Deep Learning Method for Generalized Modulation Classification under Varying Noise Condition

Yu Wang, Guan Gui, Nan Zhao, Hao Huang, Miao Liu, Jinlong Sun, Haris Gacanin, Hikmet Sari, Adachi Fumiyuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Modulation signal classification (MSC) is an indispensable technique to make the possible applications of non-cooperative communications. Currently, convolutional neural network (CNN) based MSC techniques can achieve an outstanding performance at a fixed noise regime. However, they are hard to generalize to all of noise scenarios. Because these conventional methods are trained on specific signal samples with fixed SNR and they only perform well under corresponding noise condition. Unlike the conventional methods, in this paper, we propose a robust CNN based generalized MSC (GMSC) method with powerful generality capability. This capability stems from the mixed dataset, containing in-phase and quadrature (IQ) samples under various SNR regimes. Experimental results show that the proposed method is robust under varying noise conditions, while merely losing a slight performance with comparing with conventional methods.

Original languageEnglish
Title of host publication2020 International Conference on Computing, Networking and Communications, ICNC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages938-943
Number of pages6
ISBN (Electronic)9781728149059
DOIs
Publication statusPublished - 2020 Feb
Event2020 International Conference on Computing, Networking and Communications, ICNC 2020 - Big Island, United States
Duration: 2020 Feb 172020 Feb 20

Publication series

Name2020 International Conference on Computing, Networking and Communications, ICNC 2020

Conference

Conference2020 International Conference on Computing, Networking and Communications, ICNC 2020
CountryUnited States
CityBig Island
Period20/2/1720/2/20

Keywords

  • Convolutional neural network (CNN)
  • Generalized ability
  • Modulation signal classification (MSC)
  • Non-cooperative communication

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems and Management
  • Control and Optimization

Fingerprint Dive into the research topics of 'Deep Learning Method for Generalized Modulation Classification under Varying Noise Condition'. Together they form a unique fingerprint.

Cite this