skip to main content
10.1145/3614008.3614011acmotherconferencesArticle/Chapter ViewAbstractPublication PagesspmlConference Proceedingsconference-collections
research-article

Modulation recognition technology based on ResNet50

Published: 17 October 2023 Publication History

Abstract

Modulation recognition technology belongs to one of the cognitive radio direction technologies in the field of communication, which is widely used in military and civilian use. This paper proposes a ResNet50-based modulation recognition algorithm. Compared with the matrix of most direct input signals, this paper innovatively transforms the signal through STFT pre-processing into time-frequency map [11] and then input it. The last three layers of the ResNet50 network are modified, changing the 1000 signal categories of the original model to only 9 categories, while the other modules remain unchanged. At the same time, transfer learning is introduced, so that the network is only trained on the last three layers, and good recognition performance can be obtained in small-scale data.

References

[1]
HE K. ZHANG X. REN S.C i al. Deep residual learning for image recognition [CY/ 2016 EEE Conference on Computer Vision and Pattern Reeognition. Las Vegas: IEEE, 2016: 770. 778.
[2]
Zhang Zhang, Yang Zhenhao, Cheng Shuhong. Hub recognition based on ResNet50 and transfer learning [J]. Journal of metrology,2022,43(11):1412-1417.
[3]
Duan Yilin, horse dragon, Jia Duan. A transfer learning method based on confusing styles with ResNet captcha [J]. Journal of Xi'an Petroleum University (Natural Science Edition),2019,34(06):121-125.
[4]
Chen Chao, Bin Wu. A multi-objective classification technique for improved residual deep networks [J / OL]. Computer measurement and control:1-10[2023-04-12]. http://kns.cnki.net/kcms/detail/11.4762.tp.20230309.1415.006.html
[5]
Gu Ruifan, Li Xiang, Ren Weimin. Image classification study based on the ResNet50 improved model [J]. Modern electronic technology,2023,46(04):107-112.
[6]
Liu Peng. The Design and Implementation of the Image Classification Model Based on the Neural Network [J]. Wireless Internet technology,2022,19(22):53-55.
[7]
Liu Xianghui. Research on modulation pattern recognition at low signal to noise ratio [D]. Lanzhou Jiaotong University,2022.
[8]
Wu Meilin, Gao Yuxiang, Tu Abbott, Zhang Xinyu. Research on electromagnetic signal modulation recognition based on graded noise reduction [J]. radio engineering,2023,53(02):387-393.
[9]
Ren Xiaoping, Sui Chaoya, Liu Xiaoyong. Research on modulation mode recognition based on deep neural network [J]. Information and Computer (theoretical version),2022,34(18):144-148.
[10]
Lu Huan Bing, Zhang Xu, Ding Xiaojin, etc. Research on Modulation Style Recognition Technology based on Deep Learning [C] / / Satellite Communication Committee of China Communications Society, Satellite Application Professional Committee of Chinese Society of Astronautics. Proceedings of the 18th Annual Satellite Communication Academic Conference. [Unpublisher unknown],2022:232-237.
[11]
Shen Qiang, Zhou Yufang, Zhang Lingzhu. Research on frequency hopping signal detection method based on time-frequency analysis [J]. China radio,2022(06):106-108.
[12]
Xiao Qi. Time-frequency analysis and application in low SNR signal modulation recognition [D]. Hangzhou Dianzi University, 2021.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
SPML '23: Proceedings of the 2023 6th International Conference on Signal Processing and Machine Learning
July 2023
383 pages
ISBN:9798400707575
DOI:10.1145/3614008
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 the author(s) 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: 17 October 2023

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. ResNet50
  2. STFT;
  3. modulation recognition technology
  4. transfer learning

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

SPML 2023

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 23
    Total Downloads
  • Downloads (Last 12 months)16
  • Downloads (Last 6 weeks)1
Reflects downloads up to 13 Jan 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

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media