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 accuracy in classification, and the algorithms based on convolutional neural networks show up to accuracy in classification. The training and test databases generated for these tests are also provided in open access.
Highlights
Introduction and MotivationJamming threats are increasing in the Global Navigation Satellite System (GNSS) bands.According to recent Eurocontrol Voluntary ATMincident reports [1], the number of Global PositioningSystem (GPS) outages has been increasing exponentially over the past five years, and these numbers are predicted to increase further
The rest of the paper is organized as follows: Section 2 gives a mathematical modeling of the considered jammer types; Section 3 formulates the jammer classification into an image classification problem by using a short-time short-frequency decomposition of the incoming signal; Section 4 gives an overview of the machine learning algorithms we propose to use for the classification purposes; Section 5 presents the results based on Support Vector Machines (SVM) and Convolutional Neural Network (CNN); Section 6 gives the references to the repository where we made our data public; and Section 7 summarizes the findings
Both Machine Learning (ML) algorithms described in Section 4 need a set of images in order to be trained for the later classification
Summary
Introduction and MotivationJamming threats are increasing in the Global Navigation Satellite System (GNSS) bands.According to recent Eurocontrol Voluntary ATMincident reports [1], the number of Global PositioningSystem (GPS) outages has been increasing exponentially over the past five years, and these numbers are predicted to increase further. Jamming threats are increasing in the Global Navigation Satellite System (GNSS) bands. The main cause of GPS outages is the presence of jamming signals in the GPS frequency bands, i.e., L bands around 1.5 GHz carrier frequency. A jamming signal can be typically divided into human-made or channel based. Human-made interferences can be split into intentional (e.g., jamming or spoofing) or unintentional (e.g., interference produced by other systems such as inter-modulation products or radio resource allocation). Channel based interferences involve phenomena such as multi-paths, atmospheric scintillation, or fading. Jamming can be defined as an intentional (usually narrowband) interference in the wireless bands of interest, with received powers of several orders of magnitude higher than the useful received powers, in this case the powers of the GNSS signals. The high received power differences between the jammers and the GNSS signals are due to the fact that the jammers are typically placed on Earth or in the vicinity of the Earth’s surface (e.g., drone installed jammers), while the GNSS satellites are about 19–23 thousands km above the
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
