Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-29214
Publikationstyp: | Konferenz: Paper |
Art der Begutachtung: | Peer review (Publikation) |
Titel: | Robust drone detection and classification from radio frequency signals using convolutional neural networks |
Autor/-in: | Glüge, Stefan Nyfeler, Matthias Ramagnano, Nicola Horn, Claus Schüpbach, Christof |
et. al: | No |
DOI: | 10.5220/0012176800003595 10.21256/zhaw-29214 |
Tagungsband: | Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA |
Herausgeber/-in des übergeordneten Werkes: | van Stein, Niki Marcelloni, Francesco Lam, H.K. Filipe, Joaquim |
Seite(n): | 496 |
Seiten bis: | 504 |
Angaben zur Konferenz: | 15th International Joint Conference on Computational Intelligence (IJCCI), Rome, Italy, 13-15 November 2023 |
Erscheinungsdatum: | Nov-2023 |
Verlag / Hrsg. Institution: | SciTePress |
Verlag / Hrsg. Institution: | Setubal |
ISBN: | 978-989-758-674-3 |
ISSN: | 2184-3236 |
Sprache: | Englisch |
Schlagwörter: | Deep learning; Robustness; Signal detection; Unmanned aerial vehicle |
Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
Zusammenfassung: | As the number of unmanned aerial vehicles (UAVs) in the sky increases, safety issues have become more pressing. In this paper, we compare the performance of convolutional neural networks (CNNs) using first, 1D in-phase and quadrature (IQ) data and second, 2D spectrogram data for detection and classification of UAVs based on their radio frequency (RF) signals. We focus on the robustness of the models to low signal-to-noise ratios (SNRs), as this is the most relevant aspect for a real-world application. Within an input type, either IQ or spectrogram, we found no significant difference in performance between models, even as model complexity increased. In addition, we found an advantage in favor of the 2D spectrogram representation of the data. While there is basically no performance difference at SNRs ≥ 0 dB, we observed a 100% improvement in balanced accuracy at −12 dB, i.e. 0.842 on the spectrogram data compared to 0.413 on the IQ data for the VGG11 model. Together with an easy-to-use benchmark dataset, our findings can be used to develop better models for robust UAV detection systems. |
URI: | https://digitalcollection.zhaw.ch/handle/11475/29214 |
Zugehörige Forschungsdaten: | https://www.kaggle.com/datasets/sgluege/noisy-drone-rf-signal-classification |
Volltext Version: | Publizierte Version |
Lizenz (gemäss Verlagsvertrag): | CC BY-NC-ND 4.0: Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International |
Departement: | Life Sciences und Facility Management |
Organisationseinheit: | Institut für Computational Life Sciences (ICLS) |
Publiziert im Rahmen des ZHAW-Projekts: | Drone Signal Dataset |
Enthalten in den Sammlungen: | Publikationen Life Sciences und Facility Management |
Dateien zu dieser Ressource:
Datei | Beschreibung | Größe | Format | |
---|---|---|---|---|
2023_Gluege-etal_Robust-drone-detection-classification-radio-frequency_NCTA.pdf | 3.65 MB | Adobe PDF | Öffnen/Anzeigen |
Zur Langanzeige
Glüge, S., Nyfeler, M., Ramagnano, N., Horn, C., & Schüpbach, C. (2023). Robust drone detection and classification from radio frequency signals using convolutional neural networks [Conference paper]. In N. van Stein, F. Marcelloni, H. K. Lam, & J. Filipe (Eds.), Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA (pp. 496–504). SciTePress. https://doi.org/10.5220/0012176800003595
Glüge, S. et al. (2023) ‘Robust drone detection and classification from radio frequency signals using convolutional neural networks’, in N. van Stein et al. (eds) Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA. Setubal: SciTePress, pp. 496–504. Available at: https://doi.org/10.5220/0012176800003595.
S. Glüge, M. Nyfeler, N. Ramagnano, C. Horn, and C. Schüpbach, “Robust drone detection and classification from radio frequency signals using convolutional neural networks,” in Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA, Nov. 2023, pp. 496–504. doi: 10.5220/0012176800003595.
GLÜGE, Stefan, Matthias NYFELER, Nicola RAMAGNANO, Claus HORN und Christof SCHÜPBACH, 2023. Robust drone detection and classification from radio frequency signals using convolutional neural networks. In: Niki VAN STEIN, Francesco MARCELLONI, H.K. LAM und Joaquim FILIPE (Hrsg.), Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA. Conference paper. Setubal: SciTePress. November 2023. S. 496–504. ISBN 978-989-758-674-3
Glüge, Stefan, Matthias Nyfeler, Nicola Ramagnano, Claus Horn, and Christof Schüpbach. 2023. “Robust Drone Detection and Classification from Radio Frequency Signals Using Convolutional Neural Networks.” Conference paper. In Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA, edited by Niki van Stein, Francesco Marcelloni, H.K. Lam, and Joaquim Filipe, 496–504. Setubal: SciTePress. https://doi.org/10.5220/0012176800003595.
Glüge, Stefan, et al. “Robust Drone Detection and Classification from Radio Frequency Signals Using Convolutional Neural Networks.” Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA, edited by Niki van Stein et al., SciTePress, 2023, pp. 496–504, https://doi.org/10.5220/0012176800003595.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.