A Study on the Potential of ML and DL Regression in Antenna Design: The Case Study of a Rectangular Microstrip Patch Antenna
Received: 23 July 2025 | Revised: 6 September 2025 and 24 September 2025 | Accepted: 9 October 2025 | Online: 8 December 2025
Corresponding author: Achmad Affandi
Abstract
This article presents an in-depth, comprehensive overview of Machine Learning (ML) regression and Deep Learning (DL) regression for the design and optimization of Microstrip Antennas (MSAs) in developing modern communication technologies. The study introduces a novel approach that leverages DL and neural network architectures to enhance the efficiency and accuracy of theoretical Rectangular MSA (RMSA) analysis within the 1–4 GHz frequency range. By employing ML and DL regression techniques, the method enables precise prediction of critical RMSA parameters, thereby streamlining the design process and enhancing overall design efficiency. The proposed approach offers significant advantages by reducing the reliance on domain-specific expertise throughout the RMSA design cycle. This study constructs a custom data generator that produces 1,920 samples. The results demonstrate that ML techniques yield strong predictive performance, whereas DL models exhibit architectural flexibility and high representational capacity, enabling consistently accurate predictions of parameters, such as S11, bandwidth, and Voltage Standing Wave Ratio (VSWR), even for nonlinear antenna geometries. The Tabular Network (TabNet), which integrates interpretability with efficient data processing, emerges as a competitive and reliable tool, particularly for Multi-Input Multi-Output (MIMO) cases.
Keywords:
modern communication, Deep Learning (DL) regression, geometry prediction, Machine Learning (ML) regression, Tabular Network (TabNet)Downloads
References
A. Y. Al-Zahrani and M. Najim, "Design and Implementation of a High Gain Hexagon Loop Antenna for 5G and WLAN Application," Engineering, Technology & Applied Science Research, vol. 14, no. 4, pp. 15620–15624, Aug. 2024. DOI: https://doi.org/10.48084/etasr.7323
J. Zhang, J. Xu, Q. Chen, and H. Li, "Machine-Learning-Assisted Antenna Optimization With Data Augmentation," IEEE Antennas and Wireless Propagation Letters, vol. 22, no. 8, pp. 1932–1936, Aug. 2023. DOI: https://doi.org/10.1109/LAWP.2023.3269811
J. S. Alkasassbeh, A. Y. Hindi, I. Trrad, M. O. Dwairi, E. A. Dwairi, and M. Alja’fari, "Design and Optimization of a Compact Inset Feed Microstrip Antenna for 5G Applications with Enhanced MIMO Performance," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 21373–21382, Apr. 2025. DOI: https://doi.org/10.48084/etasr.10094
A. Tiwari, A. A. Khurshid, and K. Sharma, "Compact wearable microstrip antenna design using hybrid quasi-Newton and Taguchi optimization," Scientific Reports, vol. 15, no. 1, Jan. 2025, Art. no. 116. DOI: https://doi.org/10.1038/s41598-024-83864-9
D. Mathur, S. K. Bhatnagar, and V. Sahula, "Quick Estimation of Rectangular Patch Antenna Dimensions Based on Equivalent Design Concept," IEEE Antennas and Wireless Propagation Letters, vol. 13, pp. 1469–1472, 2014. DOI: https://doi.org/10.1109/LAWP.2014.2334362
J. Dinkic, M. N. Stevanovic, and A. Djordjevic, "Physical Models for Influence of Substrate Permittivity on the Gain of Microstrip Antennas," IEEE Transactions on Antennas and Propagation, vol. 71, no. 11, pp. 9078–9083, Nov. 2023. DOI: https://doi.org/10.1109/TAP.2023.3310165
A. Esmaeilkhah, C. Ghobadi, J. Nourinia, and M. Majidzadeh, "Effect of Substrate Scaling on Microstrip Patch Antenna Performance," Advanced Electromagnetics, vol. 7, no. 5, pp. 82–86, Nov. 2018. DOI: https://doi.org/10.7716/aem.v7i5.840
D. R. Prado, J. A. López-Fernández, M. Arrebola, and G. Goussetis, "Support Vector Regression to Accelerate Design and Crosspolar Optimization of Shaped-Beam Reflectarray Antennas for Space Applications," IEEE Transactions on Antennas and Propagation, vol. 67, no. 3, pp. 1659–1668, Mar. 2019. DOI: https://doi.org/10.1109/TAP.2018.2889029
M. R. Khan, C. L. Zekios, S. Bhardwaj, and S. V. Georgakopoulos, "A Deep Learning Convolutional Neural Network for Antenna Near-Field Prediction and Surrogate Modeling," IEEE Access, vol. 12, pp. 39737–39747, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3377219
D. Yago, G. Sal-Anglada, D. Roca, J. Cante, and J. Oliver, "Machine learning in solid mechanics: Application to acoustic metamaterial design," International Journal for Numerical Methods in Engineering, vol. 125, no. 14, July 2024, Art. no. e7476. DOI: https://doi.org/10.1002/nme.7476
Q. Wu, W. Chen, C. Yu, H. Wang, and W. Hong, "Multilayer Machine Learning-Assisted Optimization-Based Robust Design and Its Applications to Antennas and Array," IEEE Transactions on Antennas and Propagation, vol. 69, no. 9, pp. 6052–6057, Sept. 2021. DOI: https://doi.org/10.1109/TAP.2021.3069491
T. Naous, A. A. Merie, S. K. A. Khatib, M. Al-Husseini, R. M. Shubair, and H. M. El Misilmani, "Machine Learning-Aided Design of Dielectric-Filled Slotted Waveguide Antennas With Specified Sidelobe Levels," IEEE Access, vol. 10, pp. 30583–30595, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3158976
Y.-F. Liu, L. Peng, and W. Shao, "An Efficient Knowledge-Based Artificial Neural Network for the Design of Circularly Polarized 3-D-Printed Lens Antenna," IEEE Transactions on Antennas and Propagation, vol. 70, no. 7, pp. 5007–5014, July 2022. DOI: https://doi.org/10.1109/TAP.2022.3140313
Y. Su, Y. Yin, S. Li, H. Zhao, and X. Yin, "Bandwidth Improvement for Patch Antenna via Knowledge-Based Deep Reinforcement Learning," IEEE Antennas and Wireless Propagation Letters, vol. 23, no. 12, pp. 4094–4098, Dec. 2024. DOI: https://doi.org/10.1109/LAWP.2024.3432182
L.-Y. Xiao, W. Shao, F.-L. Jin, and B.-Z. Wang, "Multiparameter Modeling With ANN for Antenna Design," IEEE Transactions on Antennas and Propagation, vol. 66, no. 7, pp. 3718–3723, July 2018. DOI: https://doi.org/10.1109/TAP.2018.2823775
D. Sarkar, T. Khan, Jayadeva, and A. A. Kishk, "Machine Learning Assisted Hybrid Electromagnetic Modeling Framework and Its Applications to UWB MIMO Antennas," IEEE Access, vol. 11, pp. 19645–19656, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3248961
W. Chen, Q. Wu, B. Han, C. Yu, H. Wang, and W. Hong, "Efficient Incremental Variable-Fidelity Machine-Learning-Assisted Hybrid Optimization and Its Application to Multiobjective Antenna Design," IEEE Transactions on Antennas and Propagation, vol. 72, no. 12, pp. 9347–9354, Dec. 2024. DOI: https://doi.org/10.1109/TAP.2024.3481663
B. Han, Q. Wu, C. Yu, H. Wang, and W. Hong, "Low-Wind-Load Broadband Dual-Polarized Antenna and Array Designs Using Sequential Multiphysics Machine-Learning-Assisted Optimization," IEEE Transactions on Antennas and Propagation, vol. 73, no. 1, pp. 135–148, Jan. 2025. DOI: https://doi.org/10.1109/TAP.2024.3503916
W. Li, Q. Li, J. Zhou, L. Ye, and Y. Liu, "Wideband Patch Antenna With Ground Radiation Mode and Patch Radiation Mode," IEEE Access, vol. 7, pp. 173358–173365, 2019. DOI: https://doi.org/10.1109/ACCESS.2019.2957117
M. Joler and L. Mihalić, "A Subtlety of Sizing the Inset Gap Width of a Microstrip Antenna When Built on an Ultra-Thin Substrate in the S-Band," Sensors, vol. 23, no. 1, Jan. 2023, Art. no. 213. DOI: https://doi.org/10.3390/s23010213
Q. Wu, Y. Cao, H. Wang, and W. Hong, "Machine-learning-assisted optimization and its application to antenna designs: Opportunities and challenges," China Communications, vol. 17, no. 4, pp. 152–164, Apr. 2020. DOI: https://doi.org/10.23919/JCC.2020.04.014
Q. Niu, W. Shi, Y. Xu, and W. Wen, "High-accuracy NLOS identification based on random forest and high-precision positioning on 60 GHz millimeter wave," China Communications, vol. 20, no. 12, pp. 96–110, Dec. 2023. DOI: https://doi.org/10.23919/JCC.fa.2021-0742.202312
Downloads
How to Cite
License
Copyright (c) 2025 Agusriandi, Achmad Affandi, Eko Setijadi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
