Abstract
With the development of technology and the decrease in costs, drones are now becoming easily accessible to the public. As the accessibility of this technology continues to grow, the concerns of security and surveillance increase, and to ensure a sense of security, the need to have reliable drone detection and identification systems is more urgent than ever. Besides, many civilian applications have been found for drones, which play a huge role in modern security and warfare. Unauthorized drones can be very dangerous regarding security issues, as they can be used for spying, smuggling, or even attacks against critical infrastructure. We propose a deep learning-based framework for radio frequency (RF) signal classification, using spectrogram representations. The framework utilizes pretrained transfer learning architectures, specifically ResNet-50V2, ResNet-101V2, Inception-V3, and InceptionResNetV2. Advanced techniques such as global average pooling, global max pooling, dense layers, batch normalization layers, and dropout layers are used to optimize the performance. We evaluate the proposed model on a publicly available DroneRF dataset with detection accuracy of 100%, 100% in drone identification, and 91.11% in drone flight mode classification. We also validated the model on another dataset to learn the generalization ability and robustness. The proposed model outperforms existing state-of-the-art techniques designed for RF drone detection and identification.
Recommended Citation
P. Podder et al., "Enhanced UAV Surveillance with RF-Based Drone Identification using Transfer Learning," Proceedings of the ACM Symposium on Applied Computing, pp. 2055 - 2064, Jun 2026.
The definitive version is available at https://doi.org/10.1145/3748522.3779761
Department(s)
Electrical and Computer Engineering
Publication Status
Open Access
Keywords and Phrases
accuracy; drone detection; drone mode; F1 score; inception V3; InceptionResNetV2; resnet; RF signals; spectrogram; transfer learning
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2026, All rights reserved.
Creative Commons Licensing
This work is licensed under a Creative Commons Attribution 4.0 License.
Publication Date
09 Jun 2026
Comments
Army Research Laboratory, Grant W911NF-22-2- 0208