Using NARX Neural Networks to Advance Passive 
Radar Target Detection

Sattam Alkhuraiji; Abir Alharbi

doi:https://doi.org/10.14445/22315373/IJMTT-V71I7P104

International Journal of Mathematics Trends and Technology

Research Article | Open Access | Download PDF

Volume 71 | Issue 7 | Year 2025 | Article Id. IJMTT-V71I7P104 | DOI : https://doi.org/10.14445/22315373/IJMTT-V71I7P104

Using NARX Neural Networks to Advance Passive Radar Target Detection

Sattam Alkhuraiji, Abir Alharbi

Received	Revised	Accepted	Published
21 May 2025	28 Jun 2025	13 Jul 2025	27 Jul 2025

Citation :

Sattam Alkhuraiji, Abir Alharbi, "Using NARX Neural Networks to Advance Passive Radar Target Detection," International Journal of Mathematics Trends and Technology (IJMTT), vol. 71, no. 7, pp. 33-43, 2025. Crossref, https://doi.org/10.14445/22315373/IJMTT-V71I7P104

Abstract

This study introduces a novel detection approach utilizing Artificial Neural Networks (ANNs) to enhance target detection with Passive Radar (PR) systems. The methodology goes through two distinct stages: primarily, a Backpropagation Neural Network (BPNN) to refine the target azimuth estimation, using the Levenberg-Marquardt algorithm as a replacement for the traditional MUSIC algorithm used in the classical methods. Subsequently, a NARX Recurrent Neural Network with time series features to collect data from prior flights is used to enhance detection capabilities in the proposed system. Training on datasets comprising 12 million data points from over 5000 flights demonstrated significant performance improvements, achieving a reduction in mean square error on a test flight of 1000 data points, with over 75% enhancement in localization accuracy compared to classical passive radar systems.

Keywords

Artificial neural networks, Backpropagation neural networks, NARX, Recurrent neural network, Passive Radar, Azimuth angles.

References

[1] Mateusz Malanowski, Signal Processing for Passive Bistatic Radar, Artech House publishing, 2019.
[Google Scholar] [Publisher Link]
[2] Wen-Qin Wang, and Huaizong Shao, “Azimuth-Variant Signal Processing in High-Altitude Platform Passive SAR with Spaceborne/Airborne Transmitter,” Remote Sensing, vol. 5, no. 3, pp. 1292-1310, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Xiao Yong Lyu, and Jun Wang, “Direction of Arrival Estimation in Passive Radar Based on Deep Neural Network,” IET Signal Processing, vol. 15, no. 9, pp. 612-621, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Li Song, Wang Shengli, and Xie Dingbao, “Radar Track Prediction Method Based on BP Neural Network,” The Journal of Engineering, vol. 2019, no. 21, pp. 1-5, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Mohammed Khalafalla et al., “Two-Dimensional Target Localization Approach via a Closed-Form Solution Using Range Difference Measurements Based on Pentagram Array,” Remote Sensing, vol. 16, no. 8, pp. 1-18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Ali Noroozi, and Mohammad Ali Sebt, “Target Localization in Multistatic Passive Radar Using SVD Approach for Eliminating the Nuisance Parameters,” IEEE Transactions on Aerospace and Electronic Systems, vol. 53, no. 4, pp. 1660-1671, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Yulong Gao et al., “Gridless 1-b DOA Estimation Exploiting SVM Approach,” IEEE Communications Letters, vol. 21, no. 10, pp. 2210 2213, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[8] A.H. El Zooghby, C.G. Christodoulou, and M. Georgiopoulos, “A Neural Network‐Based Smart Antenna for Multiple Source Tracking,” IEEE Transactions on Antennas and Propagation, vol. 48, no. 5, pp. 768-776, 2000.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Zhang-Meng Liu, Chenwei Zhang, and Philip 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, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[10] R.D. DeGroat, E.M. Dowling, and D.A. Linebarger, “The Constrained MUSIC Problem,” IEEE Transactions on Signal Processing, vol. 41, no. 3, pp. 1445-1449, 1993.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Laurene V. Fausett, Fundamentals of Neural Networks Architectures, Algorithms and Applications, Wiley, 1995.
[Google Scholar] [Publisher Link]
[12] Bogdan Wiliamowski, and Hao Yu, “Improved Computation for Levenberg–Marquardt Training,” IEEE Transactions on Neural Networks and Learning Systems, vol. 21, no. 6, pp. 930-937, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[13] D. Ashok Kumar, and S. Murugan, “Performance Analysis of NARX Neural Network Backpropagation Algorithm by Various Training Functions for Time Series Data,” International Journal of Data Science, vol. 3, no. 4, pp. 308-325, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Semra Çoruh et al., “The Use of NARX Neural Network for Modeling of Adsorption of Zinc Ions Using Almond Shell as a Potential Biosorbent,” Bioresource Technology, vol. 151, pp. 406-410, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Tsung-Nan Lin et al., “A Delay Damage Model Selection Algorithm for NARX Neural Networks,” IEEE Transactions on Signal Processing, vol. 45, no. 11, pp. 2719-2730, 1997.
[CrossRef] [Google Scholar] [Publisher Link]