Deep Complex-Valued Convolutional Neural Network for Drone Recognition Based on RF Fingerprinting
Drone-aided ubiquitous applications play important roles in our daily lives. Accurate recognition of drones is required in aviation management due to their potential risks and disasters. Radiofrequency (RF) fingerprinting-based recognition technology based on deep learning (DL) is considered an effe...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/6/12/374 |
| _version_ | 1827640882993561600 |
|---|---|
| author | Jie Yang Hao Gu Chenhan Hu Xixi Zhang Guan Gui Haris Gacanin |
| author_facet | Jie Yang Hao Gu Chenhan Hu Xixi Zhang Guan Gui Haris Gacanin |
| author_sort | Jie Yang |
| collection | DOAJ |
| description | Drone-aided ubiquitous applications play important roles in our daily lives. Accurate recognition of drones is required in aviation management due to their potential risks and disasters. Radiofrequency (RF) fingerprinting-based recognition technology based on deep learning (DL) is considered an effective approach to extracting hidden abstract features from the RF data of drones. Existing deep learning-based methods are either high computational burdens or have low accuracy. In this paper, we propose a deep complex-valued convolutional neural network (DC-CNN) method based on RF fingerprinting for recognizing different drones. Compared with existing recognition methods, the DC-CNN method has a high recognition accuracy, fast running time, and small network complexity. Nine algorithm models and two datasets are used to represent the superior performance of our system. Experimental results show that our proposed DC-CNN can achieve recognition accuracies of 99.5% and 74.1%, respectively, on four and eight classes of RF drone datasets. |
| first_indexed | 2024-03-09T17:05:48Z |
| format | Article |
| id | doaj.art-c0af0635cba0416e84e71fcf010e0954 |
| institution | Directory Open Access Journal |
| issn | 2504-446X |
| language | English |
| last_indexed | 2024-03-09T17:05:48Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj.art-c0af0635cba0416e84e71fcf010e09542023-11-24T14:24:35ZengMDPI AGDrones2504-446X2022-11-0161237410.3390/drones6120374Deep Complex-Valued Convolutional Neural Network for Drone Recognition Based on RF FingerprintingJie Yang0Hao Gu1Chenhan Hu2Xixi Zhang3Guan Gui4Haris Gacanin5College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaNational ASIC System Engineering Research Center, School of Electronic Science and Engineering, Southeast University, Nanjing 210096, ChinaGlasgow College, University of Electronic Science and Technology of China, Chengdu 611731, ChinaCollege of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaCollege of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaFaculty of Electrical Engineering and Information Technology, RWTH Aachen University, 55-52062 Aachen, GermanyDrone-aided ubiquitous applications play important roles in our daily lives. Accurate recognition of drones is required in aviation management due to their potential risks and disasters. Radiofrequency (RF) fingerprinting-based recognition technology based on deep learning (DL) is considered an effective approach to extracting hidden abstract features from the RF data of drones. Existing deep learning-based methods are either high computational burdens or have low accuracy. In this paper, we propose a deep complex-valued convolutional neural network (DC-CNN) method based on RF fingerprinting for recognizing different drones. Compared with existing recognition methods, the DC-CNN method has a high recognition accuracy, fast running time, and small network complexity. Nine algorithm models and two datasets are used to represent the superior performance of our system. Experimental results show that our proposed DC-CNN can achieve recognition accuracies of 99.5% and 74.1%, respectively, on four and eight classes of RF drone datasets.https://www.mdpi.com/2504-446X/6/12/374drone recognitionRF fingerprintingdeep learningdeep complex-valued networkconvolutional neural networkphysical layer security |
| spellingShingle | Jie Yang Hao Gu Chenhan Hu Xixi Zhang Guan Gui Haris Gacanin Deep Complex-Valued Convolutional Neural Network for Drone Recognition Based on RF Fingerprinting Drones drone recognition RF fingerprinting deep learning deep complex-valued network convolutional neural network physical layer security |
| title | Deep Complex-Valued Convolutional Neural Network for Drone Recognition Based on RF Fingerprinting |
| title_full | Deep Complex-Valued Convolutional Neural Network for Drone Recognition Based on RF Fingerprinting |
| title_fullStr | Deep Complex-Valued Convolutional Neural Network for Drone Recognition Based on RF Fingerprinting |
| title_full_unstemmed | Deep Complex-Valued Convolutional Neural Network for Drone Recognition Based on RF Fingerprinting |
| title_short | Deep Complex-Valued Convolutional Neural Network for Drone Recognition Based on RF Fingerprinting |
| title_sort | deep complex valued convolutional neural network for drone recognition based on rf fingerprinting |
| topic | drone recognition RF fingerprinting deep learning deep complex-valued network convolutional neural network physical layer security |
| url | https://www.mdpi.com/2504-446X/6/12/374 |
| work_keys_str_mv | AT jieyang deepcomplexvaluedconvolutionalneuralnetworkfordronerecognitionbasedonrffingerprinting AT haogu deepcomplexvaluedconvolutionalneuralnetworkfordronerecognitionbasedonrffingerprinting AT chenhanhu deepcomplexvaluedconvolutionalneuralnetworkfordronerecognitionbasedonrffingerprinting AT xixizhang deepcomplexvaluedconvolutionalneuralnetworkfordronerecognitionbasedonrffingerprinting AT guangui deepcomplexvaluedconvolutionalneuralnetworkfordronerecognitionbasedonrffingerprinting AT harisgacanin deepcomplexvaluedconvolutionalneuralnetworkfordronerecognitionbasedonrffingerprinting |