Learning Network

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this