Machine Learning-Optimized Compact Wearable Frequency Reconfigurable Antenna for Sub-6 GHz - mm-Wave 5G Integration

Sep 17, 2026

Uploaded by Levi

Future 5G wireless systems require integrating sub-6 GHz and millimeter-wave (mm-wave) bands despite their extreme frequency disparity. The work presents a machine learning-optimized compact wearable, frequency-reconfigurable antenna built on a flexible Rogers Duroid substrate. A circular resonator at 28 GHz is extended to dual-band (3.5 and 28 GHz) via an H-shaped slot, with PIN-diode switching between ON and OFF states. Measured bandwidths, gains, efficiencies, radiation patterns, and SAR compliance are reported, and ML regression predicts S11 using high-accuracy algorithms.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Introduction

Antenna Design and Reconfiguration

Dual-band operation and switching states

Measurements and Performance Results

Bandwidth, gain, efficiency, and radiation patterns

SAR and compliance

Machine Learning-Based S11 Prediction

Conclusion

bradscholars Machine Learning-Optimized Compact Wearable Frequency Reconfigurable Antenna for Sub-6 GHz/ mm-Wave 5G Integration | Item Type | Article | | --- | --- | | Authors | Salisu , Abubakar;Elwanis , Mahmud A. ;Elfergani , Issa T. ;Musa , U. ;Alfares , A. ;Gharbia , Ibrahim;Rodriguez , J. ;See , Chan H. ;AbdAlhameed , Raed | | Citation | Salisu A , See CH , Elfergani I , et al (2025) Machine LearningOptimized Compact Wearable Frequency Reconfigurable Antenna for Sub-6 GHz/ mm-Wave 5G Integration. Scientific Reports. 15: 44912. | | Rights | © 2025 The Authors. Published by Nature: Scientific Reports. Articles are published open access under a CC BY (Creative Commons Attribution 4.0 International licence) licence. | | Download date | 2026-03-18 17:18:09 | | Link to Item | [https://bradscholars.brad.ac. uk/handle/10454/20712](https://bradscholars.brad.ac. uk/handle/10454/20712) | [www. nature.com/scientificreports](www. nature.com/scientificreports) OPEN Machine learning-optimized compact wearable frequency reconfigurable antenna for sub- 6 GHz/mm-wave 5G integration Abubakar Salisu1􀀍, Mahmud Abd Elwanis1, Issa Elfergani1,2, Umar Musa3􀀍, AbdulgaforAlfares4, Ibrahim Gharbia1, Jonathan Rodriguez2, Chan H. See5 & Raed Abd-alhameed1,6􀀍 Future 5G wireless systems will have substantial challenges in integrating the sub-6 GHz and millimeter-wave (mm-wave) bands due to their massive frequency ratios. This paper proposes a machine learning-optimized compact wearable frequency-reconfigurable antenna for sub-6 GHz/mmwave 5G integration. Fabricated on a flexible Rogers Duroid substrate (27.8 × 14 × 0.508 mm3), the antenna initially employs a circular structure resonating at 28 GHz. Dual-band operation (3.5 GHz and 28 GHz) is achieved by etching an H-shaped slot into the rectangular patch. A PIN diode is employed toreconfigure the proposed antenna in theON and OFF states. In the ON state, the antenna operates at 3.5 GHz and 28 GHz, achieving measured bandwidths of 25.4% and 73.2%, gains of 3.63 dBi and 5.25 dBi, and radiation efficiencies of 90.5% and 88%, respectively. In the OFF state, the antenna operates at 28 GHz, achieving a measured bandwidth of 72.9%, gain of 6.2 dBi, and a radiation efficiency of 89% . Bidirectional E-plane and omnidirectional H-plane radiation patterns are maintained across both bands. At 3.5 GHz, the specific absorption rate (SAR) value for 1 g and 10 g of human tissue is 0.438 W/ kg and 0.0147 W/kg, while at 28 GHz, the SAR value is 0.801 W/kg and 1.09 W/kg, which comply with the FCC and ICNIRP standards. Bending tests (lap, chest, arm) demonstrate stable on-body performance. The antenna’s S11 was predicted using a supervised ML regression framework. Among tested algorithms, the decision tree achieved state-of-the-art accuracy (R2: 97.80%) with minimal errors (MAE: 0.72, MSE: 0.28, MSLE: 0.56, RMSLE: 0.81, RMSE: 0.66). The proposed antenna system is suitable for future 5G devices. Keywords Frequency reconfigurability, Machine learning, SAR, Bending investigation, PIN diode The growing demand for high-speed multimedia data transmission has become increasingly critical in today’s digital landscape1,2. To address the need for rapid data transfer and low latency, numerous countries have deployed fifth-generation (5G) communication systems3–5. As a leading future communication technology, 5G is expected to surpass the limitations of existing mobile and local area network technologies6. The Federal Communications Commission (FCC) has allocated specific frequency bands for 5G applications, including 3.5 GHz (sub-6 GHz range) and 24–30 GHz, 37 GHz, 39 GHz, and 64–71 GHz for the mm-wave range7,8. Among these, the 3.5 GHz and 24–30 GHz bands are among the most widely adopted 5G frequencies globally, including in countries like China9. To leverage the broader bandwidth available at higher frequencies, cellular systems are transitioning to mm-wave bands, which enable increased data rates. However, whil

FAQs

What antenna functionality does the paper target for future 5G devices?

It targets a compact wearable antenna that can be reconfigured in frequency for sub-6 GHz and mm-wave (28 GHz) 5G integration using switching between ON and OFF states.

How is dual-band operation achieved in the proposed antenna?

Dual-band operation at 3.5 GHz and 28 GHz is achieved by etching an H-shaped slot into a rectangular patch, while an initial circular structure resonates at 28 GHz.

How does the paper ensure user safety regarding electromagnetic exposure?

It evaluates the specific absorption rate (SAR) for 1 g and 10 g tissue at both 3.5 GHz and 28 GHz and reports compliance with FCC and ICNIRP standards.

Sep 17, 2026

Uploaded by Levi