Skip to main navigation Skip to search Skip to main content

Automatic digital modulation recognition based on support vector machines

  • Wu Zhilu*
  • , Wang Xuexia
  • , Gao Zhenzhen
  • , Ren Guanghui
  • *Corresponding author for this work
  • School of Electronics and Information Engineering, Harbin Institute of Technology

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

Abstract

This paper presents a method based on support vector machines (SVMs) for recognizing digital modulation signals in the presence of additive white Gaussian noise. As a powerful method for pattern recognition, SVMs with radial basis function (RBF) kernels are incorporated to form the multi-class recognition system which employs the conventional features of each signal obtained from its amplitude, frequency, and phase information. Computer simulations of different types of band-limited digitally modulated signals corrupted by Gaussian white noise have been carried out to measure the performance of the classification method. The simulation results that the accuracy rate of this method is at lest 85.67% show that the recognition method based on SVMs is effective. And the performance of the automatic recognition method is very satisfactory with high overall success rates even in a low signal to noise ratio (SNR) environment.

Original languageEnglish
Title of host publicationProceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05
Pages1025-1028
Number of pages4
StatePublished - 2005
Externally publishedYes
Event2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05 - Beijing, China
Duration: 13 Oct 200515 Oct 2005

Publication series

NameProceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05
Volume2

Conference

Conference2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05
Country/TerritoryChina
CityBeijing
Period13/10/0515/10/05

Fingerprint

Dive into the research topics of 'Automatic digital modulation recognition based on support vector machines'. Together they form a unique fingerprint.

Cite this