MUET logo

Hybrid Model for Data-Driven Channel Estimation in mmWave Massive MIMO Systems with Compressed Sensing and Deep Learning

Authors

  • Yang Haoxuan

    Center for Cyber Security, Faculty of Information Science and Technology (FTSM), Universiti Kebangsaan Malaysia (UKM), 43600 UKM Bangi, Selangor, Malaysia
    Author

  • Faizan Qamar

    Center for Cyber Security, Faculty of Information Science and Technology (FTSM), Universiti Kebangsaan Malaysia (UKM), 43600 UKM Bangi, Selangor, Malaysia
    Author

  • Syed Hussain Ali Kazmi

    Center for Cyber Security, Faculty of Information Science and Technology (FTSM), Universiti Kebangsaan Malaysia (UKM), 43600 UKM Bangi, Selangor, Malaysia
    Author

  • Khairul Akram Zainol Ariffin

    Center for Cyber Security, Faculty of Information Science and Technology (FTSM), Universiti Kebangsaan Malaysia (UKM), 43600 UKM Bangi, Selangor, Malaysia
    Author

  • Kashif Nisar

    School of Information Technology & Engineering, Melbourne Institute of Technology, 154 - 158 Sussex Street, Sydney, New South Wales, 2000, Australia
    Author

DOI:

https://doi.org/10.22581/0712

Keywords:

Channel Estimation , Compressed Sensing , Convolutional Neural Networks , DeepMIMO, mmWave massive-MIMO , Orthogonal Matching Pursuit

Abstract

Millimeter-wave (mmWave) massive Multiple-Input Multiple-Output (MIMO) technology promises to provide gigabit-level transmission rates for 5G/6G networks. However, this technology suffers from high channel dimensionality and sparse signals, requiring many pilot signals for estimation using traditional methods, which are also time-consuming. This paper proposes a two-stage hybrid Compressed Sensing-Deep Learning (CS-DL) framework that combines the model advantages of the Orthogonal Matching Pursuit (OMP) algorithm with the data processing capabilities of a lightweight Convolutional Neural Network (CNN). The first stage exploits the signal's sparsity in the angular domain, requiring only 5% of the pilot signal to obtain preliminary channel estimates. In the second stage, signal gain is optimized using a residual CNN, which reduces error interference. MATLAB simulation results on the DeepMIMO dataset indicate that, compared to the traditional OMP algorithm, the proposed framework reduces the Normalized Mean Square Error (NMSE) by up to 1.8 dB, increases Spectral Efficiency (SE) by approximately 9%, and decreases the total estimation time to about 0.7 milliseconds, thereby satisfying the latency requirements of 5G systems. Additionally, the framework offers remarkable flexibility, enabling integration with low-resolution hardware and hybrid beamforming architectures, making it suitable for real-time deployment in applications such as automotive communication systems and mmWave access points.

Downloads

References

[1] S. H. A. Kazmi, R. Hassan, F. Qamar, K. Nisar, and A. A. A. Ibrahim, "Security concepts in emerging 6G communication: Threats, countermeasures, authentication techniques and research directions," Symmetry, vol. 15, no. 6, p. 1147, 2023.

[2] H. Yang, F. Qamar, S. H. A. Kazmi, S. T. A. Jafri, K. A. Z. Ariffin, and Q. N. Nguyen, "Interference mitigation in b5g network architecture for mimo and cdma: State of the art, issues, and future research directions," Information, vol. 15, no. 12, p. 771, 2024.

[3] F. Qamar, M. N. Hindia, T. Abd Rahman, R. Hassan, K. Dimyati, and Q. N. Nguyen, "Propagation characterization and analysis for 5G mmWave through field experiments," Computers, Materials and Continua, vol. 68, no. 2, pp. 2249-2264, 2021.

[4] X. Ma, Z. Gao, and D. Wu, "Model-driven deep learning based channel estimation for millimeter-wave massive hybrid MIMO systems," in 2021 IEEE/CIC International Conference on Communications in China (ICCC), 2021: IEEE, pp. 676-681.

[5] I. F. Dehkordi, K. Manochehri, and V. Aghazarian, "Internet of Things (IoT) Intrusion Detection by Machine Learning (ML): A Review," Asia-Pacific Journal of Information Technology & Multimedia, vol. 12, no. 1, 2023.

[6] Z. Yi and X. Jing, "Multiple vandermonde decomposition based channel estimation for MmWave MIMO high-mobility communication in 5G and beyond," China Communications, vol. 20, no. 4, pp. 12-25, 2023.

[7] A. Liao, Z. Gao, Y. Wu, H. Wang, and M.-S. Alouini, "2D unitary ESPRIT based super-resolution channel estimation for millimeter-wave massive MIMO with hybrid precoding," IEEE Access, vol. 5, pp. 24747-24757, 2017.

[8] M. Hindia, F. Qamar, H. Ojukwu, R. Hassan, and K. Dimyati, "Robust schemes to enhance energy consumption efficiency for millimeter wave-based microcellular network in congested urban environments," International Journal of Electronics and Telecommunications, pp. 417-424-417-424, 2021.

[9] H. Lin, G. Zhang, W. Mo, T. Lan, Z. Zhang, and S. Ye, "PARAFAC-Based Channel Estimation for Relay Assisted mmWave Massive MIMO Systems," in 2021 7th International Conference on Computer and Communications (ICCC), 2021: IEEE, pp. 1869-1874.

[10] V. B. Shukla, R. Mitra, and V. Bhatia, "Adaptive sparse aware algorithm based channel estimation for mmwave hybrid MIMO system," in 2021 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), 2021: IEEE, pp. 290-295.

[11] F. Hu, L. Li, Y. Lu, and L. Jin, "Super-resolution channel estimation for MmWave massive MIMO: a Newtonian method," in 2019 IEEE 19th International Conference on Communication Technology (ICCT), 2019: IEEE, pp. 75-80.

[12] Neha, N. Kumar, and A. Kochhar, "Efficient channel estimation in mm wave massive MIMO using hybrid beamforming," in Proceedings of First International Conference on Computational Electronics for Wireless Communications: ICCWC 2021, 2022: Springer, pp. 87-95.

[13] V. A. Nugroho and B. M. Lee, "A survey of federated learning for mmwave massive MIMO," IEEE Internet of Things Journal, vol. 11, no. 16, pp. 27167-27183, 2024.

[14] Q. Gao, Z. Li, W. Zhang, X. Bao, J. Xia, and Z. Zheng, "Channel reconstruction for mmWave Massive MIMO systems based on Channel Path Map," Physical Communication, vol. 61, p. 102232, 2023.

[15] R. Zhang, W. Tan, W. Nie, X. Wu, and T. Liu, "Deep learning-based channel estimation for mmwave massive MIMO systems in mixed-ADC architecture," Sensors, vol. 22, no. 10, p. 3938, 2022.

[16] P. Wang, J. Li, X. Liu, and P. Wang, "Multi-stage training optimization for pilot compression and channel estimation in massive MIMO systems under quasi-sparse channel environment," IEEE Communications Letters, vol. 26, no. 12, pp. 3059-3063, 2022.

[17] X. Tian and Q. Zheng, "A massive MIMO channel Estimation method based on hybrid deep learning model with regularization techniques," International Journal of Intelligent Systems, vol. 2025, no. 1, p. 2597866, 2025.

[18] F. Qamar, S. H. A. Kazmi, M. U. A. Siddiqui, R. Hassan, and K. A. Z. Ariffin, "Federated learning for millimeter-wave spectrum in 6G networks: Applications, challenges, way forward and open research issues," PeerJ Computer Science, vol. 10, p. e2360, 2024.

[19] J. Gao, C. Zhong, G. Y. Li, J. B. Soriaga, and A. Behboodi, "Deep learning-based channel estimation for wideband hybrid mmWave massive MIMO," IEEE Transactions on Communications, vol. 71, no. 6, pp. 3679-3693, 2023.

[20] W. Tong, W. Xu, F. Wang, J. Shang, M. Pan, and J. Lin, "Deep learning compressed sensing-based beamspace channel estimation in mmWave massive MIMO systems," IEEE Wireless Communications Letters, vol. 11, no. 9, pp. 1935-1939, 2022.

[21] P. Soumya, R. Ganiga, S. Hiremath, and M. B. Teklu, "Integration of Deep Learning and Compressive Sensing algorithm for beamspace channel estimation in mmWave massive MIMO systems," IEEE Access, 2025.

[22] Y. Li and A. Madhukumar, "Hybrid near-and far-field THz UM-MIMO channel estimation: a sparsifying matrix learning-aided Bayesian approach," IEEE Transactions on Wireless Communications, 2024.

[23] Q. Liu, Y. Li, and J. Sun, "A Model-Driven Channel Estimation Method for Millimeter-Wave Massive MIMO Systems," Sensors, vol. 23, no. 5, p. 2638, 2023.

[24] M. Mizmizi, A. Alkhateeb, and U. Spagnolini, "Hybrid MIMO in the Upper Mid-Band: Architectures, Processing, and Energy Efficiency," arXiv preprint arXiv:2503.01382, 2025.

[25] S. N. Arinze, E. R. Obi, S. H. Ebenuwa, and A. O. Nwajana, "RF energy-harvesting techniques: applications, recent developments, challenges, and future opportunities," in Telecom, 2025, vol. 6, no. 3: MDPI, p. 45.

[26] S. Yang, C.-X. Wang, Y. Wang, J. Huang, Y. Zhou, and E.-H. M. Aggoune, "An Efficient Pre-Processing Method for 6 G Dynamic Ray-Tracing Channel Modeling," IEEE Transactions on Vehicular Technology, 2024.

[27] R. A. Roshdy, M. H. Dahshan, S. A. AlQahtani, A. Emam, H. M. Kasem, and M. A. Salem, "Methods for simplifying quasi-deterministic millimeter-wave channel models," IEEE Access, vol. 11, pp. 34529-34543, 2023.

[28] P. Jain, A. Tewari, and I. Dhillon, "Orthogonal matching pursuit with replacement," Advances in neural information processing systems, vol. 24, 2011.

Published

2026-04-01

Issue

Vol. 45 No. 2 (2026): April Issue

Section

Articles

License

Copyright (c) 2026 Mehran University Research Journal of Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite

Hybrid Model for Data-Driven Channel Estimation in mmWave Massive MIMO Systems with Compressed Sensing and Deep Learning. (2026). Mehran University Research Journal of Engineering and Technology, 45(2), 204-216. https://doi.org/10.22581/0712

Similar Articles

11-20 of 30

You may also start an advanced similarity search for this article.