Modulation Format Identification Based on Channel-spatial Attention Modules and Deep Learning

Qian Chen, Qi Zhang*, Xiangjun Xin, Yi Cui, Fu Wang, Feng Tian, Qinghua Tian, Yongjun Wang, Leijing Yang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a scheme is proposed where the channel and spatial attention convolutional neural networks are applied to identify modulation formats from signal constellation diagrams. According to the simulation results, it outperforms other modulation format identification (MFI) schemes in the overall identification rate. Moreover, the scheme shows a significant advantage in signal identification given low optical signal-to-noise ratios (OSNRs).

Original languageEnglish
Title of host publicationProceedings of 2023 IEEE 5th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2023
EditorsHuabo Sun
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages887-891
Number of pages5
ISBN (Electronic)9798350310603
DOIs
Publication statusPublished - 2023
Event5th IEEE International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2023 - Dali, China
Duration: 11 Oct 202313 Oct 2023

Publication series

NameProceedings of 2023 IEEE 5th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2023

Conference

Conference5th IEEE International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2023
Country/TerritoryChina
CityDali
Period11/10/2313/10/23

Keywords

  • convolutional neural networks
  • modulation format identification
  • signal constellation diagrams

Fingerprint

Dive into the research topics of 'Modulation Format Identification Based on Channel-spatial Attention Modules and Deep Learning'. Together they form a unique fingerprint.

Cite this