University of Leicester
Browse

Single-shot sub-Nyquist RF signal reconstruction based on deep learning network

Download (749.74 kB)
conference contribution
posted on 2019-06-11, 11:02 authored by S Liu, CK Mididoddi, H Zhou, B Li, W Xu, C Wang
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.

Funding

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)

History

Citation

2018 International Topical Meeting on Microwave Photonics (MWP), 2018

Author affiliation

/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Informatics

Source

2018 International Topical Meeting on Microwave Photonics (MWP), Toulouse, France

Version

  • AM (Accepted Manuscript)

Published in

2018 International Topical Meeting on Microwave Photonics (MWP)

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

isbn

978-1-5386-5226-8

Acceptance date

2018-10-01

Copyright date

2018

Available date

2019-06-11

Publisher version

https://ieeexplore.ieee.org/abstract/document/8552894

Temporal coverage: start date

2018-10-22

Temporal coverage: end date

2018-10-25

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC