{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T07:14:25Z","timestamp":1766819665283,"version":"build-2065373602"},"reference-count":30,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T00:00:00Z","timestamp":1678752000000},"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":["6207011332"],"award-info":[{"award-number":["6207011332"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper proposes a joint estimation method for source number and DOA based on an improved convolutional neural network for unknown source number and undetermined DOA estimation. By analyzing the signal model, the paper designs a convolutional neural network model based on the existence of a mapping relationship between the covariance matrix and both the source number and DOA estimation. The model, which discards the pooling layer to avoid data loss and introduces the dropout method to improve generalization, takes the signal covariance matrix as input and the two branches of source number estimation and DOA estimation as outputs, and achieves the unfixed number of DOA estimation by filling in invalid values. Simulation experiments and analysis of the results show that the algorithm can effectively achieve the joint estimation of source number and DOA. Under the conditions of high SNR and a large snapshot number, both the proposed algorithm and the traditional algorithm have high estimation accuracy, while under the conditions of low SNR and a small snapshot, the algorithm is better than the traditional algorithm, and under the underdetermined conditions, where the traditional algorithm often fails, the algorithm can still achieve the joint estimation.<\/jats:p>","DOI":"10.3390\/s23063100","type":"journal-article","created":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T06:14:58Z","timestamp":1678774498000},"page":"3100","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Research on Underdetermined DOA Estimation Method with Unknown Number of Sources Based on Improved CNN"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0421-5917","authenticated-orcid":false,"given":"Fangzheng","family":"Zhao","sequence":"first","affiliation":[{"name":"Graduate School, Air Force Engineering University, Xi\u2019an 710043, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7939-4588","authenticated-orcid":false,"given":"Guoping","family":"Hu","sequence":"additional","affiliation":[{"name":"Air and Missile Defense College, Air Force Engineering University, Xi\u2019an 710043, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Air and Missile Defense College, Air Force Engineering University, Xi\u2019an 710043, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhan","family":"Guo","sequence":"additional","affiliation":[{"name":"Graduate School, Air Force Engineering University, Xi\u2019an 710043, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,14]]},"reference":[{"key":"ref_1","unstructured":"Vincenzo, P., and Sandeep, R. (2021). Trends in Deep Learning Methodologies, Academic Press."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1631\/FITEE.1900527","article-title":"Artificial intelligence and wireless communications","volume":"21","author":"Wang","year":"2020","journal-title":"Front. Inform. Technol. Electron. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","article-title":"A new look at the statistical identification model","volume":"19","author":"Akaike","year":"1974","journal-title":"IEEE Trans. Autom. Contr."},{"key":"ref_4","unstructured":"Veen, A., Romme, J., and Ye, C. (2021, January 18\u201321). Rank Detection Thresholds for Hankel or Toeplitz Data Matrices. Proceedings of the 2020 28th European Signal Processing Conference (EUSIPCO), Amsterdam, The Netherlands."},{"key":"ref_5","first-page":"53","article-title":"Research on Source Number Estimation based on Geschgorin Disk Estimator Theorem and Minimum Description Length Criterion","volume":"33","author":"Xu","year":"2017","journal-title":"J. Signal Process."},{"key":"ref_6","first-page":"109","article-title":"An Improved Source Number Estimation Algorithm Based on Geschgorin Disk Estimator Criterion","volume":"40","author":"Chu","year":"2018","journal-title":"J. Detect. Control."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"108502","DOI":"10.1016\/j.apacoust.2021.108502","article-title":"Experimental study on the performance of DOA estimation algorithm using a coprime acoustic sensor array without a priori knowledge of the source number","volume":"186","author":"Dong","year":"2022","journal-title":"Appl. Acoust."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.sigpro.2017.05.008","article-title":"Joint DOA estimation and source number detection for arrays with arbitrary geometry","volume":"140","author":"Izedi","year":"2017","journal-title":"Signal Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"77944","DOI":"10.1109\/ACCESS.2019.2922382","article-title":"An Underdetermined Source Number Estimation Method for Non-Circular Targets Based on Sparse Array","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2929","DOI":"10.1109\/TAP.2020.3030997","article-title":"DOA and Range Estimation Using a Uniform Linear Antenna Array Without A Priori Knowledge of the Source Number","volume":"69","author":"Li","year":"2021","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4395","DOI":"10.1109\/TSP.2022.3200548","article-title":"Ambiguities in DOA Estimation with Linear Arrays","volume":"70","author":"Matter","year":"2022","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yu, W., and He, P. (2021, January 9\u201311). DOA Estimation Ambiguity Resolution Method for Near Field Distributed Array. Proceedings of the 2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP), Xi\u2019an, China.","DOI":"10.1109\/ICSP51882.2021.9408848"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.1109\/TSP.2011.2178410","article-title":"Multiple level nested array: An efficient geometry for 2qth order cumulant based array processing","volume":"60","author":"Pal","year":"2012","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4167","DOI":"10.1109\/TSP.2010.2049264","article-title":"Nested arrays: A novel approach to array processing with enhanced degrees of freedom","volume":"58","author":"Pal","year":"2010","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_15","first-page":"6392875","article-title":"Deep Learning Approach in DOA Estimation: A Systematic Literature Review","volume":"2021","author":"Ge","year":"2021","journal-title":"Mob. Inf. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Luo, F., and Li, Y. (1993, January 27\u201330). Real-time neural computation of the noise subspace for the MUSIC algorithm. Proceedings of the IEEE International Conference on Acoustics, Minneapolis, MN, USA.","DOI":"10.1109\/ICASSP.1993.319161"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gohil, R., and Routray, G. (2021, January 27\u201330). Learning Based Method for Robust DOA Estimation using Co-prime Circular Conformal Microphone Array. Proceedings of the 2021 National Conference on Communications (NCC), Kanpur, India.","DOI":"10.1109\/NCC52529.2021.9530130"},{"key":"ref_18","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 Trans. Antennas Propag."},{"key":"ref_19","first-page":"98","article-title":"DOA Estimation for Coherent Sources Using Deep Learning Method","volume":"8","author":"Ge","year":"2019","journal-title":"J. Signal Process."},{"key":"ref_20","first-page":"9215006","article-title":"A Novel Direction-of-Arrival Estimation Algorithm Without Knowing the Source Number","volume":"99","author":"Chen","year":"2020","journal-title":"IEEE Commun. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"8549","DOI":"10.1109\/TVT.2018.2851783","article-title":"Deep Learning for Super-Resolution Channel Estimation and DOA Estimation Based Massive MIMO System","volume":"67","author":"Huang","year":"2018","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"13200","DOI":"10.1109\/JSEN.2021.3069972","article-title":"Lightweight CNNs-Based Interleaved Sparse Array Design of Phased-MIMO Radar","volume":"21","author":"Cheng","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_23","first-page":"1","article-title":"Fuzzy Graph Subspace Convolutional Network","volume":"99","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"ref_24","unstructured":"Umberto, M. (2019). Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection, Apress."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Kr\u00f3wczy\u0144ska, M., and Raczko, E. (2020). Asbestos\u2013Cement Roofing Identification Using Remote Sensing and Convolutional Neural Networks (CNNs). Remote Sens., 12.","DOI":"10.3390\/rs12030408"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhao, F., and Hu, G. (2021). DOA Estimation Method Based on Improved Deep Convolutional Neural Network. Sensors, 22.","DOI":"10.3390\/s22041305"},{"key":"ref_27","first-page":"3687","article-title":"Underdetermined Direction of Arrival Estimation for coprime array in the presence of nonuniform noise","volume":"43","author":"Sun","year":"2021","journal-title":"J. Electron. Inf. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zuo, M., and Xie, S. (2021). DOA Estimation Based on Weighted l1-norm Sparse Representation for Low SNR Scenarios. Sensors, 21.","DOI":"10.3390\/s21134614"},{"key":"ref_29","first-page":"49","article-title":"Underdetermined DOA estimation of optimal redundancy array via double reconstruction","volume":"45","author":"Wang","year":"2023","journal-title":"Syst. Eng. Electron."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1007\/s11432-018-9635-0","article-title":"Low-degree root-MUSIC algorithm for fast DOA estimation based on variable substitution technique","volume":"63","author":"Yan","year":"2020","journal-title":"Sci. China Inf. Sci."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/6\/3100\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:54:38Z","timestamp":1760122478000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/6\/3100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,14]]},"references-count":30,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["s23063100"],"URL":"https:\/\/doi.org\/10.3390\/s23063100","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,3,14]]}}}