EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Advancing Drone Detection: Innovative Radio Frequency-CNN Fusion for Accurate Drone Detection and Identification

Afshan Ishaq, Mian Jehanzeb

Mehran University Research Journal of Engineering and Technology · 2026

DOI: 10.22581/0161 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mehran University Research Journal of Engineering and Technology, 2026. Verfasst von Afshan Ishaq und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of unmanned aerial vehicles (UAVs) has raised significant concerns about security, privacy, and unauthorized surveillance. This paper presents a proposed advanced Radio Frequency (RF)-Convolutional Neural Network (CNN) fusion model to improve the accuracy of UAV detection and identification. The proposed framework employs a deep 1D CNN trained on normalized RF amplitude data, with dropout regularization and 10-fold cross-validation to enhance generalization and result stability. The developed model can identify the signature of the UAV communication in the RF signal much better than the traditional detection strategy like radar and acoustic analysis through the application of deep learning tools on RF signal analysis and without the need for interpretation with RF signal analysis software. The suggested RF-CNN model has the highest accuracy and F1-score of 99.67% and 99.7 respectively, and that indicates its reliability and strength. Also, the UAV identification model achieves 88.39% accuracy with an F1-score of 88.4 which is better than the current RF-based UAV detection models. It has a low Root Mean Square Error (RMSE) of 0.003, indicating that the model has few classification errors; hence, it can be used in real-time drone monitoring. In contrast to the conventional techniques, the suggested RF-based deep learning model has scalable implementation, less computation complexity, and environmental adaptability. The results of this study provide practical implications to the airspace security, protection of critical infrastructure, and counter-drone technologies to facilitate the creation of sound AI-based surveillance systems on UAVs.

Zitieren

APA

Ishaq, A., & Jehanzeb, M. (2026). Advancing Drone Detection: Innovative Radio Frequency-CNN Fusion for Accurate Drone Detection and Identification. Mehran University Research Journal of Engineering and Technology. https://doi.org/10.22581/0161

Vancouver

Ishaq A, Jehanzeb M. Advancing Drone Detection: Innovative Radio Frequency-CNN Fusion for Accurate Drone Detection and Identification. Mehran University Research Journal of Engineering and Technology. 2026. doi:10.22581/0161

BibTeX
@article{Ishaq2026,
  author = {Ishaq, Afshan and Jehanzeb, Mian},
  title = {Advancing Drone Detection: Innovative Radio Frequency-CNN Fusion for Accurate Drone Detection and Identification},
  journal = {Mehran University Research Journal of Engineering and Technology},
  year = {2026},
  doi = {10.22581/0161}
}
Kostenlos starten →