CNN-SSDI: Convolution neural network inspired surveillance system for UAVs detection and identification

Akter, Rubina; Doan, Van‐Sang; Lee, Jae-Min; Kim, Dong-Seong

doi:10.1016/j.comnet.2021.108519

Cited by 28 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [11], the authors propose a deep learning method for detecting malicious drones using image and audio data. Similarly, in [12], deep learning-based drone detection and type recognition based on radio frequency emissions are proposed. The goal of this study is to find and identify illegal drones that could endanger civilians.…”

Section: Introductionmentioning

confidence: 99%

Performance Enhancement of Optimized Link State Routing Protocol by Parameter Configuration for UANET

Tuli

Golam

Kim

et al. 2022

Drones

Self Cite

View full text Add to dashboard Cite

The growing need for wireless communication has resulted in the widespread usage of unmanned aerial vehicles (UAVs) in a variety of applications. Designing a routing protocol for UAVs is paramount as well as challenging due to its dynamic attributes. The difficulty stems from features other than mobile ad hoc networks (MANET), such as aerial mobility in 3D space and frequently changing topology. This paper analyzes the performance of four topology-based routing protocols, dynamic source routing (DSR), ad hoc on-demand distance vector (AODV), geographic routing protocol (GRP), and optimized link state routing (OLSR), by using practical simulation software OPNET 14.5. Performance evaluation carries out various metrics such as throughput, delay, and data drop rate. Moreover, the performance of the OLSR routing protocol is enhanced and named “E-OLSR” by tuning parameters and reducing holding time. The optimized E-OLSR settings provide better performance than the conventional request for comments (RFC 3626) in the experiment, making it suitable for use in UAV ad hoc network (UANET) environments. Simulation results indicate the proposed E-OLSR outperforms the existing OLSR and achieves supremacy over other protocols mentioned in this paper.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance Enhancement of Optimized Link State Routing Protocol by Parameter Configuration for UANET

Tuli

Golam

Kim

et al. 2022

Drones

Self Cite

View full text Add to dashboard Cite

show abstract

“…In an analogous vein, a distinct open drone dataset was harnessed in [9], presenting raw RF signals originating from drones across four distinct scenarios. This extensive dataset encompassed a total of 227 segments, amounting to a formidable 40GB of data captured within the 2.4GHz ISM band.…”

Section: Radar-based Methodsmentioning

confidence: 99%

Drone detection with radio frequency signals and deep learning models

Dai

2024

ACE

View full text Add to dashboard Cite

The widespread use of drones raises security, environmental, privacy, and ethical issues; therefore, effective detection by drones is important. There are several methods for detecting drones, such as wireless signal detection, photoelectric detection, radar detection, and sound detection. However, these detection methods are not accurate enough to identify drones for use. To solve this question, more robust drone detection method are needed. In addition, for different types of drones and application scenarios, different technical means need to be used for detection and identification. Based on 2-class ,4-class and 10-class problems on an open ratio frequency (RF) signal dataset, we compared the drone detection and classification performances of different machine learning with deep learning models and multi-task models which is proposed by combining different RF methods with Convolutional neural networks (CNNs). Our experimental results show that the XGBoost model achieved the latest results on this groundbreaking dataset, with 99.96% accuracy for 2-class problem, 92.31% accuracy for 4-class problem, and 74.81% accuracy for 10-class problem, which exhibits the best performance for drone detection and classification.

show abstract

“…These aerial systems have garnered substantial attention due to their versatile applications in various fields. One prominent application is target tracking, where UAVs are employed for tasks such as surveillance in [1], rescue operations in [2], protection in [3], and patrol in [4,5]. Among the various applications of UAVs in target tracking, target encirclement and tracking has emerged as a prominent research hotspot [6].…”

Section: Introductionmentioning

confidence: 99%

Event‐triggered cooperative control for moving target encirclement and tracking with time‐varying pattern by UAV formation

Jia,

Chen,

Wang

et al. 2023

IET Control Theory & Appl

View full text Add to dashboard Cite

This paper investigates an event‐triggered cooperative control policy of moving‐target encirclement and tracking with time‐varying radius commands for unmanned aerial vehicle (UAV) formation. Different from the existing works, this study takes into account the relative motion model between the UAVs and the target in order to design a guidance law specifically tailored for moving‐target encirclement and tracking. Additionally, a time‐varying radius command is introduced, allowing the radius of the circular orbit formed by the UAVs around the target to adjust according to the commands. This flexibility and adaptability enhance the UAV formation's performance in complex work scenes and unstructured geometric spaces. To address the concerns of communication and computing costs associated with time‐triggered guidance laws, an event‐triggered method is proposed for dynamic target encirclement and tracking, eliminating the occurrence of Zeno behaviour. The stability of the proposed guidance laws is mathematically proven using the interconnected systems lemma. Finally, the effectiveness of the controllers is verified by some simulations.

show abstract

CNN-SSDI: Convolution neural network inspired surveillance system for UAVs detection and identification

Cited by 28 publications

References 32 publications

Performance Enhancement of Optimized Link State Routing Protocol by Parameter Configuration for UANET

Performance Enhancement of Optimized Link State Routing Protocol by Parameter Configuration for UANET

Drone detection with radio frequency signals and deep learning models

Event‐triggered cooperative control for moving target encirclement and tracking with time‐varying pattern by UAV formation

Contact Info

Product

Resources

About