Classification of modulation signals using statistical signal characterization and artificial neural networks

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Modulation recognition systems have to be able to correctly classify the incoming signal modulation scheme in the presence of noise. A new method for classification of analogue and digital modulated signals at low signal-to-noise ratio (SNR) is introduced in this paper. This method uses the statistical signal characterization (SSC) to extract parameters to classify the different modulation signals. The SSC technique produces a set of four numerical parameters for a specific modulated signal. Subsequent comparison of these parameters to those of other waveforms provides the basis for our classification system. The results of SSC technique are applied to an artificial neural network (ANN) to have a robust classification system in the presence of noise down to SNR of 3 dB. No a priori information is required by this technique about the set of input waveforms. The input to the classification system can be analogue or digital signals or a combination of both. The proposed technique shows a 100% efficiency of classification of analogue signals or digital signals at SNR of 7 dB. This classification efficiency reduces to 83% and 86% for analogue or digital signals at SNR of 3 dB. The SSC technique shows better classification results in comparison with other techniques with an important advantage over other methods, which is the simplicity of the neural network needed with this technique due to the small number of features used in the classification.

Original languageEnglish
Pages (from-to)463-472
Number of pages10
JournalEngineering Applications of Artificial Intelligence
Volume20
Issue number4
DOIs
Publication statusPublished - Jun 2007

Fingerprint

Modulation
Neural networks
Signal to noise ratio

Keywords

  • Artificial neural networks
  • Modulation classification
  • Pattern recognition
  • Statistical signal characterization

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

@article{eae918741d64423bab1a973105964f73,
title = "Classification of modulation signals using statistical signal characterization and artificial neural networks",
abstract = "Modulation recognition systems have to be able to correctly classify the incoming signal modulation scheme in the presence of noise. A new method for classification of analogue and digital modulated signals at low signal-to-noise ratio (SNR) is introduced in this paper. This method uses the statistical signal characterization (SSC) to extract parameters to classify the different modulation signals. The SSC technique produces a set of four numerical parameters for a specific modulated signal. Subsequent comparison of these parameters to those of other waveforms provides the basis for our classification system. The results of SSC technique are applied to an artificial neural network (ANN) to have a robust classification system in the presence of noise down to SNR of 3 dB. No a priori information is required by this technique about the set of input waveforms. The input to the classification system can be analogue or digital signals or a combination of both. The proposed technique shows a 100{\%} efficiency of classification of analogue signals or digital signals at SNR of 7 dB. This classification efficiency reduces to 83{\%} and 86{\%} for analogue or digital signals at SNR of 3 dB. The SSC technique shows better classification results in comparison with other techniques with an important advantage over other methods, which is the simplicity of the neural network needed with this technique due to the small number of features used in the classification.",
keywords = "Artificial neural networks, Modulation classification, Pattern recognition, Statistical signal characterization",
author = "Abdulnasir Hossen and Fakhri Al-Wadahi and Jervase, {Joseph A.}",
year = "2007",
month = "6",
doi = "10.1016/j.engappai.2006.08.004",
language = "English",
volume = "20",
pages = "463--472",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Classification of modulation signals using statistical signal characterization and artificial neural networks

AU - Hossen, Abdulnasir

AU - Al-Wadahi, Fakhri

AU - Jervase, Joseph A.

PY - 2007/6

Y1 - 2007/6

N2 - Modulation recognition systems have to be able to correctly classify the incoming signal modulation scheme in the presence of noise. A new method for classification of analogue and digital modulated signals at low signal-to-noise ratio (SNR) is introduced in this paper. This method uses the statistical signal characterization (SSC) to extract parameters to classify the different modulation signals. The SSC technique produces a set of four numerical parameters for a specific modulated signal. Subsequent comparison of these parameters to those of other waveforms provides the basis for our classification system. The results of SSC technique are applied to an artificial neural network (ANN) to have a robust classification system in the presence of noise down to SNR of 3 dB. No a priori information is required by this technique about the set of input waveforms. The input to the classification system can be analogue or digital signals or a combination of both. The proposed technique shows a 100% efficiency of classification of analogue signals or digital signals at SNR of 7 dB. This classification efficiency reduces to 83% and 86% for analogue or digital signals at SNR of 3 dB. The SSC technique shows better classification results in comparison with other techniques with an important advantage over other methods, which is the simplicity of the neural network needed with this technique due to the small number of features used in the classification.

AB - Modulation recognition systems have to be able to correctly classify the incoming signal modulation scheme in the presence of noise. A new method for classification of analogue and digital modulated signals at low signal-to-noise ratio (SNR) is introduced in this paper. This method uses the statistical signal characterization (SSC) to extract parameters to classify the different modulation signals. The SSC technique produces a set of four numerical parameters for a specific modulated signal. Subsequent comparison of these parameters to those of other waveforms provides the basis for our classification system. The results of SSC technique are applied to an artificial neural network (ANN) to have a robust classification system in the presence of noise down to SNR of 3 dB. No a priori information is required by this technique about the set of input waveforms. The input to the classification system can be analogue or digital signals or a combination of both. The proposed technique shows a 100% efficiency of classification of analogue signals or digital signals at SNR of 7 dB. This classification efficiency reduces to 83% and 86% for analogue or digital signals at SNR of 3 dB. The SSC technique shows better classification results in comparison with other techniques with an important advantage over other methods, which is the simplicity of the neural network needed with this technique due to the small number of features used in the classification.

KW - Artificial neural networks

KW - Modulation classification

KW - Pattern recognition

KW - Statistical signal characterization

UR - http://www.scopus.com/inward/record.url?scp=33947113331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947113331&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2006.08.004

DO - 10.1016/j.engappai.2006.08.004

M3 - Article

AN - SCOPUS:33947113331

VL - 20

SP - 463

EP - 472

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

IS - 4

ER -