The direction of arrival estimation of radio signal sources using convolutional neural network model for non-uniform anten array

146 views

Authors

  • Nguyen Duy Thai (Corresponding Author) Institute of Electronics, Academy of Military Science and Technology

DOI:

https://doi.org/10.54939/1859-1043.j.mst.78.2022.78-85

Keywords:

Direction of Arrival; Convolutional Neural Network; Non-uniform Linear Array.

Abstract

 In this study, a Residual convolutional neural network model, named DOA-ResNet, is proposed to improve the direction of arrival (DOA) estimation accuracy of radio signal sources. The DOA-ResNet model is analyzed by changing the number and size of filter channels in the convolutional layer to find the dependence between the angular estimation performance and those parameters. Based on the evaluation, a suitable model is proposed for a trade-off between accuracy, model size, and execution time when it is applied in practice. In addition, the proposed model is compared with some other machine learning algorithms to demonstrate its remarkable performance in both accuracy and processing time.

References

[1]. R. Wiley, “ELINT: The Interception and Analysis of Radar Signals”, Artech House, 2006.

[2]. S. Chandran, “Advances in Direction-of-Arrival Estimation”, Artech House, 2006.

[3]. L. Wu, Z.-M. Liu, and Z.-T. Huang, “Deep convolution network for direction of arrival estimation with sparse prior”, IEEE Signal Processing Letters, vol. 26, no. 11, pp. 1688–1692, Nov. 2019.

[4]. Z. Liu, C. Zhang and P. S. Yu, "Direction-of-Arrival Estimation Based on Deep Neural Networks With Robustness to Array Imperfections", IEEE Transactions on Antennas and Propagation, vol. 66, no. 12, pp. 7315-7327, Dec. 2018.

[5]. A. Faye, J. D. Ndaw and M. Sène, "SVM-Based DOA Estimation with Classification Optimization," 2018 26th Telecommunications Forum (TELFOR), 2018, pp. 1-4.

[6]. Y. Liu, H. Chen and B. Wang, "DOA Estimation of Underwater Acoustic Signals Based on PCA-kNN Algorithm," 2020 International Conference on Computer Information and Big Data Applications (CIBDA), 2020, pp. 486-490.

[7]. Y. Miao, Y. Lv, J. Zhen, and B. Guo, “Accessorial Locating for Internet of Vehicles Based on DOA Estimation in Industrial Transportation,” Wireless Communications and Mobile Computing, vol. 2021, p. 8241773, 2021.

[8]. V.-S. Doan and D.-S. Kim, “DOA estimation of multiple non-coherent and coherent signals using element transposition of covariance matrix,” ICT Express, vol. 6, no. 2, pp. 67–75, 2020.

[9]. V. -S. Doan, T. Huynh-The, V. -P. Hoang and D. -T. Nguyen, "MoDANet: Multi-task Deep Network for Joint Automatic Modulation Classification and Direction of Arrival Estimation," IEEE Communications Letters, Early Access, pp. 1-1, Dec. 2021.

[10]. S. Skansi, “Introduction to Deep Learning: From Logical Calculus to Artificial Intelligence (1st. ed.)”, Springer Publishing Company, 2018.

Published

27-04-2022

How to Cite

Nguyễn Duy Thái. “The Direction of Arrival Estimation of Radio Signal Sources Using Convolutional Neural Network Model for Non-Uniform Anten Array”. Journal of Military Science and Technology, no. 78, Apr. 2022, pp. 78-85, doi:10.54939/1859-1043.j.mst.78.2022.78-85.

Issue

Section

Research Articles