This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Shweta Zambare,
Shivani Shendage,
Pratiksha Surve,
Nilophar Shaikh,
Vaibhav Godase,
- UG Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
- UG Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
- UG Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
- UG Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
- Assistant Professor, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
Abstract
Ultra-wideband antennas require wide impedance bandwidth while maintaining stable radiation characteristics and suppressing interference from coexisting narrowband wireless services. Conventional optimization of UWB antenna geometries generally requires repeated full-wave electromagnetic simulations, making parameter exploration computationally expensive. This paper proposes an artificial-intelligence-assisted methodology for designing a compact UWB monopole antenna with a tunable band-notch characteristic. The proposed antenna uses a microstrip-fed planar monopole printed on an FR-4 substrate, while a tunable resonant slot is introduced into the radiating structure to reject an interfering frequency band. A simulation dataset containing 1,200 antenna configurations is considered for machine-learning-assisted modeling. Geometrical parameters including radiator length, radiator width, feed length, feed width, slot length, slot width, ground-plane length, and ground-plane gap are used as input variables. Random Forest, Support Vector Regression, Artificial Neural Network, and XGBoost models are employed to predict resonant frequency, impedance bandwidth, notch frequency, and notch bandwidth. An illustrative XGBoost model achieves values of 0.96, 0.95, 0.97, and 0.94 for the corresponding outputs. A multi-objective optimization procedure is then used to obtain a compact design with an operating range of approximately 3.1–10.6 GHz and a tunable rejection band centered near 5.5 GHz. The illustrative optimized design provides a notch bandwidth of approximately 0.72 GHz, peak gain of 4.8 dBi outside the rejection band, and radiation efficiency above 85% over most of the passband. The proposed methodology demonstrates how machine-learning surrogate models can reduce the number of full-wave simulations required during antenna optimization.
Keywords: UWB antenna, band notch, machine learning, XGBoost, microstrip antenna, optimization, WLAN interference, electromagnetic simulation
References
1. Godase V, Pawar P, Nagane S, Kumbhar S. Automatic railway horn system using node MCU. Journal of Control & Instrumentation. 2024 Jan;15(1).
2. Shevada L, Sayyad J, Kumar S. Design and optimization of miniaturized UWB MIMO antenna using ML methods for multiband applications. Discover Artificial Intelligence. 2026 Jun 11.
3. Jamadade VK, Ghodke MG, Katakdhond SS, Godase V. A comprehensive review on scalable Arduino radar platform for real-time object detection and mapping. Journal of Microprocessor and Microcontroller Research. 2025 May;2(2):1-2.
4. Gadhafi R, Himeur Y, Purushothama J. Machine Learning and Deep Learning for Antenna and Electromagnetic Systems: A Structured Review of Methods, Applications, and Benchmarking. IEEE Access. 2026 Jun 16.
5. Godase V. A comprehensive study of revolutionizing EV charging with solar-powered wireless solutions. Advance Research in Power Electronics and Devices e-ISSN. 2025 Apr 18:3048-7145.
6. Rahaman R, Ahammed B, Karim T, Alim MA. Compact and high-efficiency mmWave microstrip antenna for 5G with machine learning-based performance prediction. Optical and Quantum Electronics. 2025 Dec 12;58(1):29.
7. Godase V. Advanced Neural Network Models for Optimal Energy Management in Microgrids with Integrated Electric Vehicles. InProceedings of the International Conference on Trends in Material Science and Inventive Materials (ICTMIM-2025) DVD Part Number: CFP250J1-DVD 2025 Apr 18.
8. Trimukhe MA, Hogade BG. Compact UWB antenna with tunable band-notch characteristics using varactor diode. Progress In Electromagnetics Research C. 2019;97:15-28.
9. Cicchetti R, Miozzi E, Testa O. Wideband and UWB antennas for wireless applications: A comprehensive review. International Journal of Antennas and Propagation. 2017;2017(1):2390808.
10. Srivastava U, Gupta S, Kumari P, Patri U. Dual-band circularly polarized dielectric resonator antenna with wide impedance bandwidth and machine learning-assisted performance prediction. Results in Physics. 2025 Nov 19:108531.
11. Farha KA, Jasmine PM, Fasmi KA. Design, implementation, and explainable AI evaluation of a compact UWB microstrip patch antenna for 6G applications. AEU-International Journal of Electronics and Communications. 2025 Dec 27:156178.
12. Amraoui Y, Halkhams I, El Alami R, Jamil MO, Qjidaa H, Bossoufi B. Application of Artificial Intelligence in Antenna Design: Fundamentals, Algorithms, Applications and Opportunities. Archives of Computational Methods in Engineering. 2026 Jul 7:1-33.
Journal of Microwave Engineering and Technologies
| Volume | 13 | |
| 02 | ||
| Received | 21/09/2026 | |
| Accepted | 23/09/2026 | |
| Published | 26/10/2026 | |
| Publication Time | 35 Days |