Machine Learning-Based High-Isolation Dual-Band MIMO Antenna with Gain Prediction for 5G Networks at 28/38 GHz
DOI:
https://doi.org/10.24237/djes.2026.19301Keywords:
MIMO, Machine Learning , Regression modelling, 28 GHz and 36 GHz, 5GAbstract
This paper proposes an ML-driven compact dual-band four-port MIMO antenna for next-generation 5G mm-wave communications at 28/38 GHz. The challenge of integrating ML-based gain prediction with a high-isolation four-element MIMO architecture is discussed. The antenna is designed on a Rogers RT/duroid 6002 substrate with a small footprint of 15.82 × 15.82 mm2 (1.48λ₀ × 1.48λ₀) and is systematically evolved from a single element to 2-port and 4-port MIMO configurations with the maximum gains of 8.5 dBi and 7.25 dBi with the radiation efficiencies of 95% and 96% at 28 GHz and 38 GHz, respectively. The 4-port MIMO system shows excellent isolation over 30 dB, envelope correlation coefficient below 0.001, diversity gain over 0.95, and channel capacity loss of only 0.01 bps/Hz at 28 GHz, which confirms the excellent spatial diversity and spectral efficiency for 5G deployment. To accelerate the design cycle, a comprehensive ML framework was developed using six advanced regression algorithms, with inputs including key geometrical parameters like slot dimensions, impedance transformer geometry and feed line specifications. Among the models evaluated, the Extra Trees Regressor model achieved the best predictive performance with over 98% accuracy in the estimation of the bandwidth at 38 GHz and approximately 94% accuracy in the prediction of the gain at 28 GHz. This provides a scalable design paradigm for future mm-wave MIMO antennas and enables a fast simulation-free performance prediction method. Extra Trees predictions, validated through test-set evaluation and K-fold cross-validation, confirm effectiveness of the proposed four-port MIMO antenna for 28/38-GHz 5G applications.
Downloads
References
[1] S. Nizar Anouar B., Islem B. H., Lassaad L., and Ali G., “Millimeter-Wave Dual-Band MIMO Antennas for 5G Wireless Applications, Journal of Infrared, Millimeter, and Terahertz Waves,” vol. 44, pp. 297–312, 2023. DOI: https://doi.org/10.1007/s10762-023-00914-5
[2] B. Kaur, Dadkhah S, Shoeleh F, Neto EC, Xiong P, Iqbal S, Lamontagne P, Ray S, Ghorbani AA. “Internet of things (IoT) security dataset evolution: Challenges and future directions. Internet of Things,” 2023 Jul 1;22:100780.DOI:https://doi.org/10.1016/j.iot.2023.100780
[3] T. Saeidi, A. J. A. Al-Gburi, and S. Karamzadeh, “A Miniaturized Full-Ground Dual-Band MIMO Spiral Button Wearable Antenna for 5G and Sub-6 GHz Communications,” Sensors, vol. 23, no. 4, p. 1997, 2023. DOI: https://doi.org/10.3390/s23041997
[4] M.M. Alam, Ouameur, M.A., M.E. Haque, Haque, M.A., Tiang, J.J., Singh, N.S.S., Alsulami, R. and S. Alzahrani, “Circular MIMO antenna with ML-based bandwidth and isolation prediction for 6G communications,” Sci Rep 16, 19363 (2026). DOI: https://doi.org/10.1038/s41598-026-54274-w
[5] I.-J. Hwang Oh J.-I., Jo H.-W., Kim K.-S., Yu J.-W., Lee D.-J. “28 GHz and 38 GHz dual-band vertically stacked dipole antennas on flexible liquid crystal polymer substrates for millimeter-wave 5G cellular handsets,” IEEE Trans. Antennas Propag. 2022;70(5):3223–3236. DOI: https://doi.org/10.1109/TAP.2021.3137234
[6] BA Esmail, S. Koziel “Design and optimization of metamaterial-based dual-band 28/38 GHz 5G MIMO antenna with modified ground for isolation and bandwidth improvement,” IEEE Antennas and Wireless Propagation Letters. 2022 Dec 28;22(5):1069-73. DOI: https://doi.org/10.1109/LAWP.2022.3232622
[7] K Cuneray, Akcam N, Okan T, Arican GO. “28/38 GHz dual-band MIMO antenna with wideband and high gain properties for 5G applications,” AEU-International Journal of Electronics and Communications. 2023 Apr 1;162:154553.DOI:https://doi.org/10.1016/j.aeue.2023.154553
[8] M. Hussain, Mousa Ali, E., Jarchavi, S.M.R., Zaidi, A., Najam, A.I., Alotaibi, A.A., Althobaiti, A. and Ghoneim, S.S., 2022. “Design and characterization of compact broadband antenna and its MIMO configuration for 28 GHz 5G applications,” Electronics, 11(4), p.523. DOI: https://doi.org/10.3390/electronics11040523
[9] M. M. Alam, Yusof, N. A. T., Faudzi, A. A. M., Tomal, M. R. I., Haque, M. E., & Rahman, M. S. (2025), “Machine learning-based approach for bandwidth and frequency prediction of circular SIW antenna,” Journal of King Saud University–Engineering Sciences, 37(4), 1-19. DOI: https://doi.org/10.1007/s44444-025-00010-0
[10] MA Haque, Nirob JH, Nahin KH, Singh NS, Paul LC, Algarni AD, ElAffendi M, Ateya AA. “Regression supervised model techniques THz MIMO antenna for 6G wireless communication and IoT application with isolation prediction,” Results in Engineering. 2024 Dec 1;24:103507.DOI:https://doi.org/10.1016/j.rineng.2024.103507
[11] M. M. Alam, Yusof, N. A. T., Wahab, Y. A., Karim, M. S. A., & Rahman, M. S. (2025), “Design and optimization of Π-shaped slotted dual-band SIW antenna for 5G applications,” Applications of Modelling and Simulation, 9, 92-106. DOI: https://arqiipubl.com/ojs/index.php/AMS_Journal/article/view/819/213
[12] A.K. Dwivedi, N.K. Narayanaswamy, K.K.V. Penmatsa, S.K. Singh, A. Sharma, V. Singh, “Circularly polarized printed dual port MIMO antenna with polarization diversity optimized by machine learning approach for 5G NR n77/n78 frequency band applications,” Sci. Rep. 13 (1) (2023) 13994. DOI: https://doi.org/10.1038/s41598-023-41302-2
[13] N. Chhaule, C. Koley, S. Mandal, A. Onen, & T. S. Ustun, “A comprehensive review on conventional and machine Learning-Assisted design of 5G microstrip patch antenna,” Electronics, 2024, 13(19), 3819. DOI: https://doi.org/10.3390/electronics13193819
[14] M. Rana, S. M. Rabiul Islam, and S. Sarker, “Machine learning based on patch antenna design and optimization for 5 G applications at 28GHz,” Results Engineering, vol. 24, p. 103366, Dec. 2024. DOI: https://doi.org/10.1016/j.rineng.2024.103366
[15] S. S. M Al-Bawri, W. M. Abdulkawi, A. A. Sheta, Md, Moniruzzaman, “A High‐Performance 3D Eight‐Port THz‐MIMO antenna system verified with machine learning for enhanced wireless communication systems,” Int. J. Commun. Syst. 38 (4), e6006. DOI: https://doi.org/10.1002/dac.6006
[16] S. O. Hasan, Ezzulddin, S. K., Hammd, O. S., & Mahmud, R. H. “Design and performance analysis of rectangular microstrip patch antennas using different feeding techniques for 5G applications,” International journal of electrical and computer engineering systems, 14(8), 2023, 833-841. DOI: https://doi.org/10.32985/ijeces.14.8.2
[17] M.M. Alam, Ouameur M.A., Hasan M.M., Alyami G., Haque M.A., Alshammari M.A., Singh N.S., Shaman H. “Machine learning-based dual-band circular MIMO antennas for high-performance 6G IoT system,” Results Engineering, 2025:108107. DOI: https://doi.org/10.1016/j.rineng.2025.108107
[18] Al-Atyar, R. A., Farahat, A. E., Hussein, K. F. A., Shaalan, A. A., & M. F. Ahmed, “Dual-Band (28/38 GHz)–Loaded Patch Antenna for Millimeter-Wave Communication,” Journal of Infrared, Millimeter, and Terahertz Waves, 46(3), 22, 2025. DOI: https://doi.org/10.1007/s10762-025-01036-w
[19] Y.-F. Liu, L.-Y. Xiao, and Q. H. Liu, “Machine learning-based design scheme for multifunctional antenna arrays with reconfigurable scattering patterns,” IEEE Trans. Antennas Propag., vol. 73, no. 7, pp. 4535–4548, Jul. 2025. DOI: https://doi.org/10.1109/TAP.2025.3552213
[20] F. Taher, Hamadi, H.A., Alzaidi, M.S., Alhumyani, H., Elkamchouchi, D.H., Elkamshoushy, Y.H., Haweel, M.T., Sree, M.F.A. and Fatah, S.Y.A., “Design and analysis of circular polarized two-port MIMO antennas with various antenna element orientations,” Micromachines, 14(2), p.380, 2023. DOI: https://doi.org/10.3390/mi14020380
[21] S.-H. Kim, J.-Y. Chung, “Analysis of the envelope correlation coefficient of MIMO antennas connected with suspended lines,” J. Electromagn. Eng. Sci 20 (2), 83–90, Apr.2020.DOI: https://doi.org/10.26866/JEES.2020.20.2.83
[22] H. Wang, Q. Zheng, Q. Li and X. -X. Yang, “Isolation Improvement and Bandwidth Enhancement of Dual-Band MIMO Antenna Based on Metamaterial Wall,” in IEEE Antennas and Wireless Propagation Letters, vol. 24, no. 5, pp. 1144-1148, May 2025. DOI: https://doi.org/10.1109/LAWP.2025.3527688
[23] M.M. Basha, P. Pradeep, S. Gundala, J. Syed, “Design of compact and high gain dual-band four-port MIMO antenna array for mm-wave 5G communications,” Results Eng. 25 (2025) 104153. DOI: https://doi.org/10.1016/j.rineng.2025.104153
[24] Y. Amraoui, I. Halkhams, R.E. Alami, M.O. Jamil, H. Qjidaa, “High gain MIMO antenna with multiband characterization for terahertz applications,” Sci. Afr. 26 (2024) e02380. DOI: https://doi.org/10.1016/j.sciaf.2024.e02380
[25] X. Yang, “Circularly polarized antenna array synthesis based on machine-learning-assisted surrogate modeling,” IEEE Trans. Antennas Propag., vol. 72, no. 2, pp. 1469–1482, Feb. 2024. DOI: https://doi.org/10.1109/TAP.2023.3335808
[26] S. Xi, J. Cai, L. Shen, Q. Li, and G. Liu, “Dual-Band MIMO Antenna with Enhanced Isolation for 5G NR Application,” Micromachines, vol. 14, no. 1, p. 95, Dec. 2022. DOI: https://doi.org/10.3390/mi14010095
[27] Y. Zhong, P. Renner, W. Dou, G. Ye, J. Zhu, and Q. H. Liu, “A machine learning generative method for automating antenna design and optimization,” IEEE J. Multiscale Multiphys. Comput. Tech., vol. 7, pp. 285–295, 2022. https://doi.org/10.1109/JMMCT.2022.3211178
[28] M. Bilal, S. I. Naqvi, N. Hussain, Y. Amin, and N. Kim, “High-Isolation MIMO Antenna for 5G Millimeter-Wave Communication Systems,” Electronics, vol. 11, no. 6, p. 962, Mar. 2022. DOI: https://doi.org/10.3390/electronics11060962
[29] M.M. Alam, Rahman, M.S., Karim, M.S.A., Wahab, Y.A. and Yusof, N.A.T., “Design and optimization of a high-efficiency circular SIW patch antenna for satellite communication,” Digital Communications and Networks, Volume 12, Issue 6, June 2026, Pages 977-993. DOI: https://doi.org/10.1016/j.dcan.2026.03.001
[30] J Chen, de Hoogh K, Gulliver J, Hoffmann B, Hertel O, Ketzel M, Bauwelinck M, Van Donkelaar A, Hvidtfeldt UA, Katsouyanni K, Janssen NA. “A comparison of linear regression, regularization, and machine learning algorithms to develop Europe-wide spatial models of fine particles and nitrogen dioxide,” Environment international. 2019 Sep 1;130:104934. DOI: https://doi.org/10.1016/j.envint.2019.104934
[31] X. Zhu, X. Hu, L. Yang, W. Pedrycz and Z. Li, “A Development of Fuzzy-Rule-Based Regression Models Through Using Decision Trees, ” in IEEE Transactions on Fuzzy Systems, vol. 32, no. 5, pp. 2976-2986, May 2024. DOI: https://doi.org/10.1109/TFUZZ.2024.3365572
[32] D. Borup, Christensen, B. J., Mühlbach, N. S., & Nielsen, M. S. (2023). “Targeting predictors in random forest regression,” International Journal of Forecasting, 39(2), 841-868. DOI: https://doi.org/10.1016/j.ijforecast.2022.02.010
[33] S.R. Shakya, M. Kube, Z. Zhou, “A comparative analysis of machine learning approach for optimizing antenna design,” Int. J. Microw. Wirel. Technol. (Aug. 2023) 1–11. DOI: https://doi.org/10.1017/S1759078723001009
[34] AI Osman, Ahmed AN, Chow MF, Huang YF, El-Shafie A. “Extreme gradient boosting (Xgboost) model to predict the groundwater levels in Selangor Malaysia. Ain Shams Engineering Journal,” 2021 Jun 1;12(2):1545-56. DOI: https://doi.org/10.1016/j.asej.2020.11.011
[35] S. Koziel, Pietrenko-Dabrowska, A. & L. Leifsson, “Antenna optimization using machine learning with reduced-dimensionality surrogates,” Sci. Rep. 14(1), 21567. DOI: https://doi.org/10.1038/s41598-024-72478-w
[36] S. M. Robeson and C. J. Willmott, “Decomposition of the mean absolute error (MAE) into systematic and unsystematic components,” PLOS ONE, vol. 18, no. 2, p. e0279774, Feb. 2023. DOI: https://doi.org/10.1371/journal.pone.0279774
[37] MM Alam, Tomal MR, Faudzi AA, Yusof NA, “ANN-Enabled Gain Prediction and Optimization in Dual-Band SIW Antenna Designs for 5G Networks. Journal of Telecommunications and Information Technology,” 2026 Mar 2:69-78. DOI: https://doi.org/10.26636/jtit.2026.1.2424
[38] P. Takyi-Aninakwa, S. Wang, H. Zhang, Y. Xiao, C. Fernandez, “A NARX network optimized with an adaptive weighted square-root cubature Kalman filter for the dynamic state of charge estimation of lithium-ion batteries,” J. Energy Storage 68 (2023) 107728. DOI: https://doi.org/10.1016/j.est.2023.107728
[39] Gelman A, Goodrich B, Gabry J, Vehtari A. “R-squared for Bayesian regression models,” The American Statistician, 2019 Jul 3. DOI: https://doi.org/10.1080/00031305.2018.1549100
[40] G. Jiang, and W. Wang, “Error estimation based on variance analysis of k-fold cross-validation,” Pattern Recognition, 69, pp.94-106, 2021. DOI: https://doi.org/10.1016/j.patcog.2017.03.025
[41] T. Fushiki, “Estimation of prediction error by using K-fold cross-validation,” Stat Comput 21, 137–146 (2021). DOI: https://doi.org/10.1007/s11222-009-9153-8
[42] R.R. Elsharkawy, Hussein, K.A. & Farahat, A.E. “Dual-Band (28/38 GHz) Compact MIMO Antenna System for Millimeter-Wave Applications,” J Infrared Milli Terahz Waves 44, 1016–1037 (2023). DOI: https://doi.org/10.1007/s10762-023-00943-0
[43] R.N. Tiwari, Sharma, D., Singh, P. et al. “A flexible dual-band 4 × 4 MIMO antenna for 5G mm-wave 28/38 GHz wearable applications,” Sci Rep 14, 14324 (2024). DOI: https://doi.org/10.1038/s41598-024-65023-2
[44] R.H. Elabd, Al-Gburi, A.J.A. “Super-Compact 28/38 GHz 4-Port MIMO Antenna Using Metamaterial-Inspired EBG Structure with SAR Analysis for 5G Cellular Devices,” J Infrared Milli Terahz Waves 45, 35–65 (2024). DOI: https://doi.org/10.1007/s10762-023-00959-6
[45] S. Chidurala, Amara, P.R. “Design and Analysis of Compact Dual Band 4-Port MIMO Antenna for 5G 28/38 GHz Millimeter-Wave Communication,” J Infrared Milli Terahz Waves 46, 60 (2025). DOI: https://doi.org/10.1007/s10762-025-01076-2
[46] J.K. Rai, Ranjan, P., Kumar, S., Chowdhury, R., Kumar, S. and Sharma, A., 2024. “Machine learning‐enabled two‐port wideband MIMO hybrid rectangular dielectric resonator antenna for n261 5G NR millimeter wave,” International Journal of Communication Systems, 37(16), p.e5898. DOI: https://doi.org/10.1002/dac.5898
[47] M.A. Haque, Ananta, R.A., Ahammed, M.S. et al. “High-isolation dual-band MIMO antenna for next-generation 5G wireless networks at 28/38 GHz with machine learning-based gain prediction,” Sci Rep 15, 20782 (2025). DOI: https://doi.org/10.1038/s41598-025-02646-z
[48] MA Haque, Ahammed MS, Socheatra S, Ananta RA, Nirob MJ, Singh NS, Jizat NM, Alsowail S, Al-Bawri SS. “Machine learning based compact MIMO antenna array for 38 GHz millimeter wave application with robust isolation and high efficiency performance,” Results in Engineering. 2025 Mar 1;25:104006. DOI: https://doi.org/10.1016/j.rineng.2025.104006
[49] R.A. Ananta, Alyami, G. et al., “Regression machine learning-based highly efficient dual band MIMO antenna design for mm-Wave 5G application and gain prediction,” Sci Rep 15, 28730 (2025). DOI: https://doi.org/10.1038/s41598-025-13514-1
[50] M.A. Haque, Nirob, J.H., Nahin, K.H. et al., “Machine learning-based technique for gain prediction of mm-wave miniaturized 5G MIMO slotted antenna array with high isolation characteristics,” Sci Rep 15, 276 (2025). DOI: https://doi.org/10.1038/s41598-024-84182-w
[51] Haque MA, Ahammed MS, Ananta RA, Aljaloud K, Jizat NM, Abdulkawi WM, Nahin KH, Al-Bawri SS. “Broadband high gain performance MIMO antenna array for 5 G mm-wave applications-based gain prediction using machine learning approach,” Alexandria Engineering Journal. 2024 Oct 1;104:665-79. DOI: https://doi.org/10.1016/j.aej.2024.08.025
[52] D. Khan, Ahmad, A. & Choi, DY. ,”Dual-band 5G MIMO antenna with enhanced coupling reduction using metamaterials,” Sci Rep 14, 96 (2024). DOI: https://doi.org/10.1038/s41598-023-50446-0
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Md Mahabub Alam, Md. Ashraful Haque, Md Ershadul Haque, Md. Suaibur Rahman
This work is licensed under a Creative Commons Attribution 4.0 International License.
