Abstract—This paper presents a new, compact, multiband antenna designed for the Internet of Things (IoT) and Fifth Generation (5G) wireless networks to address the growing need for efficient and multi-functional antennas in modern communication systems. The antenna development progresses through four phases to achieve the desired prototype. In the first phase, a single-band antenna utilizing an inverted L-shaped element is designed. The second phase introduces a U-shaped dual-band configuration. The third phase combines a triangular shape with a reversed L structure to attain two distinct resonance frequencies. Finally, the fourth phase culminates in a triple-band antenna resonating at 1.8 GHz, 2.4 GHz, and 5 GHz, showcasing the design’s adaptability. The final prototype is implemented on a cost-effective FR-4 dielectric substrate, making the antenna suitable for Wi-Fi, Industrial, Scientific, and Medical (ISM) bands, Wireless Local Area Network (WLAN), and 5G applications. The design has been fabricated andexperimentally validated. To further enhance performance evaluation and reduce the computational burden associated with extensive parametric studies, a data-driven machine learning approach is employed for rapid prediction and optimization, using supervised Machine Learning (ML) regression models to validate the antenna gain based on simulated design parameters. The models are evaluated using statistical performance metrics, including the variance score, R-squared, mean squared error, root mean square error, and mean absolute error.

Index Terms—multiband antenna; Internet of Things (IoT); Industrial, Scientific, and Medical (ISM) bands; Machine Learning (ML); Fifth Generation (5G)

Cite: Wazie M. Abdulkawi, Abdallah M. Nabil, Md Afzalur Rahman, Samir Salem Al-Bawri, Hassan Yousif Ahmed, and Yosef T. Aladadi, "A Compact Multiband Antenna for Internet of Things (IoT) and 5G Applications: Design Optimization and Machine Learning (ML)-based Validation," International Journal of Electrical and Electronic Engineering & Telecommunications, vol. 15, no. 4, pp. 233-242, 2026. doi: 10.18178/ijeetc.15.4.233-242

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).