Abstract
Conventional direction-of-arrival (DOA) estimation methods generally rely on the white Gaussian noise assumption, making them ineffective in hybrid noise scenarios. This paper proposes a deep neural network based on sparsely-gated mixture-of-experts (SMoE) mechanism for underwater DOA estimation in hybrid noise environments. The model first transforms the complex covariance matrix of the array signal into two real covariance matrices via the method of separating real and complex parts. Subsequently, a CNN is employed to extract spatial features from the array signal. Finally, a SMoE mechanism is utilized to handle hybrid noise environments, which dynamically adapts to diverse noise conditions via sparse expert activation. With our staged training strategy, the model achieves 0.94\(^\circ\) RMSE at 0 dB SNR with six noise types, outperforming conventional approaches. This work provides a feasible solution for DOA estimation in hybrid noise environments.
Similar content being viewed by others
Data availability
Relevant information and codes are available from the corresponding author if required.
Code availability
The custom code used for data processing and analysis in this study has been deposited in the Zenodo repository with the DOI 10.5281/zenodo.18286738.
References
Godara, L. Application of antenna arrays to mobile communications. ii. Beam-forming and direction-of-arrival considerations. Proc. IEEE 85, 1195–1245. https://doi.org/10.1109/5.622504 (1997).
Yijie, R. & Xiaojun, W. Non-blind doa estimation method for 5g mobile terminal. In 2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) 1–5 (2021). https://doi.org/10.1109/ICSPCC52875.2021.9564610.
Tichavsky, P., Wong, K. & Zoltowski, M. Near-field/far-field azimuth and elevation angle estimation using a single vector hydrophone. IEEE Trans. Signal Process. 49, 2498–2510. https://doi.org/10.1109/78.960397 (2001).
Schmidt, R. Multiple emitter location and signal parameter estimation. IEEE Trans. Antennas Propag. 34, 276–280. https://doi.org/10.1109/TAP.1986.1143830 (1986).
Chen, F., Yang, D. & Mo, S. A doa estimation algorithm based on eigenvalues ranking problem. IEEE Trans. Instrum. Meas. 72, 1–15. https://doi.org/10.1109/TIM.2022.3232095 (2023).
Pesavento, M. & Gershman, A. Maximum-likelihood direction-of-arrival estimation in the presence of unknown nonuniform noise. IEEE Trans. Signal Process. 49, 1310–1324. https://doi.org/10.1109/78.928686 (2001).
Chen, C. E., Lorenzelli, F., Hudson, R. E. & Yao, K. Stochastic maximum-likelihood doa estimation in the presence of unknown nonuniform noise. IEEE Trans. Signal Process. 56, 3038–3044. https://doi.org/10.1109/TSP.2008.917364 (2008).
Liao, B., Chan, S.-C., Huang, L. & Guo, C. Iterative methods for subspace and doa estimation in nonuniform noise. IEEE Trans. Signal Process. 64, 3008–3020. https://doi.org/10.1109/TSP.2016.2537265 (2016).
Schmidt, R. Multiple emitter location and signal parameter estimation. IEEE Trans. Antennas Propag. 34, 276–282. https://doi.org/10.1109/TAP.1986.1143830 (1986).
Madurasinghe, D. A new doa estimator in nonuniform noise. IEEE Signal Process. Lett. 12, 337–339. https://doi.org/10.1109/LSP.2005.843774 (2005).
Liao, B. & Chan, S. C. A simple method for doa estimation in the presence of unknown nonuniform noise. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2789–2793 (2015). https://doi.org/10.1109/ICASSP.2015.7178479.
Liao, B., Guo, C., Huang, L. & Wen, J. Matrix completion based direction-of-arrival estimation in nonuniform noise. In 2016 IEEE International Conference on Digital Signal Processing (DSP) 66–69 (2016). https://doi.org/10.1109/ICDSP.2016.7868517.
Liao, B., Guo, C. & So, H. C. Direction-of-arrival estimation in nonuniform noise via low-rank matrix decomposition. In 2017 22nd International Conference on Digital Signal Processing (DSP) 1–4 (2017). https://doi.org/10.1109/ICDSP.2017.8096135.
Liu, K. & Zhang, Y. D. Coprime array-based doa estimation in unknown nonuniform noise environment. Digital Signal Process. 79, 66–74. https://doi.org/10.1016/j.dsp.2018.04.003 (2018).
Liao, B., Huang, L., Guo, C. & So, H. C. New approaches to direction-of-arrival estimation with sensor arrays in unknown nonuniform noise. IEEE Sens. J. 16, 8982–8989. https://doi.org/10.1109/JSEN.2016.2621057 (2016).
Esfandiari, M., Vorobyov, S. A., Alibani, S. & Karimi, M. Non-iterative subspace-based doa estimation in the presence of nonuniform noise. IEEE Signal Process. Lett. 26, 848–852. https://doi.org/10.1109/LSP.2019.2909587 (2019).
Esfandiari, M. & Vorobyov, S. A. A novel angular estimation method in the presence of nonuniform noise. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 5023–5027 (2022). https://doi.org/10.1109/ICASSP43922.2022.9747777.
Zhou-hua, Z. The fourth order cumulants based modified music algorithm for doa in colored noise. In 2010 Asia-Pacific Conference on Wearable Computing Systems 345–347 (2010). https://doi.org/10.1109/APWCS.2010.94.
Zhang, Y., Zhang, G. & Leung, H. Atomic norm minimization methods for continuous doa estimation in colored noise. In 2019 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) 1–5 (2019). https://doi.org/10.1109/ICSPCC46631.2019.8960841.
Guzey, N., Xu, H. & Jagannathan, S. Localization of near-field sources in spatially colored noise. IEEE Trans. Instrum. Meas. 64, 2302–2311. https://doi.org/10.1109/TIM.2015.2390813 (2015).
Werner, K. & Jansson, M. Doa estimation and detection in colored noise using additional noise-only data. IEEE Trans. Signal Process. 55, 5309–5322. https://doi.org/10.1109/TSP.2007.898758 (2007).
Liu, Y., Chen, H. & Wang, B. Doa estimation based on cnn for underwater acoustic array. Appl. Acoust. 172, 107594. https://doi.org/10.1016/j.apacoust.2020.107594 (2021).
Papageorgiou, G. K., Sellathurai, M. & Eldar, Y. C. Deep networks for direction-of-arrival estimation in low snr. IEEE Trans. Signal Process. 69, 3714–3729. https://doi.org/10.1109/TSP.2021.3089927 (2021).
Elbir, A. M. Deepmusic: multiple signal classification via deep learning. IEEE Sens. Lett. 4, 1–4. https://doi.org/10.1109/LSENS.2020.2980384 (2020).
Liu, K., Wang, X., Yu, J. & Ma, J. Attention based doa estimation in the presence of unknown nonuniform noise. Appl. Acoust. 211, 109506. https://doi.org/10.1016/j.apacoust.2023.109506 (2023).
Sun, W. et al. Domain transform model driven by deep learning for anti-noise hyperspectral and multispectral image fusion. IEEE Trans. Geosci. Remote Sens. 62, 1–17. https://doi.org/10.1109/TGRS.2023.3337286 (2024).
Zhou, A. et al. A novel noise-aware deep learning model for underwater acoustic denoising. IEEE Trans. Geosci. Remote Sens. 61, 1–13. https://doi.org/10.1109/TGRS.2023.3254652 (2023).
Fang, Y., Zhu, S., Liao, B., Li, X. & Liao, G. Target localization with bistatic mimo and fda-mimo dual-mode radar. IEEE Trans. Aerosp. Electron. Syst. 60, 952–964. https://doi.org/10.1109/TAES.2023.3333829 (2024).
Wang, W.-Q. Fda-mimo radar using ambiguity function for target two-dimensional localization. In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 8706–8710 (2024). https://doi.org/10.1109/ICASSP48485.2024.10448286.
Ma, R. et al. Target localization with distributed fda-mimo and epc-mimo radars using cd-music. In 2024 IEEE International Conference on Signal, Information and Data Processing (ICSIDP) 1–6 (2024). https://doi.org/10.1109/ICSIDP62679.2024.10868167.
Wu, X., Liu, Y. & Jia, X. Gridless target localization for fda-mimo radar with sparse arrays. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 1–5 (2023). https://doi.org/10.1109/ICASSP49357.2023.10096941.
Shazeer, N. et al. Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. In International Conference on Learning Representations (ICLR) (2017).
Chen, F. Research on Algorithm of High-resolution DOA Estimation using Acoustic Vector Sensor. Ph.D. thesis, Harbin Engineering University, Harbin, China (2022).
Acknowledgements
The research was supported by the Development of Key Data Algorithms for Jizhi Ship Technology (November 2055072401) and 2024 Project of Intelligent Detection System for Sensitive Information in Bastion Host Screen Recordings (Number 2055072409).
Funding
The research was supported by the Development of Key Data Algorithms for Jizhi Ship Technology (Number 2055072401)
and 2024 Project of Intelligent Detection System for Sensitive Information in Bastion Host Screen Recordings (Number 2055072409).
Author information
Authors and Affiliations
Contributions
Conceptualization, W.X. and S.Y.; methodology, S.Y.; investigation, W.X. and H.G.; formal analysis, W.X. and C.W.; writing–original draft, W.X. and Z.Z.; supervision, S.Y. and H.G.; validation, W.X. and S.Y.; funding acquisition, S.Y. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Xu, W., Yi, S., Gu, H. et al. Underwater acoustic vector DOA estimation in hybrid noise environments based on sparsely-gated mixture-of-experts mechanism. Sci Rep (2026). https://doi.org/10.1038/s41598-026-37217-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-37217-3
