Automatic classification of analog modulation schemes

Author

Xiao, Haifeng ; Shi, Yun Q. ; Su, Wei ; Kosinski, John A.

Author_Institution

Dept. of ECE, New Jersey Inst. of Technol., Newark, NJ, USA

fYear

2012

Firstpage

5

Lastpage

8

Abstract

This paper discusses automatic modulation classification (AMC) of analog schemes. Histograms of instantaneous frequency are used as classification features and Support Vector Machines (SVMs) are then applied to classify the unknown modulation schemes. This novel machine-learning based method can insure robustness in a wide range of SNR. Extensive simulation has demonstrated the validity of the proposed AMC algorithm. It is a practical algorithm in blind AMC environments.

Keywords

amplitude modulation; frequency modulation; learning (artificial intelligence); pattern classification; support vector machines; telecommunication computing; AMC algorithm; SNR wide range; analog modulation schemes; automatic modulation classification; blind AMC environments; machine learning-based method; support vector machines; Classification algorithms; Frequency estimation; Frequency modulation; Histograms; Signal to noise ratio; Support vector machines; Automatic modulation classification; Support Vector Machine; analog modulation; histogram;

fLanguage

English

Publisher

ieee

Conference_Titel

Radio and Wireless Symposium (RWS), 2012 IEEE

Conference_Location

Santa Clara, CA

ISSN

2164-2958

Print_ISBN

978-1-4577-1153-4

Type

conf

DOI

10.1109/RWS.2012.6175327

Filename

6175327