Journal of AI-Driven Communication Engineering

Articles

Vol. 1 (2025)

Enhancing IRS Localization via Deep Learning-Based AOA and Distance Estimation

Submitted
October 9, 2025
Published
2025-11-10

Abstract

In Intelligent Reflecting Surface (IRS)-assisted communication systems, accurate user localization, particularly Angle-Of-Arrival (AoA) and range estimation are challenging due to the computational complexity and limited resolution of traditional Multiple Signal Classification (MUSIC) algorithms. This paper introduces a hybrid IRS framework that combines machine learning with a modified MUSIC algorithm to achieve high-precision localization and enhanced security. The system integrates two Convolutional Neural Networks (CNNs): RefineNet, which refines AoA and range estimates from MUSIC pseudo-spectra, and ElementNet, which optimizes the number and placement of active IRS elements to balance accuracy with resource efficiency. Notably, ElementNet shows that only eight active elements are sufficient to obtain 90% of the best achievable localization accuracy, highlighting the efficiency of the proposed design. Validation on the DeepMIMO dataset demonstrates superior range accuracy and AoA precision. This work sheds light on the secure and high-precision localization for diverse wireless applications.

 

References

  1. Alam, S.S., Chakma, A., Rahman, M.H., Bin Mofidul, R., Alam, M.M., Utama, I.B.K.Y., Jang, Y.M.: Rf-enabled deep-learning-assisted drone detection and identification: An end-to-end approach. Sensors 23(9), 4202 (2023). https://doi.org/10.3390/s23094202
  2. Alam, S.S., Tang, H., Zhao, Y., Luo, C., Wang, W., Dhar, N.K.: Defense against adversarial attacks for channel estimation models in ris-assisted communication
  3. Alam, S.S., Zhao, Y., Tang, H., Wang, W., Song, M.: Deep learning-based end-toend channel estimation and csi feedback for large ris-assisted wireless communication
  4. Alkhateeb, A.: Deepmimo: A generic deep learning dataset for millimeter wave and massive mimo applications. arXiv preprint arXiv:1902.06435 (2019)
  5. (arXiv), U.: Sparse deep learning models with the 1 regularization. arXiv preprint arXiv:2408.02801 (2024),
  6. Balanis, C.A.: Antenna Theory: Analysis and Design. Wiley, Hoboken, NJ, 4th edn. (2015)
  7. BjÅNornson, E., Wymeersch, H., Matthiesen, B., Popovski, P., Sanguinetti, L., De Carvalho, E.: Reconfigurable intelligent surfaces: A signal processing perspective with wireless applications. IEEE Signal Processing Magazine 39(2), 135-158 (2022). https://doi.org/10.1109/MSP.2021.3130549
  8. Chakma, A., Alam, S.S., Rahman, M.H., Jang, Y.M.: Deep decoder csinet for fdd massive mimo system. IEEE Wireless Communications Letters 12(12), 2073-2077 (2023). https://doi.org/10.1109/LWC.2023.3307164
  9. Fahad, N., Bulut, E.: Wifi csi based liquid temperature prediction: A physicsguided machine learning approach. In: 2025 IEEE 26th International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM). pp. 122-130. IEEE (2025). https://doi.org/10.1109/WoWMoM65615.2025.00029
  10. Fahad, N., Touhiduzzaman, M., Bulut, E.: Ensemble learning based wifi sensing using spatially distributed tx-rx links. In: IEEE International Conference on Computing, Networking and Communications (ICNC), Honolulu, Hawaii, USA (2025). https://doi.org/10.1109/ICNC64010.2025.10993928
  11. Fried, D.L.: Differential angle of arrival: theory, evaluation, and measurement feasibility. Radio Science 10(1), 71-76 (1975). https://doi.org/10.1029/RS010i001p00071
  12. Gao, F., Gershman, A.B.: A generalized esprit approach to direction-of-arrival estimation. IEEE Signal Processing Letters 12(3), 254-257 (2005). https://doi.org/10.1109/LSP.2004.842276
  13. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016), https://www.deeplearningbook.org/
  14. Gross, F.: Smart Antennas for Wireless Communications. McGraw-Hill Professional (2005)
  15. He, J., Swamy, M.N.S., Ahmad, M.O.: Efficient application of music algorithm under the coexistence of far-field and near-field sources. IEEE Transactions on Signal Processing 60(4), 2066-2070 (2012). https://doi.org/10.1109/TSP.2011.2180902
  16. Huang, Y.D., Barkat, M.: Near-field multiple source localization by passive sensor array. IEEE Transactions on Antennas and Propagation 39(7), 968-975 (1991). https://doi.org/10.1109/8.86917
  17. Khan, A.,Wang, S., Zhu, Z.: Angle-of-arrival estimation using an adaptive machine learning framework. IEEE Communications Letters 23(2), 294-297 (2018). https://doi.org/10.1109/LCOMM.2018.2884464
  18. Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence. vol. 2, pp. 1137-1143. Morgan Kaufmann (1995)
  19. Pan, Y., Pan, C., Jin, S., Wang, J.: Ris-aided near-field localization and channel estimation for the terahertz system. IEEE Journal of Selected Topics in Signal Processing 17(4), 878-892 (2023). https://doi.org/10.1109/JSTSP.2023.3285431
  20. Ramezani, P., Kosasih, A., BjÅNornson, E.: An efficient modified music algorithm for ris-assisted near-field localization. arXiv preprint arXiv:2409.14152 (2024). https://doi.org/10.1109/GLOBECOM52923.2024.10901595
  21. Samiul Alam, S., Chakma, A., Imran, A., Min Jang, Y.: Dcsinet: Effective handling of noisy csi in fdd massive mimo system. IEEE Wireless Communications Letters 13(9), 2556-2560 (2024). https://doi.org/10.1109/LWC.2024.3427316
  22. Samiul Alam, S., Tang, H., Yang, G., Luo, C., Wang, W., Zhao, Y.: Dsrnet: Hybrid deep learning-based channel estimation for ris-aided wireless communication. In: Wireless Artificial Intelligent Computing Systems and Applications. pp. 62-74.Springer Nature Singapore (2025). https://doi.org/10.1007/978-981-96-8725-1_6
  23. Schmidt, R.: Multiple emitter location and signal parameter estimation. IEEE transactions on antennas and propagation 34(3), 276-280 (1986). https://doi.org/10.1109/TAP.1986.1143830
  24. Tang, H., Zhao, Y., Wang, W.: Angle of arrival based signal classification in intelligent reflecting surface-aided wireless communications. In: International Conference on Wireless Algorithms, Systems, and Applications (WASA). pp. 56-67. Springer (2022). https://doi.org/10.1007/978-3-031-23902-1_5
  25. Tibshirani, R.: Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological) 58(1), 267-288 (1996). https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
  26. Wax, M., Kailath, T.: Optimum localization of multiple sources by passive arrays. IEEE Transactions on Acoustics, Speech, and Signal Processing 31(5), 1210-1217 (2003). https://doi.org/10.1109/TASSP.1983.1164183
  27. Wymeersch, H., He, J., Denis, B., Clemente, A., Juntti, M.: Radio localization and mapping with reconfigurable intelligent surfaces: Challenges, opportunities, and research directions. IEEE Vehicular Technology Magazine 15(4), 52-61 (2020). https://doi.org/10.1109/MVT.2020.3023682
  28. Xie, J., Fu, Z., Xian, H.: Spectrum sensing based on estimation of direction of arrival. In: 2010 International Conference on Computational Problem-Solving. pp. 39-42. IEEE (2010).
  29. Zhi, W., Chia, M.Y.W.: Near-field source localization via symmetric subarrays. IEEE Signal Processing Letters 14(6), 409-412 (2007). https://doi.org/10.1109/LSP.2006.888390