Haque Md Ashraful, Nirob Jamal Hossain, Nahin Kamal Hossain, Jizat Noorlindawaty Md, Zakariya M A, Ananta Redwan A, Abdulkawi Wazie M, Aljaloud Khaled, Al-Bawri Samir Salem
Department of Electrical and Electronic Engineering, Daffodil International University, Dhaka, 1341, Bangladesh.
Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, 32610, Bandar Seri Iskandar, Perak, Malaysia.
Sci Rep. 2025 Jan 2;15(1):276. doi: 10.1038/s41598-024-84182-w.
This study presents the design and analysis of a compact 28 GHz MIMO antenna for 5G wireless networks, incorporating simulations, measurements, and machine learning (ML) techniques to optimize its performance. With dimensions of 3.19 λ₀ × 3.19 λ₀, the antenna offers a bandwidth of 5.1 GHz, a peak gain of 9.43 dBi, high isolation of 31.37 dB, and an efficiency of 99.6%. Simulations conducted in CST Studio were validated through prototype measurements, showing strong agreement between the measured and simulated results. To further validate the design, an equivalent RLC circuit model was developed and analyzed using ADS, with the reflection coefficient results closely matching those from CST. Additionally, supervised ML techniques were employed to predict the antenna's gain, evaluating nine models using metrics such as R-squared, variance score, mean absolute error, and root mean squared error. Among the models, Random Forest Regression achieved the highest accuracy, delivering approximately 99% reliability in gain prediction. This integration of machine learning with antenna design underscores its potential to optimize performance and enhance design efficiency. With its compact size, high isolation, and exceptional efficiency, the proposed antenna is a promising candidate for 28 GHz 5G applications, offering innovative solutions for next-generation wireless communication.
本研究介绍了一种用于5G无线网络的紧凑型28GHz多输入多输出（MIMO）天线的设计与分析，其中纳入了仿真、测量和机器学习（ML）技术以优化其性能。该天线尺寸为3.19λ₀×3.19λ₀，提供5.1GHz的带宽、9.43dBi的峰值增益、31.37dB的高隔离度以及99.6%的效率。在CST Studio中进行的仿真通过原型测量得到验证，测量结果与仿真结果显示出高度一致性。为进一步验证该设计，使用ADS开发并分析了一个等效RLC电路模型，其反射系数结果与CST的结果紧密匹配。此外，采用监督式ML技术来预测天线增益，使用决定系数、方差得分、平均绝对误差和均方根误差等指标评估了九个模型。在这些模型中，随机森林回归的准确率最高，在增益预测方面的可靠性约为99%。机器学习与天线设计的这种结合突出了其优化性能和提高设计效率的潜力。所提出的天线尺寸紧凑、隔离度高且效率卓越，是28GHz 5G应用的一个有前景的候选方案，为下一代无线通信提供了创新解决方案。
