Multi-receiver modulation classification for non-cooperative scenarios based on higher-order cumulants

Garrett Vanhoy, Hamed Asadi, Haris Volos, Tamal Bose

Research output: Contribution to journalArticle

Abstract

Modulation Classification (MC) is a difficult task that can increase awareness in Cognitive Radio (CR) applications. Much of the research in MC has been for single antenna and single user scenarios. With multiple users, blind source separation (BSS) techniques have successfully been used to separate a linear mixture of signals. This work demonstrates that results for MC in a single-user MIMO communications system can be extended to MC in a multi-user scenario with the use of blind source separation techniques. However, a number of difficulties exist with the use of blind source separation techniques that make a simple extension (difficult) possible. First, since the number of users is unknown, BSS techniques must attempt to separate signals with the assumption that a larger number of users exist (than are actually present). Second, BSS techniques can separate signals up to an ambiguity in phase, order, and magnitude—further complicating an extension of common classification methods. Lastly, well-known BSS techniques sometimes fail to properly separate even common digital modulations. The proposed approach to solve these issues comprises of the fastICA BSS technique for signal separation Hyvärinen and Oja (Neural Netw Off J Int Neural Netw Soc 13(4–5):411–430, 2000), fourth and sixth-order cumulants as distinguishing features for several digital modulations, and support vector machines with a radial basis function for classification. Given four common modulation schemes BPSK, QPSK, 8-PSK, and 16-QAM, the proposed approach classifies correctly more than 50% of the time for signal to noise ratios higher than 0 dB.

Original languageEnglish (US)
Pages (from-to)1-7
Number of pages7
JournalAnalog Integrated Circuits and Signal Processing
DOIs
StateAccepted/In press - Nov 28 2017

Fingerprint

Blind source separation
Modulation
Quadrature phase shift keying
Phase shift keying
Quadrature amplitude modulation
Cognitive radio
MIMO systems
Support vector machines
Signal to noise ratio
Communication systems
Antennas

Keywords

  • Blind source separation
  • Fourth-order cumulants
  • Modulation classification
  • Sixth-order cumulants
  • Support vector machine

ASJC Scopus subject areas

  • Signal Processing
  • Hardware and Architecture
  • Surfaces, Coatings and Films

Cite this

Multi-receiver modulation classification for non-cooperative scenarios based on higher-order cumulants. / Vanhoy, Garrett; Asadi, Hamed; Volos, Haris; Bose, Tamal.

In: Analog Integrated Circuits and Signal Processing, 28.11.2017, p. 1-7.

Research output: Contribution to journalArticle

@article{a899c39efbbe4046a9581c164ca641d2,
title = "Multi-receiver modulation classification for non-cooperative scenarios based on higher-order cumulants",
abstract = "Modulation Classification (MC) is a difficult task that can increase awareness in Cognitive Radio (CR) applications. Much of the research in MC has been for single antenna and single user scenarios. With multiple users, blind source separation (BSS) techniques have successfully been used to separate a linear mixture of signals. This work demonstrates that results for MC in a single-user MIMO communications system can be extended to MC in a multi-user scenario with the use of blind source separation techniques. However, a number of difficulties exist with the use of blind source separation techniques that make a simple extension (difficult) possible. First, since the number of users is unknown, BSS techniques must attempt to separate signals with the assumption that a larger number of users exist (than are actually present). Second, BSS techniques can separate signals up to an ambiguity in phase, order, and magnitude—further complicating an extension of common classification methods. Lastly, well-known BSS techniques sometimes fail to properly separate even common digital modulations. The proposed approach to solve these issues comprises of the fastICA BSS technique for signal separation Hyv{\"a}rinen and Oja (Neural Netw Off J Int Neural Netw Soc 13(4–5):411–430, 2000), fourth and sixth-order cumulants as distinguishing features for several digital modulations, and support vector machines with a radial basis function for classification. Given four common modulation schemes BPSK, QPSK, 8-PSK, and 16-QAM, the proposed approach classifies correctly more than 50{\%} of the time for signal to noise ratios higher than 0 dB.",
keywords = "Blind source separation, Fourth-order cumulants, Modulation classification, Sixth-order cumulants, Support vector machine",
author = "Garrett Vanhoy and Hamed Asadi and Haris Volos and Tamal Bose",
year = "2017",
month = "11",
day = "28",
doi = "10.1007/s10470-017-1076-2",
language = "English (US)",
pages = "1--7",
journal = "Analog Integrated Circuits and Signal Processing",
issn = "0925-1030",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Multi-receiver modulation classification for non-cooperative scenarios based on higher-order cumulants

AU - Vanhoy, Garrett

AU - Asadi, Hamed

AU - Volos, Haris

AU - Bose, Tamal

PY - 2017/11/28

Y1 - 2017/11/28

N2 - Modulation Classification (MC) is a difficult task that can increase awareness in Cognitive Radio (CR) applications. Much of the research in MC has been for single antenna and single user scenarios. With multiple users, blind source separation (BSS) techniques have successfully been used to separate a linear mixture of signals. This work demonstrates that results for MC in a single-user MIMO communications system can be extended to MC in a multi-user scenario with the use of blind source separation techniques. However, a number of difficulties exist with the use of blind source separation techniques that make a simple extension (difficult) possible. First, since the number of users is unknown, BSS techniques must attempt to separate signals with the assumption that a larger number of users exist (than are actually present). Second, BSS techniques can separate signals up to an ambiguity in phase, order, and magnitude—further complicating an extension of common classification methods. Lastly, well-known BSS techniques sometimes fail to properly separate even common digital modulations. The proposed approach to solve these issues comprises of the fastICA BSS technique for signal separation Hyvärinen and Oja (Neural Netw Off J Int Neural Netw Soc 13(4–5):411–430, 2000), fourth and sixth-order cumulants as distinguishing features for several digital modulations, and support vector machines with a radial basis function for classification. Given four common modulation schemes BPSK, QPSK, 8-PSK, and 16-QAM, the proposed approach classifies correctly more than 50% of the time for signal to noise ratios higher than 0 dB.

AB - Modulation Classification (MC) is a difficult task that can increase awareness in Cognitive Radio (CR) applications. Much of the research in MC has been for single antenna and single user scenarios. With multiple users, blind source separation (BSS) techniques have successfully been used to separate a linear mixture of signals. This work demonstrates that results for MC in a single-user MIMO communications system can be extended to MC in a multi-user scenario with the use of blind source separation techniques. However, a number of difficulties exist with the use of blind source separation techniques that make a simple extension (difficult) possible. First, since the number of users is unknown, BSS techniques must attempt to separate signals with the assumption that a larger number of users exist (than are actually present). Second, BSS techniques can separate signals up to an ambiguity in phase, order, and magnitude—further complicating an extension of common classification methods. Lastly, well-known BSS techniques sometimes fail to properly separate even common digital modulations. The proposed approach to solve these issues comprises of the fastICA BSS technique for signal separation Hyvärinen and Oja (Neural Netw Off J Int Neural Netw Soc 13(4–5):411–430, 2000), fourth and sixth-order cumulants as distinguishing features for several digital modulations, and support vector machines with a radial basis function for classification. Given four common modulation schemes BPSK, QPSK, 8-PSK, and 16-QAM, the proposed approach classifies correctly more than 50% of the time for signal to noise ratios higher than 0 dB.

KW - Blind source separation

KW - Fourth-order cumulants

KW - Modulation classification

KW - Sixth-order cumulants

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85035151870&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035151870&partnerID=8YFLogxK

U2 - 10.1007/s10470-017-1076-2

DO - 10.1007/s10470-017-1076-2

M3 - Article

AN - SCOPUS:85035151870

SP - 1

EP - 7

JO - Analog Integrated Circuits and Signal Processing

JF - Analog Integrated Circuits and Signal Processing

SN - 0925-1030

ER -