Citation: Walenczykowska, M.;
Kawalec, A. Application of
continuous wavelet transform and
artificial naural network for
automatic radar signal recognition
algorithm. Sensors 2022, 22, 7434.
https://doi.org/10.3390/s22197434
Academic Editor: Andrzej Stateczny
Received: 29 August 2022
Accepted: 28 September 2022
Published: 30 September 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Application of Continuous Wavelet Transform and Artificial
Naural Network for Automatic Radar Signal Recognition
Marta Walenczykowska * and Adam Kawalec
Faculty of Mechatronics, Armament and Aerospace, Military University of Technology, 00-908 Warsaw, Poland
* Correspondence: marta.walenczykowska@wat.edu.pl
Abstract:
This article aims to propose an algorithm for the automatic recognition of selected radar
signals. The algorithm can find application in areas such as Electronic Warfare (EW), where automatic
recognition of the type of intra-pulse modulation or the type of emitter operation mode can aid the
decision-making process. The simulations carried out included the analysis of the classification possi-
bilities of linear frequency modulated pulsed waveform (LFMPW), stepped frequency modulated
pulsed waveform (SFMPW), phase coded pulsed waveform (PCPW), rectangular pulsed waveforms
(RPW), frequency modulated continuous wave (FMCW), continuous wave (CW), Stepped Frequency
Continuous Wave SFCW) and Phase Coded Continuous Waveform (PCCW). The algorithm proposed
in this paper is based on the use of continuous wavelet transform (CWT) coefficients and higher-order
statistics (HOS) in the feature determination of selected signals. The Principal Component Analysis
(PCA) method was used for dimensionality reduction. An artificial neural network was then used as a
classifier. Simulation studies took into account the presence of noise interference with signal-to-noise
ratio (SNR) in the range from
−
5 to 10 dB. Finally, the obtained classification efficiency is presented
in the form of a confusion matrix. The simulation results show a high recognition test accuracy, above
99% with a signal-to-noise ratio greater than 0 dB. The article also deals with the selection of the
type and parameters of the wavelet. The authors also point to the problems encountered during the
research and examples of how to solve them.
Keywords:
radar signal recognition; artificial neural network (ANN); continuous wavelet transform
(CWT); automatic signal recognition (AMR); feature extraction
1. Introduction
The modern battlefield requires both an effective threat detection system and a system
enabling their correct classification. The richness of signals in the radio space means that,
both in the case of ELINT and ES, which are elements of EW [
1
], the development of an
effective and fast algorithm for recognizing enemy radars is a key element contributing
to the success of the mission. Fast and appropriate recognition of the signal type and the
related ability to identify the sources of emissions and the mode of their work is one of the
key aspects determining the deployment of forces in military operations. When it comes
to military navigation, the efficient ES allows to recognise and avoid dangers in a timely
manner. The systems, which provide knowledge of the environment and the deployment
of military forces and assets, allow a safe route to be determined, which is particularly
important when navigating in areas of military operations. It can also help to identify
navigation systems interferences. That is why radio-electronic reconnaissance is an integral
part of the fire command and control systems.
In electronic intelligence (ELINT) systems, many emission source parameters, such as
radio frequency (RF), direction of arrival (DOA), time of arrival (TOA), pulse width (PW),
pulse repetition frequency (PRF), intra-pulse modulation, etc. are determined. In paper [
2
]
an instantaneous frequency profile is used to measure the exotic modulations and their
Sensors 2022, 22, 7434. https://doi.org/10.3390/s22197434 https://www.mdpi.com/journal/sensors
