A Fingerprint-Based Method of Signals and Machine Learning for Identifying Interfering Earth Stations

• Josinaldo Azevedo Military Institute of Engineering
• Paulo C. S. Vidal Military Institute of Engineering
• Ronaldo R. Goldschmidt Military Institute of Engineering

DOI: https://doi.org/10.5753/sbbd.2022.225035

Abstract

Satellite network communications are essential all over the world, and usually they are the only way to bring connectivity to hard-to-reach areas. These networks use wireless links and are affected by harmful interference. A relevant problem is to identify the source of such interference. The main technique for identifying the location of the interference source is the satellite geolocation. This technique reveals a list of suspected earth stations that probably emitted the interference. This work proposes a method that can reduce this list, by using classification models applied to Radio Frequency Fingerprint features extracted from the signals. Such method obtained accuracy above 98\% in experiments with real data involving 64800 signal instances and 6 earth stations.

Keywords: Radio Frequency Fingerprint, Machine Learning, RF, Fingerprint, RFF, Carrier Identification (Id), CID, Radiometric Signature, RF DNA, Satellite, Earth Station, Spectrogram

References

Aggarwal, C. C. et al. (2015). Data mining: the textbook, volume 1. Springer.

Azevedo, J., Barcellos, A. L., Mendes, A. C., de Oliveira, D., Vidal, P. C., and Bedo, M. (2021). Sat-espec: Análise e coleta de dados da transmissão de estações terrenas de uma rede satélite. In Anais do III Dataset Showcase Workshop, pages 43-52. SBBD.

Bitar, N., Muhammad, S., and Refai, H. H. (2018). Wireless technology identification using deep convolutional neural networks. 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC), 1:1-6.

Brik, V. et al. (2008). Wireless device identification with radiometric signatures. 14th ACM international conference on Mobile computing and networking, 1:116-127.

Deng, S. et al. (2017). Radio frequency fingerprint extraction based on multidimension permutation entropy. International Journal of Antennas and Propagation, 2017.

Faceli, K. et al. (2021). Inteligência Artificial: Uma abordagem de aprendizado de máquina. Grupo Gen-LTC.

Gahlawat, S. (2020). Investigation of rf fingerprinting approaches in gnss. Master’s thesis, Tampere University, Faculty of Information Technology, Finlândia.

Hao, C. et al. (2020). Interference geolocation in satellite communications systems: An overview. IEEE Vehicular Technology Magazine, 16(1):66-74.

Henarejos, P. et al. (2019). Deep learning for experimental hybrid terrestrial and satellite interference management. 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 1:1-5.

Huang, H. et al. (2020). Fcn-based carrier signal detection in broadband power spectrum. IEEE Access, 8:113042-113051.

Kennedy, I. et al. (2008). Radio transmitter fingerprinting: A steady state frequency domain approach. 2008 IEEE 68th Vehicular Technology Conference, 1:1-5.

Laignier, P. and Fortes, R. (2009). Introdução à história da comunicação. Ed. E-papers.

Li, Y., Chen, X., Lin, Y., Srivastava, G., and Liu, S. (2020). Wireless transmitter identification based on device imperfections. IEEE Access, 8:59305-59314.

Pratt, T. and Allnutt, J. (2020). Satellite Communication. 2020 John Wiley & Sons Ltd, Virginia, USA, 3 edition.

Smith, R. et al. (2021). An o-ran approach to spectrum sharing between commercial 5g and government satellite systems. In MILCOM 2021-2021 IEEE Military Communications Conference (MILCOM), pages 739-744. IEEE.

Soltanieh, N. et al. (2020). A review of radio frequency fingerprinting techniques. IEEE Journal of Radio Frequency Identification, 4(3):222-233.

UIT (2010). Use of appendix 10 of the radio regulation to convey information related to emissions from both gso and non-gso space stations including geolocation information. 2022-05-31.