{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T11:56:18Z","timestamp":1790769378197,"version":"4.1.0"},"reference-count":27,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301581"],"award-info":[{"award-number":["62301581"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301578"],"award-info":[{"award-number":["62301578"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["62301581"],"award-info":[{"award-number":["62301581"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"award":["62301578"],"award-info":[{"award-number":["62301578"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Radar signal sorting is a fundamental task in passive electromagnetic sensing that separates pulses emitted by multiple radars from densely interleaved streams. Existing supervised deep learning methods often require large labeled datasets and iterative optimization, limiting their applicability in non-cooperative, latency-sensitive electronic-support-measure scenarios. This article proposes a dual-layer multi-head attention broad learning system (DMHA-BLS). Conventional random feature mapping is replaced by two attention blocks with fixed random-orthogonal query, key, and value projections. A residual branch maps first-layer attention features to the input dimension through closed-form ridge regression, preserving physical pulse attributes. The output weights are also solved analytically, and accumulated Gram statistics enable batchwise updates. On an 8000-pulse simulated stream, DMHA-BLS reaches 83.17% macro F1 with 200 samples and 91.88% with 8000 samples. It provides a clear advantage over the temporal baselines in the small-sample condition, while their performance gradually approaches DMHA-BLS as the number of labeled pulses increases. In a second 1000-pulse scenario with eight emitters and strongly overlapping PDW ranges, DMHA-BLS remains the top-performing method across the evaluated sample sizes. Full-data training requires 1.57 s, compared with 100\u2013109 s for the evaluated deep networks, indicating a favorable trade-off between sorting performance and computational efficiency.<\/jats:p>","DOI":"10.3390\/s26196201","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T10:59:25Z","timestamp":1790765965000},"page":"6201","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Radar Signal Sorting via a Dual-Layer Multi-Head Attention Broad Learning System"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3964-913X","authenticated-orcid":false,"given":"Longkun","family":"Kuang","sequence":"first","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3927-167X","authenticated-orcid":false,"given":"Xuan","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1369-7818","authenticated-orcid":false,"given":"Mingyang","family":"Du","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0188-1842","authenticated-orcid":false,"given":"Zhihui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9910-0663","authenticated-orcid":false,"given":"Junpeng","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"writing-review-editing","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"ref_1","unstructured":"Wiley, R.G. (2006). ELINT: The Interception and Analysis of Radar Signals, Artech House."},{"key":"ref_2","unstructured":"Adamy, D.L. (2001). EW 101: A First Course in Electronic Warfare, Artech House."},{"key":"ref_3","unstructured":"Barton, D.K. (2004). Radar System Analysis and Modeling, Artech House."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4093","DOI":"10.1109\/TAES.2025.3650737","article-title":"Radar Signal Deinterleaving with Progressive Correlation-Integrated Neural Network","volume":"62","author":"Chen","year":"2026","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1049\/ip-f-2.1989.0025","article-title":"New techniques for the deinterleaving of repetitive sequences","volume":"136","author":"Mardia","year":"1989","journal-title":"IEE Proc. F Radar Signal Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1049\/ip-f-2.1992.0012","article-title":"Improved algorithm for the deinterleaving of radar pulses","volume":"139","year":"1992","journal-title":"IEE Proc. F Radar Signal Process."},{"key":"ref_7","first-page":"73","article-title":"Special purpose correlation functions for improved signal detection and parameter estimation","volume":"Volume 4","author":"Nelson","year":"1993","journal-title":"Proceedings of the 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing, Minneapolis, MN, USA, April 1993"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1109\/7.845217","article-title":"Improved algorithm for estimating pulse repetition intervals","volume":"36","author":"Nishiguchi","year":"2000","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1049\/iet-rsn.2017.0516","article-title":"Improved method for deinterleaving radar signals and estimating PRI values","volume":"12","author":"Liu","year":"2018","journal-title":"IET Radar Sonar Navig."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6818","DOI":"10.1049\/joe.2019.0593","article-title":"Deinterleaving method of complex staggered PRI radar signals based on EDW fusion","volume":"2019","author":"Tian","year":"2019","journal-title":"J. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Manickchand, K., Strydom, J.J., and Mishra, A.K. (2017). Comparative study of TOA based emitter deinterleaving and tracking algorithms. Proceedings of the 2017 IEEE AFRICON, Cape Town, South Africa, 18\u201320 September 2017, IEEE.","DOI":"10.1109\/AFRCON.2017.8095485"},{"key":"ref_12","first-page":"55","article-title":"Radar signal pre-sorting based on K-means algorithm","volume":"26","author":"Xiaowei","year":"2013","journal-title":"Electron. Sci. Technol."},{"key":"ref_13","first-page":"2463","article-title":"Connected K-nearest neighbor clustering algorithm for radar signal sorting","volume":"45","author":"Si","year":"2023","journal-title":"Syst. Eng. Electron."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2956","DOI":"10.1109\/TAES.2024.3481212","article-title":"A Radar Signal Deinterleaving Method Based on Enhanced Sparse Subspace Clustering","volume":"61","author":"Guo","year":"2024","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1624","DOI":"10.1109\/TAES.2018.2874139","article-title":"Classification, denoising, and deinterleaving of pulse streams with recurrent neural networks","volume":"55","author":"Liu","year":"2018","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3585","DOI":"10.1109\/TAES.2021.3079571","article-title":"Pulse deinterleaving for multifunction radars with hierarchical deep neural networks","volume":"57","author":"Liu","year":"2021","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5806","DOI":"10.1109\/TSP.2022.3229630","article-title":"A radar signal deinterleaving method based on semantic segmentation with neural network","volume":"70","author":"Wang","year":"2022","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1109\/TAES.2021.3122411","article-title":"Model-based representation and deinterleaving of mixed radar pulse sequences with neural machine translation network","volume":"58","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1109\/LSP.2024.3519884","article-title":"Radar signal sorting via graph convolutional network and semi-supervised learning","volume":"32","author":"Li","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"9327","DOI":"10.1109\/TAES.2025.3555244","article-title":"Deinterleaving of Intercepted Radar Pulse Streams Via Temporal Convolutional Attention Network","volume":"61","author":"Wang","year":"2025","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/TNNLS.2017.2716952","article-title":"Broad learning system: An effective and efficient incremental learning system without the need for deep architecture","volume":"29","author":"Chen","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1109\/TCYB.2018.2857815","article-title":"Fuzzy broad learning system: A novel neuro-fuzzy model for regression and classification","volume":"50","author":"Feng","year":"2018","journal-title":"IEEE Trans. Cybern."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.1109\/TCYB.2018.2863020","article-title":"Recurrent broad learning systems for time series prediction","volume":"50","author":"Xu","year":"2018","journal-title":"IEEE Trans. Cybern."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"108324","DOI":"10.1016\/j.compchemeng.2023.108324","article-title":"Adaptive cascade enhancement broad learning system combined with stacked correlation information autoencoder for soft sensor modeling of industrial process","volume":"177","author":"Ni","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.neucom.2021.07.065","article-title":"Graph-based broad learning system for classification","volume":"463","author":"Liu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"109831","DOI":"10.1016\/j.asoc.2022.109831","article-title":"Multi-Attn BLS: Multi-head attention mechanism with broad learning system for chaotic time series prediction","volume":"132","author":"Su","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Buatoom, U., Kongprawechnon, W., and Theeramunkong, T. (2018). Constrained clustering with seeds and term weighting scheme. Proceedings of the 2018 Thirteenth International Conference on Knowledge, Information and Creativity Support Systems (KICSS), Pattaya, Thailand, 15\u201317 November 2018, IEEE.","DOI":"10.1109\/KICSS45055.2018.8950598"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6201\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T11:04:12Z","timestamp":1790766252000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6201"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":27,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196201"],"URL":"https:\/\/doi.org\/10.3390\/s26196201","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]}}}