GNSS Interference Spectrum Highway Dataset 2

Citation Author(s):
Felix
Ott
Fraunhofer Institute for Integrated Circuits IIS
Lucas
Heublein
Fraunhofer Institute for Integrated Circuits IIS
Alexander
Rügamer
Fraunhofer Institute for Integrated Circuits IIS
Submitted by:
Felix Ott
Last updated:
Tue, 11/12/2024 - 03:22
DOI:
10.21227/eaxr-qg80
Data Format:
Research Article Link:
Links:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

Jamming devices pose a significant threat by disrupting signals from the global navigation satellite system (GNSS), compromising the robustness of accurate positioning. Detecting anomalies in frequency snapshots is crucial to counteract these interferences effectively. The ability to adapt to diverse, unseen interference characteristics is essential for ensuring the reliability of GNSS in real-world applications. We recorded a dataset with our own sensor station at a German highway with two interference classes and one non-interference class. This dataset allows the development and evaluation of machine learning methods, such as domain adaptation, few-shot learning, and continual learning.

 

Instructions: 

Introduction

We publish the Spectrum Highway Dataset 2 that was recorded close to a German highway and contains a variety of interference classes in GNSS signals from spectral hardware. For the dataset recording, we developed a hardware setup that captures short, wideband snapshots in both E1 and E6 GNSS bands. This setup is mounted to a bridge over a highway. We place two sensor stations with a distance of 1km next to a highway. The setup records 20ms raw IQ snapshots triggered from the energy with a sample rate of 62.5MHz, an analog bandwidth of 50MHz and an 8bit bit-width. See the following visualization of the highway lanes of the real-world highway dataset 2. The car with integrated jammers drove from north to south and from south to north, each with two lanes.

Dataset

The repository contains the Spectrum Highway Dataset 2 with the corresponding labels in .txt files for the train-test split. One sample in the text file is defined as for example:

data/157369.npy 0

For classical ML methods, use the train.txt and test.txt dataset to train and evaluate your model.

At certain frequencies the GPS/Galileo or GLONASS signals can easily be seen as a slight increase in the spectrum. Note that experts manually analyzed the datastreams by thresholding CN/0 and AGC values.

License

This work is licensed under a CC BY-NC-SA 4.0: Creative Commons Attribution-Noncommercial-ShareAlike, see https://creativecommons.org/licenses/by-nc-sa/4.0/

Further Datasets & Methods

For more information on the dataset, links to other datasets, and our methodologies, visit the following Gitlab page: https://gitlab.cc-asp.fraunhofer.de/darcy_gnss

Funding Agency: 
This work has been carried out within the DARCII project, funding code 50NA2401, supported by the German Federal Ministry for Economic Affairs and Climate Action (BMWK), managed by the German Space Agency at DLR.
Grant Number: 
50NA2401

Comments

For an alternative download possibility, see the following Gitlab website:

https://gitlab.cc-asp.fraunhofer.de/darcy_gnss/fiot_highway2

 

Submitted by Felix Ott on Mon, 11/11/2024 - 15:54