Abstract
Array imperfections severely degrade the performance of most physics-driven direction-of-arrival (DOA) methods. Deep learning-based methods do not rely on any assumptions, can learn the latent data features of a given dataset, and are expected to adapt better to array imperfections compared with existing physics-driven methods. Hence, an improved DOA estimation method based on long short-term memory (LSTM) neural networks for situations with array imperfections is proposed in this paper. Various analyses given by this paper demonstrate that the phase features are the key to DOA estimation. Considering the sequential characteristics of the moving target and the correlation of multi-frame data features, the LSTM neural networks are used to learn and enhance the phase features of sampled data. The DOA estimation accuracy and generalization capability are improved by mitigating the phase distortion using LSTM. Numerical simulations and statistical results show that the proposed method is satisfactory in terms of both the generalization capability and imperfection adaptability compared with state-of-the-art physics-driven and data-driven methods.
Similar content being viewed by others
References
Johnson DH, Dan ED (1993) Array signal processing: concepts and techniques P T R. Prentice Hall
Van Veen BD, Buckley KM (1988) Beamforming: a versatile approach to spatial filtering. IEEE ASSP Mag 5(2):4–24. https://doi.org/10.1109/53.665
Litva J, Lo TK (1996) Digital beamforming in wireless communications. Artech House, Inc
Li J, Stoica P (2006) Robust adaptive beamforming. Wiley Online Library
Schmidt R (1986) Multiple emitter location and signal parameter estimation. IEEE Trans Antennas Propag 34(3):276–280. https://doi.org/10.1109/TAP.1986.1143830
Roy R, Kailath T (1989) ESPRIT-estimation of signal parameters via rotational invariance techniques. IEEE Trans Acous Speech Signal Process 37(7):984–995. https://doi.org/10.1109/29.32276
Gonen E, Mendel JM (1999) Subspace-based direction finding methods. In: Madisetti VK, Williams DB (eds) The digital signal processing handbook, chapitre 62
Liu Z, Zhou Y (2013) A unified framework and sparse Bayesian perspective for direction-of-arrival estimation in the presence of array imperfections. IEEE Trans Signal Process 61(15):3786–3798. https://doi.org/10.1109/TSP.2013.2262682
Carlin M, Rocca P, Oliveri G, Viani F, Massa A (2013) Directions-of-arrival estimation through Bayesian compressive sensing strategies. IEEE Trans Antennas Propag 61(7):3828–3838. https://doi.org/10.1109/TAP.2013.2256093
Yang Z, Xie L, Zhang C (2013) Off-grid direction of arrival estimation using sparse Bayesian inference. IEEE Trans Signal Process 61(1):38–43. https://doi.org/10.1109/TSP.2012.2222378
Malioutov D, Cetin M, Willsky AS (2005) A sparse signal reconstruction perspective for source localization with sensor arrays. IEEE Trans Signal Process 53(8):3010–3022. https://doi.org/10.1109/TSP.2005.850882
Ziskind I, Wax M (1988) Maximum likelihood localization of multiple sources by alternating projection. IEEE Trans Acous Speech Signal Process 36(10):1553–1560. https://doi.org/10.1109/29.7543
Jaffer AG (1988) Maximum likelihood direction finding of stochastic sources: a separable solution. In: ICASSP-88., International conference on acoustics, speech, and signal processing. https://doi.org/10.1109/ICASSP.1988.197258, vol 5, pp 2893–2896
Stoica P, Nehorai A (1988) Music, maximum likelihood and cramer-rao bound. In: ICASSP-88., International conference on acoustics, speech, and signal processing. https://doi.org/10.1109/ICASSP.1988.197097, vol 4, pp 2296–2299
Miller MI, Fuhrmann DR (1990) Maximum-likelihood narrow-band direction finding and the em algorithm. IEEE Trans Acous Speech Signal Process 38(9):1560–1577. https://doi.org/10.1109/29.60075
Krim H, Viberg M (1996) Two decades of array signal processing research: the parametric approach. IEEE Signal Process Mag 13(4):67–94. https://doi.org/10.1109/79.526899
Allen B, Ghavami M (2005) Adaptive array systems: fundamentals and applications. John Wiley & Sons
Viberg M, Swindlehurst AL (1994) Analysis of the combined effects of finite samples and model errors on array processing performance. IEEE Trans Signal Process 42(11):3073–3083. https://doi.org/10.1109/78.330367
Liu ZM, Huang ZT, Zhou YY (2009) Bias analysis of MUSIC in the presence of mutual coupling. IET Signal Process 3(1):74–84. https://doi.org/10.1049/iet-spr:20070213
Huang Z, Liu Z, Liu J, Zhou YY (2010) Performance analysis of MUSIC for non-circular signals in the presence of mutual coupling. IET Radar Sonar Navigation 4(5):703–711. https://doi.org/10.1049/iet-rsn.2009.0003
Friedlander B, Weiss AJ (1991) Direction finding in the presence of mutual coupling. IEEE Trans Antennas Propag 39(3):273–284. https://doi.org/10.1109/8.76322
Porat B, Friedlander B (1997) Accuracy requirements in off-line array calibration. IEEE Trans Aerosp Electron Syst 33(2):545–556. https://doi.org/10.1109/7.575894
Lin M, Yang L (2006) Blind calibration and DOA estimation with uniform circular arrays in the presence of mutual coupling. IEEE Antennas Wireless Propag Lett 5:315–318. https://doi.org/10.1109/LAWP.2006.878898
Flanagan BP, Bell KL (2001) Array self-calibration with large sensor position errors. Signal Process 81(10):2201–2214. https://doi.org/10.1016/S0165-1684(01)00121-9. http://www.sciencedirect.com/science/article/pii/S0165168401001219
Ng BC, See CMS (1996) Sensor-array calibration using a maximum-likelihood approach. IEEE Trans Antennas Propag 44(6):827–835. https://doi.org/10.1109/8.509886
Stavropoulos KV, Manikas A (2000) Array calibration in the presence of unknown sensor characteristics and mutual coupling. In: 2000 10th European signal processing conference, pp 1–4
Huang K, Wu Y, Wang C, et al. (2020) A projective and discriminative dictionary learning for high-dimensional process monitoring with industrial applications. IEEE Trans Industr Inform, 1–1. https://doi.org/10.1109/TII.2020.2992728
Wu X, Zhong M, Guo Y, et al. (2020) The assessment of small bowel motility with attentive deformable neural network. Inform Sci 508:22–32. https://doi.org/10.1016/j.ins.2019.08.059
Xiang H, Chen B, Yang T, Liu D (2020) Phase enhancement model based on supervised convolutional neural network for coherent DOA estimation. Appl Intell 50:2411–2422. https://doi.org/10.1007/s10489-020-01678-4
Liu Y, Zhou B, Han C, Guo T, Qin J (2020) A novel method based on deep learning for aligned fingerprints matching. Appl Intell 50:397–416. https://doi.org/10.1007/s10489-019-01530-4
Kuang P, Ma T, Chen Z, Li F (2019) Image super-resolution with densely connected convolutional networks. Appl Intell 49:125–136. https://doi.org/10.1007/s10489-018-1234-y
Noda K, Yamaguchi Y, Nakadai K, et al. (2015) Audio-visual speech recognition using deep learning. Appl Intell 42:722–737. https://doi.org/10.1007/s10489-014-0629-7
Brklja B, Janev M, Obradovi R, et al. (2014) Sparse representation of precision matrices used in GMMs. Appl Intell 41:956–973. https://doi.org/10.1007/s10489-014-0581-6
Pastorino M, Randazzo A (2005) A smart antenna system for direction of arrival estimation based on a support vector regression. IEEE Trans Antennas Propag 53(7):2161–2168. https://doi.org/10.1109/TAP.2005.850735
Randazzo A, Abou-Khousa MA, Pastorino M, Zoughi R (2007) Direction of arrival estimation based on support vector regression: experimental validation and comparison with MUSIC. IEEE Antennas Wireless Propag Lett 6:379–382. https://doi.org/10.1109/LAWP.2007.903491
Terabayashi K, Natsuaki R, Hirose A (2014) Ultrawideband direction-of-arrival estimation using complex-valued spatiotemporal neural networks. IEEE Transon Neural Netw Learn Syst 25(9):1727–1732. https://doi.org/10.1109/TNNLS.2014.2313869
Gao Y, Hu D, Chen Y, Ma Y (2017) Gridless one-bit DOA estimation exploiting SVM approach. IEEE Commun Lett 21(10):2210–2213. https://doi.org/10.1109/LCOMM.2017.2723359
nleren MF, Yaldiz E (2016) Direction of arrival estimation by using artificial neural networks. In: 2016 European modelling symposium (EMS). https://doi.org/10.1109/EMS.2016.049, pp 242–245
Southall HL, Simmers JA, O’Donnell TH (1995) Direction finding in phased arrays with a neural network beamformer. IEEE Trans Antennas Propag 43(12):1369–1374. https://doi.org/10.1109/8.475924
El Zooghby AH, Christodoulou CG, Georgiopoulos M (2000) A neural network-based smart antenna for multiple source tracking. IEEE Trans Antennas Propag 48(5):768–776. https://doi.org/10.1109/8.855496
Huang H, Yang J, Huang H, Song Y, Gui G (2018) Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system. IEEE Trans Veh Technol 67(9):8549–8560. https://doi.org/10.1109/TVT.2018.2851783
Wu L, Huang Z (2019) Coherent SVR learning for wideband direction-of-arrival estimation. IEEE Signal Process Lett 26(4):642–646. https://doi.org/10.1109/LSP.2019.2901641
Xiang H, Chen B, Yang M, Li C (2019) Altitude measurement based on characteristics reversal by deep neural network for VHF radar. IET Radar Sonar Navig 13(1):98–103. https://doi.org/10.1049/iet-rsn.2018.5121
Xiang H, Chen B, Xu H (2019) Spatial distribution feature learning for DOA estimation in multi-path environment. In: 2019 IEEE International conference on computational electromagnetics (ICCEM). https://doi.org/10.1109/COMPEM.2019.8778948, pp 1–4
Xiang H, Chen B, Yang M, Yang T, Liu D (2019) A novel phase enhancement method for low-angle estimation based on supervised DNN learning. IEEE Access 7:82329–82336. https://doi.org/10.1109/ACCESS.2019.2924156
Agatonovi M, Stankovi Z, Milovanovi B, Donov N (2011) DOA estimation using radial basis function neural networks as uniform circular antenna array signal processor. In: 2011 10th International conference on telecommunication in modern satellite cable and broadcasting services (TELSIKS). https://doi.org/10.1109/TELSKS.2011.6143173, vol 2, pp 544–547
Wu L, Liu Z, Huang Z (2019) Deep convolution network for direction of arrival estimation with sparse prior. IEEE Signal Process Lett 26(11):1688–1692
Elbir AM (2020) DeepMUSIC: multiple signal classification via deep learning. IEEE Sensors Lett 4(4):1–4
Liu Z, Zhang C, Yu PS (2018) Direction-of-arrival estimation based on deep neural networks with robustness to array imperfections. IEEE Trans Antennas Propag 66(12):7315–7327
Wang Y, Wang J, Zhang W, Yang J, Gui G (2020) Deep learning-based cooperative automatic modulation classification method for MIMO systems. IEEE Trans Veh Technol, 4575–4579. https://doi.org/10.1109/TVT.2020.2976942
Wu X, Zhong M, Guo Y et al (2020) Non-ferrous metals price forecasting based on variational mode decomposition and LSTM network. Knowl-Based Syst 188:105006. https://doi.org/10.1016/j.knosys.2019.105006
Milan A, Rezatofighi SH, Dick A, Reid I, Schindler K (2017) Online multi-target tracking using recurrent neural networks. In: Thirty-First AAAI conference on artificial intelligence
Ondruska P, Posner I (2016) Deep tracking: seeing beyond seeing using recurrent neural networks. In: Thirtieth AAAI conference on artificial intelligence
Yang T, Chan AB (2017) Recurrent filter learning for visual tracking. In: 2017 IEEE International conference on computer vision workshops (ICCVW). https://doi.org/10.1109/ICCVW.2017.235, pp 2010–2019
Gao C, Yan J, Zhou S, Chen B, Liu H (2019) Long short-term memory-based recurrent neural networks for nonlinear target tracking. Signal Process 164:67–73. https://doi.org/10.1016/j.sigpro.2019.05.027
Gao C, Yan J, Zhou S, Varshney PK, Liu H (2019) Long short-term memory-based deep recurrent neural networks for target tracking. Inform Sci 502:279–296. https://doi.org/10.1016/j.ins.2019.06.039
Tang Y, Lu Y (2014) Multi-resolution composite array for digital beamforming with high angular-resolution. IEEE Trans Antennas Propag 62(8):4377–4380. https://doi.org/10.1109/TAP.2014.2323427
Xiang H, Chen B, Yang T, Liu D (2020) Improved de-multipath neural network models with self-paced feature-to-feature learning for doa estimation in multipath environment. IEEE Trans Veh Technol 69 (5):5068–5078
Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78 (10):1550–1560. https://doi.org/10.1109/5.58337
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980
Acknowledgements
This work was supported by the National Natural Science Foundation of China (No. 61571344, No. 61971323), Fundamental Research Funds for the Central Universities and the Innovation Fund of Xidian University. The authors sincerely express their gratitude to anonymous reviewers and editors for their helpful and constructive comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors declared that they have no conflicts of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xiang, H., Chen, B., Yang, M. et al. Improved direction-of-arrival estimation method based on LSTM neural networks with robustness to array imperfections. Appl Intell 51, 4420–4433 (2021). https://doi.org/10.1007/s10489-020-02124-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-02124-1