{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:31:04Z","timestamp":1784737864888,"version":"3.55.0"},"reference-count":34,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Major scientific and technological innovation projects of Shandong Province of China","award":["2022ZLGX04"],"award-info":[{"award-number":["2022ZLGX04"]}]},{"name":"Major scientific and technological innovation projects of Shandong Province of China","award":["2021ZLGX05"],"award-info":[{"award-number":["2021ZLGX05"]}]},{"name":"Major scientific and technological innovation projects of Shandong Province of China","award":["62071144"],"award-info":[{"award-number":["62071144"]}]},{"name":"National Natural Science Foundation of China","award":["2022ZLGX04"],"award-info":[{"award-number":["2022ZLGX04"]}]},{"name":"National Natural Science Foundation of China","award":["2021ZLGX05"],"award-info":[{"award-number":["2021ZLGX05"]}]},{"name":"National Natural Science Foundation of China","award":["62071144"],"award-info":[{"award-number":["62071144"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Addressing the issue of inadequate convergence and suboptimal accuracy in classical data-driven algorithms for coherent polarization\u2013direction-of-arrival (DOA) estimation, a novel high-precision two-dimensional coherent polarization\u2013DOA estimation method utilizing a sequence-embedding fusion (SEF) transformer is proposed for the first time. Drawing inspiration from natural language processing (NLP), this approach employs transformer-based multitasking text inference to facilitate joint estimation of polarization and DOA. This method leverages the multi-head self-attention mechanism of the transformer to effectively capture the multi-dimensional features within the spatial-polarization domain of the covariance matrix data. Additionally, an SEF module was proposed to fuse the spatial-polarization domain features from different dimensions. The module is a combination of a convolutional neural network (CNN) with local information extraction capabilities and a feature dimension transformation function, serving to improve the model\u2019s ability to fuse information about features in the spatial-polarization domain. Moreover, to enhance the model\u2019s expressive capacity, we designed a multi-task parallel output mode and a multi-task weighted loss function. Simulation results demonstrate that our method outperforms classical data-driven approaches in both accuracy and generalization, and the estimation accuracy of our method is improved relative to the traditional model-driven algorithm.<\/jats:p>","DOI":"10.3390\/rs16213977","type":"journal-article","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T10:50:08Z","timestamp":1729853408000},"page":"3977","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Two-Dimensional Coherent Polarization\u2013Direction-of-Arrival Estimation Based on Sequence-Embedding Fusion Transformer"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3233-5318","authenticated-orcid":false,"given":"Zihan","family":"Wu","sequence":"first","affiliation":[{"name":"School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150000, China"},{"name":"School of Information Science and Engineering, Harbin Institute of Technology, Weihai 264209, China"},{"name":"Key Laboratory of Cross-Domain Synergy and Comprehensive Support for Unmanned Marine Systems, Ministry of Industry and Information Technology, Weihai 264209, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150000, China"},{"name":"School of Information Science and Engineering, Harbin Institute of Technology, Weihai 264209, China"},{"name":"Key Laboratory of Cross-Domain Synergy and Comprehensive Support for Unmanned Marine Systems, Ministry of Industry and Information Technology, Weihai 264209, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiquan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150000, China"},{"name":"School of Information Science and Engineering, Harbin Institute of Technology, Weihai 264209, China"},{"name":"Key Laboratory of Cross-Domain Synergy and Comprehensive Support for Unmanned Marine Systems, Ministry of Industry and Information Technology, Weihai 264209, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1109\/TAP.1986.1143830","article-title":"Multiple emitter location and signal parameter estimation","volume":"34","author":"Schmidt","year":"1986","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1109\/29.32276","article-title":"ESPRIT-estimation of signal parameters via rotational invariance techniques","volume":"37","author":"Roy","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2330","DOI":"10.1109\/TSP.2012.2187519","article-title":"DoA and polarization estimation for arbitrary array configurations","volume":"60","author":"Costa","year":"2012","journal-title":"IEEE Trans. Signal Process"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2628","DOI":"10.1109\/78.229894","article-title":"Analysis of a signal estimation algorithm for diversely polarized arrays","volume":"41","author":"Weiss","year":"1993","journal-title":"IEEE Trans. Signal Process"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1109\/TSP.2020.2964213","article-title":"The extended manifold for antenna arrays","volume":"68","author":"Friedlander","year":"2020","journal-title":"IEEE Trans. Signal Process"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1049\/iet-rsn:20050108","article-title":"Polarimetric angular smoothing algorithm for an electromagnetic vector-sensor array","volume":"1","author":"Xu","year":"2007","journal-title":"IET Radar Sonar Navig."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1109\/JSEE.2012.00061","article-title":"Direction finding of coexisted independent and coherent signals using electromagnetic vector sensor","volume":"23","author":"Diao","year":"2012","journal-title":"J. Syst. Eng. Electron"},{"key":"ref_8","first-page":"835","article-title":"Joint angle-polarization estimation via generalized signal-subspace fitting","volume":"30","author":"Xu","year":"2010","journal-title":"Trans. Beijing Inst. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1110","DOI":"10.1109\/78.80966","article-title":"Sensor array processing based on subspace fitting","volume":"39","author":"Viberg","year":"1991","journal-title":"IEEE Trans. Signal Process"},{"key":"ref_10","first-page":"281","article-title":"Doa estimation in non-uniform noise using matrix completion via alternating projection","volume":"2","author":"Fei","year":"2021","journal-title":"IEEE OJAP"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pavel, S.R., Chowdhury, M.W.T., Zhang, Y.D., Shen, D., and Chen, G. (November, January 31). Machine learning-based direction-of-arrival estimation exploiting distributed sparse arrays. Proceedings of the IEEE 2021 55th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA.","DOI":"10.1109\/IEEECONF53345.2021.9723401"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2279","DOI":"10.1109\/TAP.2009.2024485","article-title":"An innovative multiresolution approach for DOA estimation based on a support vector classification","volume":"57","author":"Donelli","year":"2009","journal-title":"IEEE T. Antenn. Propag."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4901","DOI":"10.1109\/TAP.2012.2209195","article-title":"A support vector machine MUSIC algorithm","volume":"60","author":"Christodoulou","year":"2012","journal-title":"IEEE T. Antenn. Propag."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/dac.4882","article-title":"Direction of arrival estimation in multipath environments using deep learning","volume":"34","author":"Harkouss","year":"2021","journal-title":"Int. J. Commun. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3714","DOI":"10.1109\/TSP.2021.3089927","article-title":"Deep networks for direction-of-arrival estimation in low SNR","volume":"69","author":"Papageorgiou","year":"2021","journal-title":"IEEE Trans. Signal Proc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1109\/LSP.2019.2901641","article-title":"Coherent SVR learning for wideband direction-of-arrival estimation","volume":"26","author":"Wu","year":"2019","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ahmed, A.M., Eissa, O., and Sezgin, A. (2020, January 6\u20137). Deep autoencoders for DOA estimation of coherent sources using imperfect antenna array. Proceedings of the 2020 Third International Workshop on Mobile Terahertz Systems (IWMTS), Essen, Germany.","DOI":"10.1109\/IWMTS49292.2020.9166332"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.1109\/LSP.2021.3096117","article-title":"Unsupervised learning strategy for direction-of-arrival estimation network","volume":"28","author":"Yuan","year":"2021","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5068","DOI":"10.1109\/TVT.2020.2977894","article-title":"Improved de-multipath neural network models with self-paced feature-to-feature learning for DOA estimation in multipath environment","volume":"69","author":"Xiang","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"82329","DOI":"10.1109\/ACCESS.2019.2924156","article-title":"A novel phase enhancement method for low-angle estimation based on supervised DNN learning","volume":"7","author":"Xiang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2411","DOI":"10.1007\/s10489-020-01678-4","article-title":"Phase enhancement model based on supervised convolutional neural network for coherent DOA estimation","volume":"50","author":"Xiang","year":"2020","journal-title":"Appl. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/LCOMM.2020.3032733","article-title":"Angle separation learning for coherent DOA estimation with deep sparse prior","volume":"25","author":"Xiang","year":"2020","journal-title":"IEEE Commun. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7315","DOI":"10.1109\/TAP.2018.2874430","article-title":"Direction-of-arrival estimation based on deep neural networks with robustness to array imperfections","volume":"66","author":"Liu","year":"2018","journal-title":"IEEE T. Antenn. Propag."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wu, Z., and Wang, J. (2023). Small Sample Coherent DOA Estimation Method Based on S2S Neural Network Meta Reinforcement Learning. Sensors, 23.","DOI":"10.3390\/s23031546"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"26183","DOI":"10.1109\/ACCESS.2024.3360306","article-title":"Shortcut Learning Explanations for Deep Natural Language Processing: A Survey on Dataset Biases","volume":"12","author":"Dogra","year":"2024","journal-title":"IEEE Access"},{"key":"ref_26","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inform. Proc. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/LSP.2023.3342628","article-title":"Dual Class Token Vision Transformer for Direction of Arrival Estimation in Low SNR","volume":"31","author":"Guo","year":"2023","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_28","first-page":"3614","article-title":"Multi-task learning for dense prediction tasks: A survey","volume":"44","author":"Vandenhende","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"J. Big Data"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hussain, A.A., Tayem, N., and Soliman, A.H. (2021, January 4\u20135). FPGA hardware implementation of computationally efficient DOA estimation of coherent signals. Proceedings of the 2021 International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET) IEEE, Bali, Indonesia.","DOI":"10.1109\/ICRAMET53537.2021.9650476"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TVLSI.2024.3462467","article-title":"Hardware\u2013Algorithm Codesigned Low-Latency and Resource-Efficient OMP Accelerator for DOA Estimation on FPGA","volume":"10","author":"Jiang","year":"2024","journal-title":"IEEE Trans. Very Large Scale Integr. (VLSI) Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"48865","DOI":"10.1109\/ACCESS.2024.3382994","article-title":"Channel Pruning Method Based on Decoupling Feature Scale Distribution in Batch Normalization Layers","volume":"12","author":"Qiu","year":"2024","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1109\/LSP.2024.3353039","article-title":"Transformer-Based End-to-End Speech Translation With Rotary Position Embedding","volume":"31","author":"Li","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Valsecchi, C., Consonni, V., Todeschini, R., Orlandi, M.E., Gosetti, F., and Ballabio, D. (2021). Parsimonious Optimization of Multitask Neural Network Hyperparameters. Molecules, 26.","DOI":"10.3390\/molecules26237254"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/21\/3977\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:20:50Z","timestamp":1760113250000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/21\/3977"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"references-count":34,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2024,11]]}},"alternative-id":["rs16213977"],"URL":"https:\/\/doi.org\/10.3390\/rs16213977","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]}}}