Scholarlink

This paper designs and optimizes a dual-band microstrip antenna applicable to 5G communication. After completing the antenna design, the paper presents a method to optimally design the antenna using machine learning techniques. Machine learning can be used to accelerate the antenna design process and identify the optimal parameters. Three algorithms are employed in this study: Decision Tree, K-Nearest Neighbors (KNN), and Neural Networks. Among these algorithms, the KNN model demonstrated the best performance. By utilizing machine learning techniques, traditional electromagnetic simulations can be replaced, allowing for faster simulation results. The final optimized dual-band antenna covers two 5G operating bands: 3.4–3.5 GHz (n77 band) and 4.8–5.0 GHz (n79 band), meeting the requirements for 5G wireless communication.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Design and Optimization of Antennas Based on Machine Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • ShiHao Shao,
  • Xiaoming Li,
  • Haofei Zhang,
  • Xin Yan,
  • Xueguang Yuan,
  • Zhenyu Xiao,
  • Yang’an Zhang

摘要

This paper designs and optimizes a dual-band microstrip antenna applicable to 5G communication. After completing the antenna design, the paper presents a method to optimally design the antenna using machine learning techniques. Machine learning can be used to accelerate the antenna design process and identify the optimal parameters. Three algorithms are employed in this study: Decision Tree, K-Nearest Neighbors (KNN), and Neural Networks. Among these algorithms, the KNN model demonstrated the best performance. By utilizing machine learning techniques, traditional electromagnetic simulations can be replaced, allowing for faster simulation results. The final optimized dual-band antenna covers two 5G operating bands: 3.4–3.5 GHz (n77 band) and 4.8–5.0 GHz (n79 band), meeting the requirements for 5G wireless communication.