A Hybrid ICA-SVM Approach to Continuous Phase Modulation Recognition

Author

Boutte, David ; Santhanam, Balu

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of New Mexico, Albuquerque, NM

Volume

16

Issue

5

fYear

2009

fDate

5/1/2009 12:00:00 AM

Firstpage

402

Lastpage

405

Abstract

Automatic modulation recognition is a topic of interest in many fields including signal surveillance, multi-user detection and radio frequency spectrum monitoring. In this paper, we present an algorithm for recognition of different types of continuous phase modulation signals that uses a combination of features extracted through cyclic spectral analysis and an ICA-SVM hybrid recognition system. Simulation results demonstrate the ability of the algorithm to correctly identify modulation types over a wide range of SNR scenarios. The effects of pulse shaping and partial response waveforms are also investigated.

Keywords

feature extraction; phase modulation; pulse shaping; support vector machines; ICA-SVM hybrid recognition system; SNR scenarios; continuous phase modulation signals; cyclic spectral analysis; features extraction; partial response waveforms; pulse shaping; Computerized monitoring; Continuous phase modulation; Feature extraction; Multiuser detection; RF signals; Radio frequency; Radiofrequency identification; Signal detection; Spectral analysis; Surveillance; Automatic modulation recognition; ICA; SVM;

fLanguage

English

Journal_Title

Signal Processing Letters, IEEE

Publisher

ieee

ISSN

1070-9908

Type

jour

DOI

10.1109/LSP.2009.2016444

Filename

4804948