Multimodal Learning for Reliable Interference Classification in GNSS Signals

Brieger, Tobias; Raichur, Nisha Lakshmana; Jdidi, Dorsaf; Ott, Felix; Feigl, Tobias; Merwe, J. Rossouw van der; Rügamer, Alexander; Felber, Wolfgang

doi:10.33012/2022.18586

Cited by 5 publications

(16 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GNSS receiver outputs monitoring and signal spectrum monitoring methods complement each other [ 13 , 49 , 56 , 57 ]. For example, GNSS receiver monitoring may yield false detection when a receiver is indoors and has low CN0 values, but spectrum monitoring would reveal no interference.…”

Section: Background To Interference Monitoringmentioning

confidence: 99%

“…Traditional classification has several limitations: the effort of deriving and tuning optimal detectors, the inability to adapt to new waveforms without new development, high processing costs, and complex logic trees. The latest state-of-the-art techniques employ ML or deep learning (DL) methods to compensate for these weaknesses and to reliably and accurately classify interference signals [ 36 , 43 , 57 , 58 ]. Modern ML- and DL-based methods are on par with or even superior to classical techniques in practical situations, as these methods learn non-deterministic and non-linear correlations from data.…”

Section: Background To Interference Monitoringmentioning

confidence: 99%

“…The performance of ResNet18 and TS-Transformer on data that more accurately reflect the complexities of real-world scenarios, including multipath effects, variable distances and power levels, motion dynamics, and real-world noise, remains to be determined. Based on the current literature, CNNs are a viable approach as they treat the spectrogram of a signal as an image [ 57 , 62 , 65 ], which facilitates image classification approaches from the computer science literature. Statistical methods incorporating a more diverse range of pre-processed features may benefit using SVMs [ 66 , 67 ].…”

Section: Background To Interference Monitoringmentioning

confidence: 99%

“…These three boards are interesting candidates for improving the system, but there are many other COTS SDR RFFEs [ 93 ]. An RFFE with more dynamic range, larger bandwidth, or better clocking stability leads to superior detection and classification capabilities or combining it with other sensors [ 57 , 94 ].…”

Section: Hardware Designmentioning

confidence: 99%

“…Compared with the original implementation [ 36 ], the ML pipeline is slightly tuned through experience with realistic experiments [ 43 , 57 , 58 , 94 ]. It is now more adequate for handling different data input types, i.e., time series such as C/N0, AGC, and elevation and images of spectrograms.…”

Section: Algorithmic Designmentioning

confidence: 99%

See 4 more Smart Citations

Low-Cost COTS GNSS Interference Monitoring, Detection, and Classification System

Merwe

Franco

Hansen

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Interference signals cause position errors and outages to global navigation satellite system (GNSS) receivers. However, to solve these problems, the interference source must be detected, classified, its purpose determined, and localized to eliminate it. Several interference monitoring solutions exist, but these are expensive, resulting in fewer nodes that may miss spatially sparse interference signals. This article introduces a low-cost commercial-off-the-shelf (COTS) GNSS interference monitoring, detection, and classification receiver. It employs machine learning (ML) on tailored signal pre-processing of the raw signal samples and GNSS measurements to facilitate a generalized, high-performance architecture that does not require human-in-the-loop (HIL) calibration. Therefore, the low-cost receivers with high performance can justify significantly more receivers being deployed, resulting in a significantly higher probability of intercept (POI). The architecture of the monitoring system is described in detail in this article, including an analysis of the energy consumption and optimization. Controlled interference scenarios demonstrate detection and classification capabilities exceeding conventional approaches. The ML results show that accurate and reliable detection and classification are possible with COTS hardware.

show abstract

Section: Background To Interference Monitoringmentioning

confidence: 99%