Jammer Classification in GNSS Bands Via Machine Learning Algorithms

Ruben Morales Ferre; Alberto de la Fuente; Elena Simona Lohan

doi:10.3390/s19224841

Jammer Classification in GNSS Bands Via Machine Learning Algorithms

Ruben Morales Ferre
, Alberto de la Fuente
, Elena Simona Lohan

Research output: Contribution to journal › Article › Scientific › peer-review

110 Citations (Scopus)

37 Downloads (Pure)

Abstract

This paper proposes to treat the jammer classification problem in the Global Navigation Satellite System bands as a black-and-white image classification problem, based on a time-frequency analysis and image mapping of a jammed signal. The paper also proposes to apply machine learning approaches in order to sort the received signal into six classes, namely five classes when the jammer is present with different jammer types and one class where the jammer is absent. The algorithms based on support vector machines show up to 94 . 90 % accuracy in classification, and the algorithms based on convolutional neural networks show up to 91 . 36 % accuracy in classification. The training and test databases generated for these tests are also provided in open access.

Original language	English
Article number	4841
Number of pages	15
Journal	Sensors
Volume	19
Issue number	22
DOIs	https://doi.org/10.3390/s19224841
Publication status	Published - 6 Nov 2019
Publication type	A1 Journal article-refereed

Funding

Funding: This work received funding from the SESAR Joint Undertaking under the European Union’s Horizon 2020 research and innovation program under Grant Agreement No. 783183 (this project is a partnership between GMVInnovating Solutions, Tampere University, and the LINKSFoundation; more details at: https://www.sesarju.eu/node/3107). The opinions expressed herein reflect the authors’ views only. Under no circumstances shall the SESAR Joint Undertaking be responsible for any use that may be made of the information contained herein.

Keywords

Classification
Convolutional Neural Networks (CNN)
Deep learning
Global Navigation Satellite Systems (GNSS)
Image processing
Jamming
Support Vector Machines (SVN)

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Analytical Chemistry
Biochemistry
Atomic and Molecular Physics, and Optics
Instrumentation
Electrical and Electronic Engineering

Access to Document

10.3390/s19224841Licence: CC BY

sensors-19-04841-v2Final published version, 3.3 MBLicence: CC BY

http://urn.fi/URN:NBN:fi:tuni-201911286383Licence: CC BY

Cite this

@article{82c3bb8d4f8b4ab0a8442d130b3640de,

title = "Jammer Classification in GNSS Bands Via Machine Learning Algorithms",

abstract = "This paper proposes to treat the jammer classification problem in the Global Navigation Satellite System bands as a black-and-white image classification problem, based on a time-frequency analysis and image mapping of a jammed signal. The paper also proposes to apply machine learning approaches in order to sort the received signal into six classes, namely five classes when the jammer is present with different jammer types and one class where the jammer is absent. The algorithms based on support vector machines show up to 94 . 90 \% accuracy in classification, and the algorithms based on convolutional neural networks show up to 91 . 36 \% accuracy in classification. The training and test databases generated for these tests are also provided in open access.",

keywords = "Classification, Convolutional Neural Networks (CNN), Deep learning, Global Navigation Satellite Systems (GNSS), Image processing, Jamming, Support Vector Machines (SVN)",

author = "\{Morales Ferre\}, Ruben and \{de la Fuente\}, Alberto and Lohan, \{Elena Simona\}",

note = "Funding Information: Funding: This work received funding from the SESAR Joint Undertaking under the European Union{\textquoteright}s Horizon 2020 research and innovation program under Grant Agreement No. 783183 (this project is a partnership between GMVInnovating Solutions, Tampere University, and the LINKSFoundation; more details at: https://www.sesarju.eu/node/3107). The opinions expressed herein reflect the authors{\textquoteright} views only. Under no circumstances shall the SESAR Joint Undertaking be responsible for any use that may be made of the information contained herein. Publisher Copyright: {\textcopyright} 2019 by the authors. Licensee MDPI, Basel, Switzerland. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.",

year = "2019",

month = nov,

day = "6",

doi = "10.3390/s19224841",

language = "English",

volume = "19",

journal = "Sensors",

issn = "1424-8220",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "22",

}

TY - JOUR

T1 - Jammer Classification in GNSS Bands Via Machine Learning Algorithms

AU - Morales Ferre, Ruben

AU - de la Fuente, Alberto

AU - Lohan, Elena Simona

N1 - Funding Information: Funding: This work received funding from the SESAR Joint Undertaking under the European Union’s Horizon 2020 research and innovation program under Grant Agreement No. 783183 (this project is a partnership between GMVInnovating Solutions, Tampere University, and the LINKSFoundation; more details at: https://www.sesarju.eu/node/3107). The opinions expressed herein reflect the authors’ views only. Under no circumstances shall the SESAR Joint Undertaking be responsible for any use that may be made of the information contained herein. Publisher Copyright: © 2019 by the authors. Licensee MDPI, Basel, Switzerland. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.

PY - 2019/11/6

Y1 - 2019/11/6

N2 - This paper proposes to treat the jammer classification problem in the Global Navigation Satellite System bands as a black-and-white image classification problem, based on a time-frequency analysis and image mapping of a jammed signal. The paper also proposes to apply machine learning approaches in order to sort the received signal into six classes, namely five classes when the jammer is present with different jammer types and one class where the jammer is absent. The algorithms based on support vector machines show up to 94 . 90 % accuracy in classification, and the algorithms based on convolutional neural networks show up to 91 . 36 % accuracy in classification. The training and test databases generated for these tests are also provided in open access.

AB - This paper proposes to treat the jammer classification problem in the Global Navigation Satellite System bands as a black-and-white image classification problem, based on a time-frequency analysis and image mapping of a jammed signal. The paper also proposes to apply machine learning approaches in order to sort the received signal into six classes, namely five classes when the jammer is present with different jammer types and one class where the jammer is absent. The algorithms based on support vector machines show up to 94 . 90 % accuracy in classification, and the algorithms based on convolutional neural networks show up to 91 . 36 % accuracy in classification. The training and test databases generated for these tests are also provided in open access.

KW - Classification

KW - Convolutional Neural Networks (CNN)

KW - Deep learning

KW - Global Navigation Satellite Systems (GNSS)

KW - Image processing

KW - Jamming

KW - Support Vector Machines (SVN)

U2 - 10.3390/s19224841

DO - 10.3390/s19224841

M3 - Article

C2 - 31698860

SN - 1424-8220

VL - 19

JO - Sensors

JF - Sensors

IS - 22

M1 - 4841

ER -

Jammer Classification in GNSS Bands Via Machine Learning Algorithms

Abstract

Funding

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this