Automatic classification of analog modulation schemes

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

doi:10.1109/RWS.2012.6175327

Automatic classification of analog modulation schemes

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

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

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.

Original language	English (US)
Title of host publication	RWW 2012 - Proceedings
Subtitle of host publication	IEEE Radio and Wireless Symposium, RWS 2012
Pages	5-8
Number of pages	4
DOIs	https://doi.org/10.1109/RWS.2012.6175327
State	Published - 2012
Event	2012 6th IEEE Radio and Wireless Week, RWW 2012 - 2012 IEEE Radio and Wireless Symposium, RWS 2012 - Santa Clara, CA, United States Duration: Jan 15 2012 → Jan 18 2012

Publication series

Name	RWW 2012 - Proceedings: IEEE Radio and Wireless Symposium, RWS 2012

Other

Other	2012 6th IEEE Radio and Wireless Week, RWW 2012 - 2012 IEEE Radio and Wireless Symposium, RWS 2012
Country/Territory	United States
City	Santa Clara, CA
Period	1/15/12 → 1/18/12

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Electrical and Electronic Engineering

Keywords

Automatic modulation classification
Support Vector Machine
analog modulation
histogram

Access to Document

10.1109/RWS.2012.6175327

Cite this

@inproceedings{db28f89c78f04ba7b44d09d5b971fc7a,

title = "Automatic classification of analog modulation schemes",

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 = "Automatic modulation classification, Support Vector Machine, analog modulation, histogram",

author = "Haifeng Xiao and Shi, {Yun Q.} and Wei Su and Kosinski, {John A.}",

year = "2012",

doi = "10.1109/RWS.2012.6175327",

language = "English (US)",

isbn = "9781457711541",

series = "RWW 2012 - Proceedings: IEEE Radio and Wireless Symposium, RWS 2012",

pages = "5--8",

booktitle = "RWW 2012 - Proceedings",

note = "2012 6th IEEE Radio and Wireless Week, RWW 2012 - 2012 IEEE Radio and Wireless Symposium, RWS 2012 ; Conference date: 15-01-2012 Through 18-01-2012",

}

Xiao, H, Shi, YQ, Su, W & Kosinski, JA 2012, Automatic classification of analog modulation schemes. in RWW 2012 - Proceedings: IEEE Radio and Wireless Symposium, RWS 2012., 6175327, RWW 2012 - Proceedings: IEEE Radio and Wireless Symposium, RWS 2012, pp. 5-8, 2012 6th IEEE Radio and Wireless Week, RWW 2012 - 2012 IEEE Radio and Wireless Symposium, RWS 2012, Santa Clara, CA, United States, 1/15/12. https://doi.org/10.1109/RWS.2012.6175327

TY - GEN

T1 - Automatic classification of analog modulation schemes

AU - Xiao, Haifeng

AU - Shi, Yun Q.

AU - Su, Wei

AU - Kosinski, John A.

PY - 2012

Y1 - 2012

N2 - 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.

AB - 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.

KW - Automatic modulation classification

KW - Support Vector Machine

KW - analog modulation

KW - histogram

UR - http://www.scopus.com/inward/record.url?scp=84860680749&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860680749&partnerID=8YFLogxK

U2 - 10.1109/RWS.2012.6175327

DO - 10.1109/RWS.2012.6175327

M3 - Conference contribution

AN - SCOPUS:84860680749

SN - 9781457711541

T3 - RWW 2012 - Proceedings: IEEE Radio and Wireless Symposium, RWS 2012

SP - 5

EP - 8

BT - RWW 2012 - Proceedings

T2 - 2012 6th IEEE Radio and Wireless Week, RWW 2012 - 2012 IEEE Radio and Wireless Symposium, RWS 2012

Y2 - 15 January 2012 through 18 January 2012

ER -

Automatic classification of analog modulation schemes

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this