Compared Transformer and CNN architectures for detecting drones from RF signatures, and showed that the DroneRF benchmark's data-splitting protocol materially inflates reported accuracy. Published on Zenodo, DOI 10.5281/zenodo.22847365.
Project
RF-Based Counter-UAS Detection
Transformers vs. CNNs for detecting drones from RF, and a benchmark flaw that inflates accuracy.
CompletedResearch
Have a platform, a dataset, and a problem?
Tell us the hardware, the sensors, and the constraint. We'll come back within a week with a scoped proposal.
Book a scoping call (opens in a new tab)