Signal classification and jamming detection in wide-band radios using naïve bayes classifier

M. O. Mughal, Sunwoo Kim

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This correspondence proposes a new technique for signal classification and jamming detection in wide-band (WB) radios. Theory of compressed sensing is exploited to recover the sparsely populated WB spectrum from sub-Nyquist samples, thus reducing the very high-rate sampling requirements at the receiver analog to digital converter. From the recovered WB, key spectral features of each narrow-band (NB) signal are extracted. These spectral features are then used to train a simple yet powerful classifier, the naïve Bayes classifier (NBC). The trained NBC is then used not only to classify various NB signals into their respective modulations but also to detect the jamming on different NB signals, which are the main contributions of this letter. The proposed algorithm is then evaluated under different empirical setups and is shown to perform better when compared to a recently proposed feature-based jamming detection algorithm.

Original languageEnglish
Pages (from-to)1398-1401
Number of pages4
JournalIEEE Communications Letters
Volume22
Issue number7
DOIs
StatePublished - 2018 Jul 1

Fingerprint

Bayes Classifier
Radio receivers
Jamming
Classifiers
Compressed sensing
Digital to analog conversion
Modulation
Sampling
Analog-to-digital Converter
Compressed Sensing
Receiver
Correspondence
Classify
Classifier
Requirements

Keywords

  • Wide-band radios
  • compressed sensing
  • jamming detection
  • naïve Bayes classifier

Cite this

@article{5c91fc5580b745ae8bb9ccf21fafb4a5,
title = "Signal classification and jamming detection in wide-band radios using na{\"i}ve bayes classifier",
abstract = "This correspondence proposes a new technique for signal classification and jamming detection in wide-band (WB) radios. Theory of compressed sensing is exploited to recover the sparsely populated WB spectrum from sub-Nyquist samples, thus reducing the very high-rate sampling requirements at the receiver analog to digital converter. From the recovered WB, key spectral features of each narrow-band (NB) signal are extracted. These spectral features are then used to train a simple yet powerful classifier, the na{\"i}ve Bayes classifier (NBC). The trained NBC is then used not only to classify various NB signals into their respective modulations but also to detect the jamming on different NB signals, which are the main contributions of this letter. The proposed algorithm is then evaluated under different empirical setups and is shown to perform better when compared to a recently proposed feature-based jamming detection algorithm.",
keywords = "Wide-band radios, compressed sensing, jamming detection, na{\"i}ve Bayes classifier",
author = "Mughal, {M. O.} and Sunwoo Kim",
year = "2018",
month = "7",
day = "1",
doi = "10.1109/LCOMM.2018.2830769",
language = "English",
volume = "22",
pages = "1398--1401",
journal = "IEEE Communications Letters",
issn = "1089-7798",
number = "7",

}

Signal classification and jamming detection in wide-band radios using naïve bayes classifier. / Mughal, M. O.; Kim, Sunwoo.

In: IEEE Communications Letters, Vol. 22, No. 7, 01.07.2018, p. 1398-1401.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Signal classification and jamming detection in wide-band radios using naïve bayes classifier

AU - Mughal, M. O.

AU - Kim, Sunwoo

PY - 2018/7/1

Y1 - 2018/7/1

N2 - This correspondence proposes a new technique for signal classification and jamming detection in wide-band (WB) radios. Theory of compressed sensing is exploited to recover the sparsely populated WB spectrum from sub-Nyquist samples, thus reducing the very high-rate sampling requirements at the receiver analog to digital converter. From the recovered WB, key spectral features of each narrow-band (NB) signal are extracted. These spectral features are then used to train a simple yet powerful classifier, the naïve Bayes classifier (NBC). The trained NBC is then used not only to classify various NB signals into their respective modulations but also to detect the jamming on different NB signals, which are the main contributions of this letter. The proposed algorithm is then evaluated under different empirical setups and is shown to perform better when compared to a recently proposed feature-based jamming detection algorithm.

AB - This correspondence proposes a new technique for signal classification and jamming detection in wide-band (WB) radios. Theory of compressed sensing is exploited to recover the sparsely populated WB spectrum from sub-Nyquist samples, thus reducing the very high-rate sampling requirements at the receiver analog to digital converter. From the recovered WB, key spectral features of each narrow-band (NB) signal are extracted. These spectral features are then used to train a simple yet powerful classifier, the naïve Bayes classifier (NBC). The trained NBC is then used not only to classify various NB signals into their respective modulations but also to detect the jamming on different NB signals, which are the main contributions of this letter. The proposed algorithm is then evaluated under different empirical setups and is shown to perform better when compared to a recently proposed feature-based jamming detection algorithm.

KW - Wide-band radios

KW - compressed sensing

KW - jamming detection

KW - naïve Bayes classifier

UR - http://www.scopus.com/inward/record.url?scp=85046343698&partnerID=8YFLogxK

U2 - 10.1109/LCOMM.2018.2830769

DO - 10.1109/LCOMM.2018.2830769

M3 - Article

AN - SCOPUS:85046343698

VL - 22

SP - 1398

EP - 1401

JO - IEEE Communications Letters

JF - IEEE Communications Letters

SN - 1089-7798

IS - 7

ER -