skip to main content
10.1145/3447654.3447662acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicnccConference Proceedingsconference-collections
research-article

Recognition of Signal Modulation Mode Based on Gaussian Filter and Deep Learning

Published: 13 May 2021 Publication History

Abstract

In recent years, some studies have shown that the deep learning method can be used to recognize the modulation mode of signal quickly and effectively, but the modulation recognition effect of low signal to noise rate (SNR) signal is obviously poor. This paper presented a signal modulation recognition method based on filtering technique and Convolution Neural Network (CNN) plus Long-Short Term Memory (LSTM) networks. First of all, signals are divided into high SNR signals and low SNR signals by second-order statistics of modulated signals, and Gaussian filtering is carried out for low SNR signals, so as to achieve the effect of noise reduction. Then, modulation recognition is carried out for all signals. Experimental results show that this method can recognize 11 types of modulation which including digital signals and analog signals, and the average recognition accuracy is 71.33%. When the SNR is greater than 0 dB, the average recognition accuracy can reach 96.53%. When the SNR is at -20 dB ∼ -8 dB, the recognition accuracy is also improved compared with the CNN method.

References

[1]
Zhou Longmei. Deep Learning Based Communication Signal Recognition Technologies [D]. Beijing University of Posts and Telecommunications, 2018.
[2]
P. Li, F. Wang Algorithm for Modulation Recognition Based on High-order Cumulants and Subspace Decomposition [C]. 2006 8th International Conference on Signal Processing, Beijing, 2006.
[3]
W. Xie, S. Hu, Deep Learning in Digital Modulation Recognition Using High Order Cumulants [J]. IEEE Access. 2019, 7, 63760-63766.
[4]
Zhang Qian. Recognition of Digital Modulation Signals Based on High-order Statistical Characteristics [D]. University of Electronic Science and Technology of China, 2018.
[5]
Hao Simin. Modulation Classification Based on Cumulants and Goodness of Fit Test [D]. Shandong University, 2019.
[6]
HOU Tao, ZHENG Yuzheng. Communication Signal Modulation Identification Based on Deep Learning [J]. Radio Engineering, 2019, 49 (9): 796-800.
[7]
O'Shea, T. J., Corgan, J, Convolutional Radio Modulation Recognition Networks [C]. Engineering Applications of Neural Networks. 2016, 213-226.
[8]
K. Karra, S. Kuzdeba, Modulation Recognition Using Hierarchical Deep Neural Networks [C]. 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DSAN), Piscataway, NJ, 2017, 1-3.
[9]
Zhang D, Ding W, Automatic Modulation Classification Based on Deep Learning for Unmanned Aerial Vehicles [J]. Sensors, 2018, 18(3): 924.
[10]
Shengliang P, Hanyu J, Modulation Classification Based on Signal Constellation Diagrams and Deep Learning [J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30: 718-727.
[11]
Zhang Bin, Zhao Mengwei, Automatic Modulation Classification Based on Deep Learning [J]. Electronic Measurement Technology. 2018, 41 (23): 131-136.
[12]
O'Shea, T. J. WEST, N. Nathan. Radio Machine Learning Dataset Generation with GNU Radio [C]. Proceedings of the GNU Radio Conference, [S. l.], v. 1, n. 1, Sep. 2016.
[13]
O'Shea, T. J. Corgan, J. Unsupervised Representation Learning of Structured Radio Communication Signals [C]. 2016 First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE), Aalborg, 2016, 1-5.
[14]
O'Shea, T. J. WEST, N. Semi-supervised Radio Signal Identification[C]. International Conference on Advanced Communication Technology, IEEE, 2017:33-38.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICNCC '20: Proceedings of the 2020 9th International Conference on Networks, Communication and Computing
December 2020
157 pages
ISBN:9781450388566
DOI:10.1145/3447654
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 May 2021

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Deep learning
  2. Gaussian filter
  3. Modulation recognition

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ICNCC 2020

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 52
    Total Downloads
  • Downloads (Last 12 months)5
  • Downloads (Last 6 weeks)0
Reflects downloads up to 20 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media