We present a deep learning approach for near real-time detection of Global Navigation Satellite System (GNSS) radio frequency interference (RFI) based on a large amount of aircraft data collected onboard from the Global Positioning System (GPS) and Attitude and Heading Reference System (AHRS). Our approach enables detection of GNSS RFI in the absence of total GPS failure, i.e. while the receiver is still able to estimate a position, which means RFI sources with low power or at larger distance can be detected. We demonstrate how deep one-class classification can be used to detect GNSS RFI. Furthermore, thanks to a unique dataset from the Swiss Air Force and Swiss Air-Rescue (Rega), preprocessed by Swiss Air Navigation Services Ltd. (Skyguide), we demonstrate application of deep learning for GNSS RFI detection on real-world large scale aircraft data containing flight recordings impacted by real jamming. The approach we present is highly general and can be used as a foundation for solving various automated decision-making problems based on different types of Communications, Navigation and Surveillance (CNS) and Air Traffic Management (ATM) streaming data. The experimental results indicate that our system successfully detects GNSS RFI with 83$\,\cdot\,$5% accuracy. Extensive empirical studies demonstrate that the proposed method outperforms strong machine learning and rule-based baselines.

Finding one's geographical position (fix) without the use of a Global Navigation Satellite System (GNSS), which was common place before the establishment of the latter, could be tedious and/or inaccurate. Apart from sound knowledge of spherical trigonometry and navigational methods, it also requires the knowledge of the navigator's approximate or assumed position, the use of the current year's celestial bodies' ephemeris (Nautical Almanac), and graphical methods (Lines of Position – LOP) which sometimes can prove wanting in accuracy and/or challenging for the unaccustomed user. The method proposed here is based on sight reduction from two celestial bodies, and directly calculates the geographical position, both for stationary and moving observers (“running fix”) using easily available modern programmable calculating devices, without the need of the assumed position, graphical methods (LOP) or the current year's ephemeris, hence the term “stand-alone”. This self-contained method is implemented by the author in a software application, which can be easily used in a portable computer (for example, a smartphone). The results are considered satisfactorily accurate.

The importance of the Global Positioning System (GPS) and related electronic systems continues to increase in a range of environmental, engineering and navigation applications. However, civilian GPS signals are vulnerable to Radio Frequency (RF) interference. Spoofing is an intentional intervention that aims to force a GPS receiver to acquire and track invalid navigation data. Analysis of spoofing and authentic signal patterns represents the differences as phase, energy and imaginary components of the signal. In this paper, early-late phase, delta, and signal level as the three main features are extracted from the correlation output of the tracking loop. Using these features, spoofing detection can be performed by exploiting conventional machine learning algorithms such as K-Nearest Neighbourhood (KNN) and naive Bayesian classifier. A Neural Network (NN) as a learning machine is a modern computational method for collecting the required knowledge and predicting the output values in complicated systems. This paper presents a new approach for GPS spoofing detection based on multi-layer NN whose inputs are indices of features. Simulation results on a software GPS receiver showed adequate detection accuracy was obtained from NN with a short detection time.

Navigational error accounts for half of the accidents and serious incidents in close to shore maritime transport in Norway predominantly due to the rapidly changing weather conditions and the dangerous nature of the narrow inshore waters found along the Norwegian coast. This creates a dependence on Differential Global Positioning System (DGPS) use and any disruption to this service can lead to an increased accident rate. The aim of this paper is to research the jamming vulnerability of existing maritime receivers and to understand if an upgrade to a multi-constellation or multi-frequency receiver would improve system resilience. The novelty of this work is a comparison of jamming resilience between different combinations of multiple constellations (GPS and Globalnaya Navigatsionnaya Sputnikovaya Sistema (GLONASS)) and multi-frequency Global Navigation Satellite System (GNSS) signals. This paper presents results from GNSS jamming trials conducted in the northern part of Norway, confirming previous research and indicating that typical maritime GPS receivers are easy to jam and may produce erroneous positional information. Results demonstrate that the single frequency multi-constellation receivers offer better jamming resilience than multi-frequency (L1 + L2) GPS receivers. Further, the GLONASS constellation demonstrated a better resilience than GPS. Results demonstrate a known correlation between GPS L1 and L2 frequencies, as well as a probable over-dependence on GPS for signal acquisition, meaning that no signal can be received without GPS L1 present. With these limitations in mind, the authors suggest that the most economic update to the single frequency GPS receivers, currently used for maritime applications, should be multi-constellation GPS + GLONASS receivers. This solution is cheaper and it also offer better jamming resistance for close to shore navigation than dual frequency receivers.