Machine Learning Assisted Design of a Compact Asymmetrical Slotted Rectangular Antenna for 6G Applications

Abstract This paper presents a machine learning (ML)–assisted design of a novel asymmetrical open-slotted rectangular antenna for 6G wireless communication systems. The proposed antenna achieves triple-band operation at 10.2–10.6 GHz, 11.3–12.2 GHz, and a wideband range from 15.2 to 24.2 GHz, all within the 6G candidate upper-mid band (7.125–24.25 GHz). A dataset comprising 108,108 samples was generated through parametric CST simulations by varying key antenna design parameters, with each of the 108 antenna geometries evaluated at 1001 frequency points. To predict and optimize the reflection coefficient of an antenna, various ML models were trained including Decision Tree, Random Forest, Gradient Boosting, K-Nearest Neighbors and XGBoost. Among the evaluated machine learning models, Random Forest demonstrated the best predictive performance, achieving an R2 value of 0.9961 and a root mean square error (RMSE) of 0.2883, with a mean absolute percentage error (MAPE) of only 0.9631%. Experimental validation shows good match between measured and predicted results. The peak gain of the optimized antenna is 7.4 dBi along with a radiation efficiency and total efficiency of 96.1% and 94.5% respectively. The results of this study show that ML-driven approaches can efficiently facilitate antenna design and optimization for high-performance 6G communication systems.

Authors

Institutions

Publication Details

Journal
Engineering Research Express
Published
2026-11-17
DOI
https://doi.org/10.1088/2631-8695/aec374
Primary Topic
Antenna Design and Analysis
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Machine Learning Assisted Design of a Compact Asymmetrical Slotted Rectangular Antenna for 6G Applications

Mustafa Seçmen, Sibel Yenikaya, Sanaa Irıqat
7 links
Engineering Research Express
Antenna Design and Analysis
article

Machine Learning Assisted Design of a Compact Asymmetrical Slotted Rectangular Antenna for 6G Applications

Mustafa Seçmen, Sibel Yenikaya, Sanaa Irıqat
article en

Abstract

Abstract This paper presents a machine learning (ML)–assisted design of a novel asymmetrical open-slotted rectangular antenna for 6G wireless communication systems. The proposed antenna achieves triple-band operation at 10.2–10.6 GHz, 11.3–12.2 GHz, and a wideband range from 15.2 to 24.2 GHz, all within the 6G candidate upper-mid band (7.125–24.25 GHz). A dataset comprising 108,108 samples was generated through parametric CST simulations by varying key antenna design parameters, with each of the 108 antenna geometries evaluated at 1001 frequency points. To predict and optimize the reflection coefficient of an antenna, various ML models were trained including Decision Tree, Random Forest, Gradient Boosting, K-Nearest Neighbors and XGBoost. Among the evaluated machine learning models, Random Forest demonstrated the best predictive performance, achieving an R2 value of 0.9961 and a root mean square error (RMSE) of 0.2883, with a mean absolute percentage error (MAPE) of only 0.9631%. Experimental validation shows good match between measured and predicted results. The peak gain of the optimized antenna is 7.4 dBi along with a radiation efficiency and total efficiency of 96.1% and 94.5% respectively. The results of this study show that ML-driven approaches can efficiently facilitate antenna design and optimization for high-performance 6G communication systems.

Engineering Research Express
Bursa Uludağ Üni̇versi̇tesi̇ (TR), Al-Quds University (PS), Yaşar University (TR)
Ege Üniversitesi
Industry, innovation and infrastructure
Antenna Design and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon