Feature selection for cyclostationary-based signal classification

Garrett Vanhoy, Noel Teku, Tamal Bose

Research output: Contribution to journalConference article

Abstract

Cognitive radio (CR) is a concept that imagines a radio (wireless transceiver) that contains an embedded intelligent agent that can adapt to its spectral environment. Using a software defined radio (SDR), a radio can detect the presence of other users in the spectrum and adapt accordingly, but it is important in many applications to discern between individual transmitters and this can be done using signal classification. The use of cyclostationary features have been shown to be robust to many common channel conditions. One such cyclostationary feature, the spectral correlation density (SCD), has seen limited use in signal classification until now because it is a computationally intensive process. This work demonstrates how feature selection techniques can be used to enable real-time classification. The proposed technique is validated using 8 common modulation formats that are generated and collected over the air.

Original languageEnglish (US)
JournalProceedings of the International Telemetering Conference
StatePublished - Jan 1 2017

Fingerprint

Feature extraction
spectral correlation
transmitter receivers
transmitters
format
Intelligent agents
Cognitive radio
Transceivers
computer programs
modulation
Transmitters
air
Modulation
Air

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Instrumentation
  • Computer Networks and Communications
  • Signal Processing

Cite this

Feature selection for cyclostationary-based signal classification. / Vanhoy, Garrett; Teku, Noel; Bose, Tamal.

In: Proceedings of the International Telemetering Conference, 01.01.2017.

Research output: Contribution to journalConference article

@article{639866236b4a47a8926627a3a06b3bef,
title = "Feature selection for cyclostationary-based signal classification",
abstract = "Cognitive radio (CR) is a concept that imagines a radio (wireless transceiver) that contains an embedded intelligent agent that can adapt to its spectral environment. Using a software defined radio (SDR), a radio can detect the presence of other users in the spectrum and adapt accordingly, but it is important in many applications to discern between individual transmitters and this can be done using signal classification. The use of cyclostationary features have been shown to be robust to many common channel conditions. One such cyclostationary feature, the spectral correlation density (SCD), has seen limited use in signal classification until now because it is a computationally intensive process. This work demonstrates how feature selection techniques can be used to enable real-time classification. The proposed technique is validated using 8 common modulation formats that are generated and collected over the air.",
author = "Garrett Vanhoy and Noel Teku and Tamal Bose",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
journal = "Proceedings of the International Telemetering Conference",
issn = "0884-5123",

}

TY - JOUR

T1 - Feature selection for cyclostationary-based signal classification

AU - Vanhoy, Garrett

AU - Teku, Noel

AU - Bose, Tamal

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Cognitive radio (CR) is a concept that imagines a radio (wireless transceiver) that contains an embedded intelligent agent that can adapt to its spectral environment. Using a software defined radio (SDR), a radio can detect the presence of other users in the spectrum and adapt accordingly, but it is important in many applications to discern between individual transmitters and this can be done using signal classification. The use of cyclostationary features have been shown to be robust to many common channel conditions. One such cyclostationary feature, the spectral correlation density (SCD), has seen limited use in signal classification until now because it is a computationally intensive process. This work demonstrates how feature selection techniques can be used to enable real-time classification. The proposed technique is validated using 8 common modulation formats that are generated and collected over the air.

AB - Cognitive radio (CR) is a concept that imagines a radio (wireless transceiver) that contains an embedded intelligent agent that can adapt to its spectral environment. Using a software defined radio (SDR), a radio can detect the presence of other users in the spectrum and adapt accordingly, but it is important in many applications to discern between individual transmitters and this can be done using signal classification. The use of cyclostationary features have been shown to be robust to many common channel conditions. One such cyclostationary feature, the spectral correlation density (SCD), has seen limited use in signal classification until now because it is a computationally intensive process. This work demonstrates how feature selection techniques can be used to enable real-time classification. The proposed technique is validated using 8 common modulation formats that are generated and collected over the air.

UR - http://www.scopus.com/inward/record.url?scp=85041482239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041482239&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85041482239

JO - Proceedings of the International Telemetering Conference

JF - Proceedings of the International Telemetering Conference

SN - 0884-5123

ER -