DAWFNN: An Automatic Modulation Recognition Method Based on Multi Feature Fusion

Yitong Lu*, Shujuan Hou, Qin Zhang, Hai Li

*Corresponding author for this work

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

Abstract

Nowadays, automatic modulation recognition (AMR) technology has become an important component of civil and military wireless communication systems. Especially in noncooperative communication scenarios, modulation recognition plays a decisive role in the acquisition of subsequent data information. In order to fully combine the advantages of modulation recognition technology based on feature extraction and deep learning, we propose to use in-phase component and quadrature component (IQ) and a circulant feature matrix (CFM) composed of traditional feature parameters as the input data of the neural network, and design a feature extraction module for the CFM. We design a dynamic adaptive weighted feature fusion module for the intermediate feature parameters of IQ data and CFM after the neural network, and realize feature fusion that is more conducive to modulation recognition. Experimental results show that our method has advantages in recognition accuracy compared with other network models.

Original languageEnglish
Title of host publication10th International Conference on Computer and Communication Systems, ICCCS 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages480-485
Number of pages6
ISBN (Electronic)9798331523145
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event10th International Conference on Computer and Communication Systems, ICCCS 2025 - Chengdu, China
Duration: 18 Apr 202521 Apr 2025

Publication series

Name10th International Conference on Computer and Communication Systems, ICCCS 2025

Conference

Conference10th International Conference on Computer and Communication Systems, ICCCS 2025
Country/TerritoryChina
CityChengdu
Period18/04/2521/04/25

Keywords

  • automatic modulation recognition
  • multi feature fusion
  • neural network

Fingerprint

Dive into the research topics of 'DAWFNN: An Automatic Modulation Recognition Method Based on Multi Feature Fusion'. Together they form a unique fingerprint.

Cite this