Multiple hypothesis modulation classification based on cyclic cumulants of different orders

Author

Marchand, Pierre ; Lacoume, Jean-Louis ; Martret, Christophe Le

Author_Institution

CEPHAG-ENSIEG, Domaine Univ., France

Volume

4

fYear

1998

fDate

12-15 May 1998

Firstpage

2157

Abstract

A multiple hypothesis modulation QAM classification task is addressed. The classifier is designed within the rigorous framework of decision theory. A characteristic feature is extracted from the signal, and is compared to the possible theoretical features in the maximum likelihood sense. This feature is composed of a combination between fourth-order and squared second-order cyclic temporal cumulants. No assumption about the power of the signal is made. It is shown that this uncertainty about the power of the signal does not affect the decision rule. As an application, we present simulated performance in the context of 4-QAM vs 16-QAM vs 64-QAM classification

Keywords

decision theory; feature extraction; higher order statistics; pattern classification; quadrature amplitude modulation; 16-QAM; 4-QAM; 64-QAM; cyclic cumulants; cyclic multicorrelations; decision rule; decision theory; feature extraction; fourth-order cyclic temporal cumulant; interference; maximum likelihood function; multiple hypothesis modulation classification; noise corrupted signal; simulated performance; squared second-order cyclic temporal cumulant; Context modeling; Decision theory; Frequency shift keying; Interference; Maximum likelihood detection; Pattern classification; Quadrature amplitude modulation; Signal detection; Signal processing; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on

Conference_Location

Seattle, WA

ISSN

1520-6149

Print_ISBN

0-7803-4428-6

Type

conf

DOI

10.1109/ICASSP.1998.681573

Filename

681573