# Machine Learning Framework for RF-Based Drone Detection and Identification System

arXiv: https://arxiv.org/abs/2003.02656 · HTML: https://mlsanity.com/paper/2003.02656/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2020.

## Built on by (most cited first, 6 of 6)

- [Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions](https://mlsanity.com/paper/2504.11967/) (2025)
- [Advance and Refinement: The Evolution of UAV Detection and Classification Technologies](https://mlsanity.com/paper/2409.05985/) (2024)
- [URANUS: Radio Frequency Tracking, Classification and Identification of Unmanned Aircraft Vehicles](https://mlsanity.com/paper/2207.06025/) (2022)
- [One-shot Generative Distribution Matching for Augmented RF-based UAV Identification](https://mlsanity.com/paper/2301.08403/) (2023)
- [A Two-Dimensional Deep Network for RF-based Drone Detection and Identification Towards Secure Coverage Extension](https://mlsanity.com/paper/2308.13906/) (2023)
- [CageDroneRF: A Large-Scale RF Benchmark and Toolkit for Drone Perception](https://mlsanity.com/paper/2601.03302/) (2026)

## Abstract (arXiv)

The emergence of drones has added new dimension to privacy and security issues. There are little or no strict regulations on the people that can purchase or own a drone. For this reason, people can take advantage of these aircraft to intrude into restricted or private areas. A Drone Detection and Identification (DDI) system is one of the ways of detecting and identifying the presence of a drone in an area. DDI systems can employ different sensing technique such radio frequency (RF) signals, video, sounds and thermal for detecting an intruding drone. In this work, we propose a machine learning RF-based DDI system that uses low band RF signals from drone-to-flight controller communication. We develop three machine learning models using the XGBoost algorithm to detect and identify the presence of a drone, the type of drones and the operational mode of drones. For these three XGBoost models, we evaluated the models using 10-fold cross validation and we achieve average accuracy of 99.96%, 90.73% and 70.09% respectively.