Cellular Signal Identification Using Convolutional Neural Networks: AWGN and Rayleigh Fading Channels

Hongtao Xia, Khalid Alshathri, Victor B. Lawrence, Yu Dong Yao, Armando Montalvo, Michael Rauchwerk, Robert Cupo

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

28 Scopus citations

Abstract

Spectrum awareness is crucial in wireless communications systems for dynamic network environments. It is required for spectrum resource management, adaptive transmissions, and interference detection. Existing spectrum awareness research includes tasks of spectrum sensing, modulation classification, and medium access control protocol (MAC) identification. This paper explores the identification and classification of signals of various cellular networks, including Global System for Mobile (GSM), Universal Mobile Telecommunication Service (UMTS), and Long-Term Evolution (LTE). We utilize deep learning, specifically, convolutional neural networks (CNN), in training and testing wireless fading signals in those cellular networks. Experimentations demonstrate the effectiveness of deep learning in cellular signal identification.

Original languageEnglish
Title of host publication2019 IEEE International Symposium on Dynamic Spectrum Access Networks, DySPAN 2019
ISBN (Electronic)9781728123769
DOIs
StatePublished - Nov 2019
Event2019 IEEE International Symposium on Dynamic Spectrum Access Networks, DySPAN 2019 - Newark, United States
Duration: 11 Nov 201914 Nov 2019

Publication series

Name2019 IEEE International Symposium on Dynamic Spectrum Access Networks, DySPAN 2019

Conference

Conference2019 IEEE International Symposium on Dynamic Spectrum Access Networks, DySPAN 2019
Country/TerritoryUnited States
CityNewark
Period11/11/1914/11/19

Keywords

  • Cellular system
  • convolutional neural network (CNN)
  • deep learning
  • signal classification
  • spectrum awareness

Fingerprint

Dive into the research topics of 'Cellular Signal Identification Using Convolutional Neural Networks: AWGN and Rayleigh Fading Channels'. Together they form a unique fingerprint.

Cite this