RF-based drone detection and identification using deep learning approaches: An initiative towards a large open source drone database
Introduction
Commercial unmanned aerial vehicles, or drones, are gaining great popularity over the recent years, thanks to their lower cost, smaller size, lighter weight, higher capabilities, and advancements in batteries and motors. This has rendered drones viable for various applications, such as traffic monitoring [1], [2], weather observation [3], disaster management [4], spraying of agricultural chemicals [5], inspection of infrastructures [6], and fire detection and protection [7]. Drones are remotely controlled using wireless technologies such as Bluetooth, 4G and WiFi; hence, by using off-the-shelf upgrades, drones have become a modular solution. The ubiquitous utility of drones can lead to technical, security, and public safety issues that need to be addressed, regulated and prevented, e.g. spying, transfer of illegal or dangerous goods, disturbing electricity and telephone lines, and assault [8]. Therefore, regulating entities need technologies that are capable of detecting and identifying drones without prior assumption on their type or flight mode.
Conventional methods for detecting and identifying intruding drones, e.g. radars, vision and acoustics, are not solely reliable as they can be easily restrained [9], [10]. Radio frequency (RF) sensing combined with deep learning approaches promised a solution; however, it was hindered by the lack of databases for the RF signals of drones [11]. In this paper, we (1) build a novel open source database for the RF signals of various drones under different flight modes, and (2) test the developed database in a drone detection and identification system designed using deep neural networks. This work is a stepping stone towards a larger database built by a community of researchers to encompass the RF signals of many other drones.
The rest of the paper is organized as follows: Section 2 is an overview of related work. We present in Section 3 the system model and describe our methodologies to build and test the database. In Section 4, we present and discuss results of the drone detection and identification system, and finally, we conclude in Section 5.
Section snippets
Related work
In this Section, we review current anti-drone systems and discuss the need for open source drone databases. Moreover, we review state-of-the-art methods used to detect and identify intruding drones and discuss their applicability in real-life scenarios. Finally, we review the role of deep learning techniques in anti-drone systems and discuss their feasibility to test the developed RF database.
Anti-drone systems: several commercial and military anti-drone systems have been discussed in the
Methodology
In this Section, we present the system model that is used to build up the drone RF database and to test its feasibility in a drone detection and identification system. First, we discuss the subsystems and components of the model and summarize their requirements and roles. After that, we elaborate on the discussion for each component and present the experimental setup to build the drone RF database. Finally, we design a drone detection and identification system using DNNs to test the feasibility
Results and discussions
In this Section, we first present the experimental settings and preprocessing utilized in this work to develop the drone RF database and the RF-based drone detection and identification system. After that, we present snippets from the developed RF database and analyze its spectral information for different drones under different flight modes. Finally, we present and discuss results of the RF-based drone detection and identification system.
Conclusions
As drones are becoming more popular among civilians, regulating entities demand intelligent systems that are capable of detecting and identifying intruding drones. However, the design of such systems is hindered by the lack of large labeled open source databases. This work is a contribution towards this goal by developing a database of drones Radio Frequency (RF) communications that can be further extended by researchers and students. The developed database encompasses RF signals of various
Acknowledgments
This publication was supported by Qatar universityInternal Grant No. QUCP-CENG-2018/2019-1. The work of Aiman Erbad is supported by grant number NPRP 7-1469-1-273. The findings achieved herein are solely the responsibility of the authors.
Declaration of competing interest
No author associated with this paper has disclosed any potential or pertinent conflicts which may be perceived to have impending conflict with this work.
Mohammad Fathi Al-Sa’d received his B.Sc. and M.Sc. degrees in Electrical Engineering from Qatar University, Qatar, in 2012 and 2016 respectively. He specialized in signal processing and graduated with honors under professor Boualem Boashash supervision. He worked as a Research Assistant at Qatar University, and currently he is a Researcher and a Doctoral student at Laboratory of Signal Processing, Tampere University of Technology, Finland. He has served as a technical reviewer for several
References (69)
Dynamic UAV-based traffic monitoring under uncertainty as a stochastic arc-inventory routing policy
Int. J. Transp. Sci. Technol.
(2016)- et al.
Detection of known and unknown DDoS attacks using artificial neural networks
Neurocomputing
(2016) - et al.
Stochastic switched sampled-data control for synchronization of delayed chaotic neural networks with packet dropout
Appl. Math. Comput.
(2018) - et al.
New reliable nonuniform sampling control for uncertain chaotic neural networks under Markov switching topologies
Appl. Math. Comput.
(2019) - et al.
Distribution-balanced stratified cross-validation for accuracy estimation
J. Exp. Theor. Artif. Intell.
(2000) Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation
Pattern Recognit.
(2015)- F. Mohammed, A. Idries, N. Mohamed, J. Al-Jaroodi, I. Jawhar, UAVs for smart cities: Opportunities and challenges, in:...
Coastal and environmental remote sensing from unmanned aerial vehicles: An overview
J. Coast. Res.
(2018)- et al.
Help from the Sky: Leveraging UAVs for disaster management
IEEE Pervasive Comput.
(2017) - et al.
Development and prospect of unmanned aerial vehicle technologies for agricultural production management
Int. J. Agric. Biol. Eng.
(2013)
Visual monitoring of civil infrastructure systems via camera-equipped Unmanned Aerial Vehicles (UAVs): A review of related works
Vis. Eng.
Efficient forest fire detection index for application in unmanned aerial systems (UASs)
Sensors
Anti-drone system with multiple surveillance technologies: Architecture, implementation, and challenges
IEEE Commun. Mag.
An amateur drone surveillance system based on the cognitive internet of things
IEEE Commun. Mag.
Detection, tracking, and interdiction for amateur drones
IEEE Commun. Mag.
UAS detection classification and neutralization: Market survey
Systems engineering baseline concept of a multispectral drone detection solution for airports
IEEE Access
Blind detection: Advanced techniques for WiFi-based drone surveillance
IEEE Trans. Veh. Technol.
Cost-effective and passive RF-based drone presence detection and characterization
GetMobile: Mobile Comp. Comm.
Technologies for efficient amateur drone detection in 5G millimeter-wave cellular infrastructure
IEEE Commun. Mag.
Using shape descriptors for UAV detection
Electron. Imaging
Real-time drone detection using deep learning approach
Drone detection by acoustic signature identification
Electron. Imaging
Cited by (187)
RF/WiFi-based UAV surveillance systems: A systematic literature review
2024, Internet of Things (Netherlands)Deep learning for unmanned aerial vehicles detection: A review
2024, Computer Science ReviewSustainable Drone Detection using Deep Learning Paradigms
2024, E3S Web of ConferencesDrone identification based on the normalized cyclic prefix correlation spectrum
2024, Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian UniversityDroneRFa: A Large-scale Dataset of Drone Radio Frequency Signals for Detecting Low-altitude Drones
2024, Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology
![](https://ars.els-cdn.com/content/image/1-s2.0-S0167739X18330760-pic1.jpg)
Mohammad Fathi Al-Sa’d received his B.Sc. and M.Sc. degrees in Electrical Engineering from Qatar University, Qatar, in 2012 and 2016 respectively. He specialized in signal processing and graduated with honors under professor Boualem Boashash supervision. He worked as a Research Assistant at Qatar University, and currently he is a Researcher and a Doctoral student at Laboratory of Signal Processing, Tampere University of Technology, Finland. He has served as a technical reviewer for several journals, including Biomedical Signal Processing and Control, and IEEE Access. His research interests include EEG analysis and processing, time–frequency array processing, information flow and theory, modeling, optimization and machine learning.
![](https://ars.els-cdn.com/content/image/1-s2.0-S0167739X18330760-pic2.jpg)
Abdullah Al-Ali obtained his master’s degree in software design engineering and Ph.D. degree in Computer Engineering from Northeastern University in Boston, MA, USA in 2008 and 2014, respectively. He is an active researcher in Cognitive Radios for smart cities and vehicular ad-hoc networks (VANETs). He has published several peer-reviewed papers in journals and conferences. Dr. Abdulla is currently head of the Technology Innovation and Engineering Education (TIEE) at the College of Engineering in Qatar University.
![](https://ars.els-cdn.com/content/image/1-s2.0-S0167739X18330760-pic3.jpg)
Amr Mohamed received his M.S. and Ph.D. in electrical and computer engineering from the University of British Columbia, Vancouver, Canada, in 2001, and 2006 respectively. His research interests include wireless networking, edge computing, and security for IoT applications. Dr. Amr Mohamed has co-authored over 160 refereed journal and conference papers, patents, textbook, and book chapters in reputed international journals, and conferences. He is serving as a technical editor in two international journals and has been part of the organizing committee of many international conferences as a symposia co-chair e.g. IEEE Globecom’16.
![](https://ars.els-cdn.com/content/image/1-s2.0-S0167739X18330760-pic4.jpg)
Tamer Khattab received the B.Sc. and M.Sc. degrees from Cairo University, Giza, Egypt, and the Ph.D. degree from The University of British Columbia, Vancouver, BC, Canada, in 2007. From 1994 to 1999, he was with IBM wtc, Giza, Egypt. From 2000 to 2003, he was with Nokia Networks, Burnaby, BC, Canada. He joined Qatar University in 2007, where he is currently an Associate Professor of Electrical Engineering. He is also a senior member of the technical staff with Qatar Mobility Innovation Center. His research interests cover physical layer security techniques, information theoretic aspects of communication systems, and radar and RF sensing techniques.
![](https://ars.els-cdn.com/content/image/1-s2.0-S0167739X18330760-pic5.jpg)
Aiman Erbad is an Associate Professor at the Computer Science and Engineering (CSE) Department and the Director of Research Planning and Development at Qatar University. Dr. Erbad obtained a Ph.D. in Computer Science from the University of British Columbia (Canada), and a Master of Computer Science in Embedded Systems and Robotics from the University of Essex (UK). Dr. Erbad received the Platinum award from H.H. The Emir Sheikh Tamim bin Hamad Al Thani at the Education Excellence Day 2013 (Ph.D. category). Dr. Erbad research interests span cloud computing, multimedia systems and networking, and his research is published in reputed international conferences and journals.
- 1
This work was done while Mohammad F. Al-Sa’d was with the Computer Science and Engineering Department, Qatar University, Doha, Qatar.