Multi-UAV RF Signals CNN|Triplet-DNN Heterogeneous Network Feature Extraction and Type Recognition

ZHAO Shen; LI Guangxuan; ZHOU Xiancheng; HUANG Wendi; YANG Lingling; GAO Liping

doi:10.11999/JEIT250757

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2026 >

ZHAO Shen, LI Guangxuan, ZHOU Xiancheng, HUANG Wendi, YANG Lingling, GAO Liping. Multi-UAV RF Signals CNN|Triplet-DNN Heterogeneous Network Feature Extraction and Type Recognition[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT250757

Citation:

ZHAO Shen, LI Guangxuan, ZHOU Xiancheng, HUANG Wendi, YANG Lingling, GAO Liping. Multi-UAV RF Signals CNN|Triplet-DNN Heterogeneous Network Feature Extraction and Type Recognition[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT250757

Citation:

ZHAO Shen, LI Guangxuan, ZHOU Xiancheng, HUANG Wendi, YANG Lingling, GAO Liping. Multi-UAV RF Signals CNN|Triplet-DNN Heterogeneous Network Feature Extraction and Type Recognition[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT250757

PDF( 9615 KB)

Multi-UAV RF Signals CNN|Triplet-DNN Heterogeneous Network Feature Extraction and Type Recognition

doi: 10.11999/JEIT250757 cstr: 32379.14.JEIT250757

1.
School of Xiangjiang Outstanding Engineers, Hunan University of Technology and Business, Changsha 410205, China
2.
School of Intelligent Engineering and Intelligent Manufacturing, Hunan University of Technology and Business, Changsha 410205, China

Funds: National Natural Science Foundation of China(No.62303176), Key Research and Development Plan Project of Hunan Province (No. 2024AQ2033), Natural Science Foundation of Hunan Province (No.2024JJ9188, No.2025JJ90243), Scientific Research Foundation of Hunan Provincial Department of Education (No.21B0577), Postgraduate Research Innovation Project of Hunan Provincial(CX20251684, LXBZZ2024349)

Accepted Date: 2025-12-29

Available Online: 2026-01-15

Abstract

Abstract

Objective To address the detection requirements for multiple types of unmanned aerial vehicles (UAVs) operating simultaneously, the pivotal strategy involves extracting model-specific information features from the radio frequency (RF) time-frequency spectrum. Consequently, an innovative CNN|Triplet-DNN heterogeneous network architecture has been developed to optimize feature extraction and classification methodologies. This solution effectively resolves the challenge of identifying individual models within the coexisting signals of multiple UAVs, thereby laying the groundwork for efficient management and control of multiple UAVs in complex operational environments. Methods The CNN|Triplet-DNN heterogeneous network architecture adopts a parallel-branch structure that integrates convolutional neural network (CNN) and Triplet Convolutional Neural Network (Triplet-CNN) components. Specifically, Branch 1 employs a lightweight CNN architecture to extract global features from RF time-frequency diagrams while minimizing computational complexity. Branch 2 incorporates an enhanced center loss function to improve the discriminative capability of global features, thereby effectively resolving the ambiguity in feature boundaries of time-frequency diagrams under complex scenarios. Branch 3, built on the Triplet-CNN framework, utilizes Triplet Loss to simultaneously capture both local and global features of RF time-frequency diagrams. The complementary features from each branch are subsequently integrated and processed via a DNN fully connected layer combined with the Softmax activation function, generating probability distributions for drone signal classification. This approach significantly enhances the performance of aircraft type recognition and classification. Results and Discussions RF signals from the open-source DroneRFa dataset were superimposed to simulate multi-drone coexistence signals, while real-world drone signals were collected through controlled flight experiments to construct a comprehensive drone signal database. (1) based on the single-drone RF time-frequency diagrams from the open-source dataset, ablation experiments(Fig.7) were conducted on the three-branch structure of CNN|Triplet-DNN model to demonstrate the scientificity and rationality of its design, and each model was trained. (2) the simulated multi-drone coexistence signal dataset was employed for identification tasks to evaluate the recognition performance of each model under multi-drone coexistence scenarios. Experimental results(Fig.10) demonstrate that the recognition accuracy for four or fewer drone types ranges from 83% to 100%, thereby validating the efficacy of the CNN|Triplet-DNN model. (3) Each model was trained using the flight dataset and then applied to identify actual multi-drone coexistence signals. The CNN|Triplet-DNN model achieved(Fig.14) recognition accuracies of 86%, 57%, and 73% for two, three, and four drone types, respectively. Comparative analysis with the CNN, Triplet-CNN, and Transformer reveals that the CNN|Triplet-DNN exhibits superior generalizability. Notably, all models experienced performance degradation when tested against real-world data compared to the open-source dataset, primarily due to the dynamic adjustment of drone communication frequency bands, which adversely affects multi-drone recognition performance. Conclusions To tackle the challenge of coexistence identification for RF signals emitted by multiple UAVs, a novel heterogeneous network architecture integrating CNN|Triplet-DNN is proposed. This model, leveraging a three-branch structural framework and backpropagation algorithm, demonstrates superior capability in extracting discriminative features of aircraft models. The incorporation of DNN significantly enhances the model's generalization capacity. The efficacy and practical applicability of the proposed approach have been validated through comprehensive experiments utilizing open-source datasets and real-world flight scenarios. Future research directions will focus on dataset expansion, model optimization for dynamic communication frequency band adaptation, and enhancement of recognition performance in complex coexistence environments.
- Multi-UAV coexistence,
- UAV type recognition,
- CNN|Triplet-DNN model,
- Radio Frequency (RF) signal,
- Time-Frequency diagram

FullText(HTML)

References(20)

References

[1]	RAHMAN M S, KHALIL I, and ATIQUZZAMAN M. Blockchain-powered policy enforcement for ensuring flight compliance in drone-based service systems[J]. IEEE Network, 2021, 35(1): 116–123. doi: 10.1109/MNET.011.2000219.
[2]	SHAN Lin, MIURA R, MATSUDA T, et al. Vehicle-to-vehicle based autonomous flight coordination control system for safer operation of unmanned aerial vehicles[J]. Drones, 2023, 7(11): 669. doi: 10.3390/drones7110669.
[3]	赵慎, 诸皓冉, 周超, 等. 声学探测无人机中的麦克风立体阵列优化设计[J]. 电子测量与仪器学报, 2025, 39(5): 155–165. doi: 10.13382/j.jemi.B2407714. ZHAO Shen, ZHU Haoran, ZHOU Chao, et al. Optimization design of microphone array for acoustic detection drones[J]. Journal of Electronic Measurement and Instrumentation, 2025, 39(5): 155–165. doi: 10.13382/j.jemi.B2407714.
[4]	CAI Zhenxin, WANG Yu, JIANG Qi, et al. Toward intelligent lightweight and efficient UAV identification with RF fingerprinting[J]. IEEE Internet of Things Journal, 2024, 11(15): 26329–26339. doi: 10.1109/JIOT.2024.3395466.
[5]	MAGANAHALLI G M, MARUTHI A, UTTARKAR C, et al. Neural network-based classification of unmanned aerial vehicle flight modes using convolution and transfer learning[J]. AIP Conference Proceedings, 2025, 3278(1): 020025. doi: 10.1063/5.0262989.
[6]	FENG Junhao, TANG Xiaogang, ZHANG Binquan, et al. A lightweight deep learning RF fingerprint recognition method[C]. Proceedings of the 4th International Conference on Communications, Information System and Computer Engineering, Shenzhen, China, 2022: 452–457. doi: 10.1109/CISCE55963.2022.9851177.
[7]	LI Chaoqun, WANG Jinming, WANG Wenyan, et al. RF-based on feature fusion and convolutional neural network classification of UAVs[C]. Proceedings of the IEEE 8th International Conference on Computer and Communications, Chengdu, China, 2022: 1899–1904. doi: 10.1109/ICCC56324.2022.10065895.
[8]	周景贤, 李希娜. 基于改进卷积神经网络和射频指纹的无人机检测与识别[J]. 计算机应用, 2024, 44(3): 876–882. doi: 10.11772/j.issn.1001-9081.2023030299. ZHOU Jingxian and LI Xina. UAV detection and recognition based on improved convolutional neural network and radio frequency fingerprint[J]. Journal of Computer Applications, 2024, 44(3): 876–882. doi: 10.11772/j.issn.1001-9081.2023030299.
[9]	晏行伟, 孔令轩, 刘坤, 等. 基于MobileNet-DOA的无人机射频信号识别方法[J]. 雷达科学与技术, 2025, 23(1): 57–66. doi: 10.3969/j.issn.1672-2337.2025.01.006. YAN Xingwei, KONG Lingxuan, LIU Kun, et al. Drone radio frequency signal identification method based on MobileNet-DOA[J]. Radar Science and Technology, 2025, 23(1): 57–66. doi: 10.3969/j.issn.1672-2337.2025.01.006.
[10]	曾政智, 周嘉伟, 罗正华. 同频段混合信号中的无人机信号盲检测识别[J]. 电讯技术, 2020, 60(6): 689–694. doi: 10.3969/j.issn.1001-893x.2020.06.013. ZENG Zhengzhi, ZHOU Jiawei, and LUO Zhenghua. Blind detection and recognition of UAV signal in mixed signal in same frequency band[J]. Telecommunication Engineering, 2020, 60(6): 689–694. doi: 10.3969/j.issn.1001-893x.2020.06.013.
[11]	SAZDIĆ-JOTIĆ B, POKRAJAC I, BAJČETIĆ J, et al. Single and multiple drones detection and identification using RF based deep learning algorithm[J]. Expert Systems with Applications, 2022, 187: 115928. doi: 10.1016/j.eswa.2021.115928.
[12]	XU Chengtao, CHEN Bowen, LIU Yongxin, et al. RF fingerprint measurement for detecting multiple amateur drones based on STFT and feature reduction[C]. 2020 Integrated Communications Navigation and Surveillance Conference (ICNS), Herndon, USA, 2020: 4G1. doi: 10.1109/ICNS50378.2020.9223013.
[13]	ZHANG Jiangfan, ZHANG Yan, SHI Zhiguang, et al. Unmanned aerial vehicle object detection based on information-preserving and fine-grained feature aggregation[J]. Remote Sensing, 2024, 16(14): 2590. doi: 10.3390/rs16142590.
[14]	张萌, 李响, 张经纬. 基于图像偏移角和多分支卷积神经网络的旋转不变模型设计[J]. 电子与信息学报, 2024, 46(12): 4522–4528. doi: 10.11999/JEIT240417. ZHANG Meng, LI Xiang, and ZHANG Jingwei. Design of rotation invariant model based on image offset angle and multibranch convolutional neural networks[J]. Journal of Electronics & Information Technology, 2024, 46(12): 4522–4528. doi: 10.11999/JEIT240417.
[15]	ZHENG Yunfei, ZHANG Xuejun, WANG Shenghan, et al. Convolutional neural network and ensemble learning-based unmanned aerial vehicles radio frequency fingerprinting identification[J]. Drones, 2024, 8(8): 391. doi: 10.3390/drones8080391.
[16]	CHA B R and VAIDYA B. Enhancing human activity recognition with Siamese networks: A comparative study of contrastive and triplet learning approaches[J]. Electronics, 2024, 13(9): 1739. doi: 10.3390/electronics13091739.
[17]	SINGH G, STEFENON S F, and YOW K C. The shallowest transparent and interpretable deep neural network for image recognition[J]. Scientific Reports, 2025, 15(1): 13940. doi: 10.1038/s41598-025-92945-2.
[18]	俞宁宁, 毛盛健, 周成伟, 等. DroneRFa: 用于侦测低空无人机的大规模无人机射频信号数据集[J]. 电子与信息学报, 2024, 46(4): 1147–1156. doi: 10.11999/JEIT230570. YU Ningning, MAO Shengjian, ZHOU Chengwei, et al. DroneRFa: A large-scale dataset of drone radio frequency signals for detecting low-altitude drones[J]. Journal of Electronics & Information Technology, 2024, 46(4): 1147–1156. doi: 10.11999/JEIT230570.
[19]	HAN Jia, YU Zhiyong, YANG Jian, et al. Real-world UAV recognition based on radio frequency fingerprinting with transformer[J]. IET Communications, 2025, 19(1): e70004. doi: 10.1049/cmu2.70004.
[20]	ROMAN-RANGEL E and MARCHAND-MAILLET S. Inductive t-SNE via deep learning to visualize multi-label images[J]. Engineering Applications of Artificial Intelligence, 2019, 81: 336–345. doi: 10.1016/j.engappai.2019.01.015.