{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T18:05:22Z","timestamp":1780682722811,"version":"3.54.1"},"reference-count":22,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:00Z","timestamp":1780617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Laboratory on Electromagnetic Environment Effects Foundation","award":["6142205240201"],"award-info":[{"award-number":["6142205240201"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>In the multi-class recognition task for unmanned aerial vehicle (UAV) radio frequency (RF) signals, noise interference and complex backgrounds can significantly degrade recognition performance. The stability and accuracy of existing recognition methods often fail to meet the requirements of practical applications. To enhance the stability and accuracy of UAV RF signal recognition, especially to mitigate performance degradation in complex backgrounds, a UAV RF signal classification method, MD-Net, is proposed that integrates Adaptive Time-Frequency Masking and a dual-network architecture. First, an Adaptive Time-Frequency Masking mechanism is constructed. By analyzing the energy distribution of RF signals in the time-frequency domain, the masking region is automatically determined, ensuring that the training data maintains a diverse distribution across different interference scenarios. This significantly improves the model\u2019s anti-interference performance and discriminative stability in complex environments. Subsequently, a dual-branch recognition network architecture is designed, integrating a multi-layer perceptron (MLP) and a long short-term memory (LSTM) network. The MLP extracts static amplitude features from the signals, while the LSTM learns time-series features. These two feature types are then fused to achieve complementary characteristics, ultimately enabling accurate classification of UAV RF signals. Extensive comparative experiments conducted on the DroneRF dataset demonstrate that the MD-Net model achieves an average recognition accuracy of 85.58%, an improvement of 5.27 percentage points over the baseline model. The experimental results show that Adaptive Time-Frequency Masking can effectively enhance the model\u2019s adaptability to real-world interference environments, while the dual-network fusion mechanism fully integrates static amplitude and time-series features, providing a feasible and highly reliable technical approach for UAV RF signal recognition.<\/jats:p>","DOI":"10.3390\/info17060562","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T17:18:16Z","timestamp":1780679896000},"page":"562","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MD-Net: A Lightweight Dual-Branch Network with Adaptive Time-Frequency Masking for Robust UAV RF Signal Classification"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6152-7912","authenticated-orcid":false,"given":"Min","family":"Huang","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2523-4810","authenticated-orcid":false,"given":"Leihan","family":"Dou","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6602-3284","authenticated-orcid":false,"given":"Qiuhong","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,5]]},"reference":[{"key":"ref_1","first-page":"2672","article-title":"A review of radio frequency fingerprint recognition methods for unmanned aerial vehicles","volume":"54","author":"Wang","year":"2024","journal-title":"Radio Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2731","DOI":"10.1109\/TVT.2020.2964110","article-title":"An acoustic-based surveillance system for amateur drones detection and localization","volume":"69","author":"Shi","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1109\/TSP.2022.3229946","article-title":"Ziv\u2013Zakai bound for DOAs estimation","volume":"71","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"11439","DOI":"10.1109\/JSEN.2022.3171293","article-title":"On the detection of unauthorized drones\u2014Techniques and future perspectives: A review","volume":"22","author":"Khan","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_5","first-page":"58","article-title":"Research on unmanned aerial vehicle detection technology","volume":"7","author":"Wang","year":"2024","journal-title":"Eng. Constr."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Alam, S.S., Chakma, A., and Rahman, M.H. (2023). RF-enabled deep-learning-assisted drone detection and identification: An end-to-end approach. Sensors, 23.","DOI":"10.3390\/s23094202"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Aouladhadj, D., Kpre, E., and Deniau, V. (2023). Drone detection and tracking using RF identification signals. Sensors, 23.","DOI":"10.3390\/s23177650"},{"key":"ref_8","first-page":"101028","article-title":"Drone classification using RF signal based spectral features","volume":"28","author":"Kilic","year":"2022","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"ref_9","unstructured":"Yang, L., Camtepe, S., and Gao, Y. (2024). Robustness and security enhancement of radio frequency fingerprint identification in time-varying channels. arXiv."},{"key":"ref_10","unstructured":"Tiras, F.E., and Altinoluk, H.S. (2025). CrossRF: A domain-invariant deep learning approach for RF fingerprinting. arXiv."},{"key":"ref_11","first-page":"1147","article-title":"DroneRFA: A large-scale UAV radio frequency signal dataset for detecting low-altitude UAVs","volume":"46","author":"Yu","year":"2024","journal-title":"J. Electron. Inf. Technol."},{"key":"ref_12","first-page":"69","article-title":"Radio frequency fingerprint extraction method for identity recognition of wireless devices","volume":"24","author":"Zhou","year":"2024","journal-title":"Integr. Circuits Embed. Syst."},{"key":"ref_13","first-page":"919","article-title":"Real-time detection method of unmanned aerial vehicle radio frequency signal under low signal-to-noise ratio conditions","volume":"39","author":"Su","year":"2023","journal-title":"Signal Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.future.2019.05.007","article-title":"RF-based drone detection and identification using deep learning approaches: An initiative towards a large open source drone database","volume":"100","author":"Mohamed","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"104313","DOI":"10.1016\/j.dib.2019.104313","article-title":"DroneRF dataset: A dataset of drones for RF-based detection, classification and identification","volume":"26","author":"Allahham","year":"2019","journal-title":"Data Brief"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Swinney, C.J., and Woods, J.C. (2020, January 29\u201330). Unmanned aerial vehicle flight mode classification using convolutional neural network and transfer learning. Proceedings of the 16th International Computer Engineering Conference (ICENCO), Cairo, Egypt.","DOI":"10.1109\/ICENCO49778.2020.9357368"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bai, H., Li, S., and Jia, Y. (2025). Radio signal recognition using two-stage spatiotemporal network with bispectral analysis. Sensors, 25.","DOI":"10.3390\/s25175449"},{"key":"ref_18","first-page":"301948","article-title":"DRIFTER: A drone identification technique using RF signals","volume":"54","author":"Choudhary","year":"2025","journal-title":"Forensic Sci. Int. Digit. Investig."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Fang, M., Pani, S., and Di Fulvio, A. (2021, January 16\u201323). Enabling PSD-capability for a high-density channel imager. Proceedings of the IEEE Nuclear Science Symposium and Medical Imaging Conference, Piscataway, NJ, USA.","DOI":"10.1109\/NSS\/MIC44867.2021.9875505"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Alqodah, M.A., Tahsin, M., and Omari, M.H. (2024, January 7\u20138). RF-based lightweight machine learning for comprehensive drone activity classification. Proceedings of the 2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, Mt. Pleasant, MI, USA.","DOI":"10.1109\/AIBThings63359.2024.10863363"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Al-Emadi, S., and Al-Senaid, F. (2020, January 2\u20135). Drone detection approach based on radio-frequency using convolutional neural network. Proceedings of the IEEE International Conference on Informatics, IoT, and Enabling Technologies, Doha, Qatar.","DOI":"10.1109\/ICIoT48696.2020.9089489"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"108519","DOI":"10.1016\/j.comnet.2021.108519","article-title":"CNN-SSDI: Convolution neural network inspired surveillance system for UAVs detection and identification","volume":"201","author":"Akter","year":"2021","journal-title":"Comput. Netw."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/6\/562\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T17:43:57Z","timestamp":1780681437000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/6\/562"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,5]]},"references-count":22,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["info17060562"],"URL":"https:\/\/doi.org\/10.3390\/info17060562","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,5]]}}}