MSOM based automatic modulation recognition and demodulation

Lei Zhou, Qiao Cai, Fangming He, Hong Man

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

6 Scopus citations

Abstract

Automatic modulation recognition (AMR) and demodulation are two essential components in cognitive radio receivers. This paper proposes a novel method based on MSOM neural networks to automatically recognize the modulation type and demodulate the radio signal at the same time. This efficient method is directly applied to the normalized radio signal samples and has relatively low computation complexity. A dynamic AMR method is also introduced, which further can reduce the computation without obvious loss in recognition. In this paper, four modulation types, i.e. BPSK, MSK, 2FSK and QPSK, are investigated. Our simulation results show that, compared with the traditional cyclic feature-based methods, the proposed MSOM classifier has better performance while requiring less number of signal samples, and it can also perform demodulation at good accuracy.

Original languageEnglish
Title of host publication2011 34th IEEE Sarnoff Symposium, SARNOFF 2011
DOIs
StatePublished - 2011
Event2011 34th IEEE Sarnoff Symposium, SARNOFF 2011 - Princeton, NJ, United States
Duration: 3 May 20114 May 2011

Publication series

Name2011 34th IEEE Sarnoff Symposium, SARNOFF 2011

Conference

Conference2011 34th IEEE Sarnoff Symposium, SARNOFF 2011
Country/TerritoryUnited States
CityPrinceton, NJ
Period3/05/114/05/11

Keywords

  • SOM neural network
  • cognitive radio
  • demodultation
  • modulation recognition

Fingerprint

Dive into the research topics of 'MSOM based automatic modulation recognition and demodulation'. Together they form a unique fingerprint.

Cite this