Support vector machine based classifier for digital modulations in presence of HF noise

Author

Alotaiby, Turky N. ; Shoaib, Mohammed ; Saleh, Alshebeili ; Hazza, Alharbi

Author_Institution

King Abdul-Aziz City for Sci. & Technol., King Saud Univ., Riyadh, Saudi Arabia

fYear

2013

fDate

27-30 April 2013

Firstpage

1

Lastpage

4

Abstract

Support vector machines (SVMs) deal with challenging classification problems. One such a challenge is to classify the modulation type of a signal transmitted over High frequency (HF) band. The noise distribution in this band has time varying nature. SVM can mitigate these variations with correct choice of features and kernel functions. This paper presents a feature-based classification method utilizing SVM for the classification of 10 types of modulations in the presence of Gaussian as well as non-Gaussian noise disturbances. The proposed method is able to classify type and order of modulation at relatively low signal-to-noise ratios (SNRs) for both simulated as well as actual data.

Keywords

Gaussian noise; signal classification; support vector machines; Gaussian noise disturbance; HF noise; SNR; SVM; digital modulation-order classification; digital modulation-type classification; feature-based classification method; high-frequency band; kernel functions; nonGaussian noise disturbance; signal transmission; signal-to-noise ratios; support vector machine-based classifier; time varying noise distribution; Feature extraction; Frequency shift keying; Signal to noise ratio; Support vector machines; Training; Automatic Modulation Classification (AMC); Bi-kappa noise; Feature-Based Classification; HF communications; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Communications and Photonics Conference (SIECPC), 2013 Saudi International

Conference_Location

Fira

Print_ISBN

978-1-4673-6196-5

Electronic_ISBN

978-1-4673-6194-1

Type

conf

DOI

10.1109/SIECPC.2013.6551016

Filename

6551016