RF-UAVNet: High-Performance Convolutional Network for RF-based Drone Surveillance Systems
- 문서 유형
- 연구출판물 · 학술지 논문
- 등재
- SCIEScopus
- 저널 순위
- JCR Q2Scopus Q1
- 저널
- IEEE ACCESS10 · pp.49696 · 2022
- 피인용
- Web of Science 54Scopus 78
- FWCI (Scopus)
- 3.99
- JCR IF
- JCR 2021 3.476
- ISSN
- 2169-3536
저자
- Thien Huynh-The제1저자교신저자Kumoh Natl Inst Technol, ICT Convergence Res Ctr, Gumi Si 39177, Gyeongsangbuk D, South Korea
- 팜쿽비엣Pusan Natl Univ, Korean Southeast Ctr 4th Ind Revolut Leader Educ, Busan 46241, South Korea
- Toan-Van NguyenUtah State Univ, Dept Elect & Comp Engn, Logan, UT 84321 USA
- Da Costa, Daniel BenevidesTechnol Innovat Inst TII, Digital Sci Res Ctr, Abu Dhabi, U Arab Emirates
- Kim, Dong-SeongKumoh Natl Inst Technol, ICT Convergence Res Ctr, Gumi Si 39177, Gyeongsangbuk D, South Korea
초록
AuthorIn recent years, the increasing popularity of unmanned aerial vehicles (UAVs) has arisen from the emergence of cutting-edge technologies deployed in small and low-cost devices. With the great capability of friendly uses and wide applications for multiple purposes, amateur drones can be piloted to effortlessly access any geographical area. This poses some difficulties in monitoring and managing drones that may invade private or limited-access areas. In this paper, we propose a radio-frequency (RF)-based surveillance solution to effectively detect and classify drones, and recognize operations by leveraging a high-performance convolutional neural network. The proposed network, namely RF-UAVNet, is specified with grouped one-dimensional convolution to significantly reduce the network size and computational cost. Besides, a novel structure of multi-level skip-connection, for the preservation of gradient flow, incorporating multi-level pooling, for the collection of informative deep features, is proposed to achieve high accuracy via learning efficiency improvement. In the experiments, RF-UAVNet yields the accuracy of 99.85% for drone detection, 98.53% for drone classification, and 95.33% for operation mode recognition, numbers which outperform the current state-of-the-art deep learning-based methods on DroneRF, a publicly available dataset for RF-based drone surveillance systems.
키워드
Convolutional neural networkdeep learningdrone classificationdrone detectiondrone surveillanceWI-FILOCALIZATIONIDENTIFICATIONRADIOCNN
식별자
- Scopus EID
- 2-s2.0-85129666976
- WoS UID
- 000795578700001



로그인
연구물 목록으로