Machine-Learning-Assisted Antenna Optimization With Data Augmentation

Zhang, Jiapeng; Xu, Jinkai; Chen, Qiang; Li, Hui

doi:10.1109/lawp.2023.3269811

Cited by 7 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm has been successfully demonstrated for the design of circularly polarized antennas, two wideband antennas and an array antenna. Random forest algorithm with data augmentation has been explored in Zhang et al 7 with improved estimation accuracy for the design and optimization of a circularly polarized base station antenna. In Zhang et al, 8 the Multigroup Differential Evolution Optimization Framework has been exploited for the design of multiantenna systems.…”

Section: Introductionmentioning

confidence: 99%

Design and optimization of a Quasi‐Yagi antenna for 5G communications

Ala,

Bactavatchalame,

Karuppiah

2024

Micro & Optical Tech Letters

View full text Add to dashboard Cite

A novel Quasi‐Yagi‐Uda antenna on a flexible material is designed and demonstrated in this paper. The antenna is developed on an ultra‐thin polyimide substrate to support dual‐frequency bands centered at 3.8 and 5.2 GHz for 5G and WiFi‐enabled wireless communications. The proposed Quasi‐Yagi‐Uda has a twin‐F‐shaped driven element which is excited using a microstrip line feed. The arms of the driven element are suitably designed to meet the frequency specifications of the proposed antenna. The design of the antenna is carried out using Computer Simulation Technology Microwave Studio while the antenna optimization is performed using the Fire‐Fly algorithm. The optimum geometrical details of the proposed antenna are obtained with a higher rate of convergence. The proposed dual‐band antenna provides 205 and 195 MHz bandwidth in both frequency bands guaranteeing high‐speed wireless communications in the 5G domain. The Quasi‐Yagi‐Uda provides a gain greater than 4.5 dBi in both operating bands with an efficiency greater than 80%. The prototype antenna optimized using the Fire‐Fly algorithm is fabricated and the simulation results are validated.

show abstract

Section: Introductionmentioning

confidence: 99%

Design and optimization of a Quasi‐Yagi antenna for 5G communications

Ala,

Bactavatchalame,

Karuppiah

2024

Micro & Optical Tech Letters

View full text Add to dashboard Cite

show abstract

Design and optimization of dielectric resonator based MIMO antenna with beam tilting at mm-wave for enhanced 5G communication using machine learning

Pandey,

Sehgal,

Kumar

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

In this paper, a dual-port ceramic-based multipleinput multiple output (MIMO) antenna is designed at mm-wave-frequency. A partially reflecting surface (PRS) is applied over a dual-port antenna to achieve the beam tilting feature. Moreover, various machine learning (ML) algorithms are used to optimize the |S11| parameter of the proposed antenna. Aperture is used to excite the ceramic and produce HEM11δmode in cylindrical dielectric resonator antenna (CDRA). The antenna proposed includes an isolation level greater than 35dB amid ports, approves its working between 25.9-27.4 GHz. PRS tilts the broadsided beam by ±300, which incorporates the pattern diversity concept. These features make the proposed antenna suitable for the mm-wave vehicle-to-vehicle/ 5G communication system.

show abstract

Applications of Machine Learning and Deep Learning in Antenna Design, Optimization, and Selection: A Review

Sarker,

Podder,

Mondal

et al. 2023

IEEE Access

View full text Add to dashboard Cite

This review paper provides an overview of the latest developments in artificial intelligence (AI)-based antenna design and optimization for wireless communications. Machine learning (ML) and deep learning (DL) algorithms are applied to antenna engineering to improve the efficiency of the design and optimization processes. The review discusses the use of electromagnetic (EM) simulators such as computer simulation technology (CST) and high-frequency structure simulator (HFSS) for ML and DL-based antenna design, which also covers reinforcement learning (RL)-bases approaches. Various antenna optimization methods including parallel optimization, single and multi-objective optimization, variable fidelity optimization, multilayer ML-assisted optimization, and surrogate-based optimization are discussed. The review also covers the AI-based antenna selection approaches for wireless applications. To support the automation of antenna engineering, the data generation technique with computational electromagnetics software is described and some useful datasets are reported. The review concludes that ML/DL can enhance antenna behavior prediction, reduce the number of simulations, improve computer efficiency, and speed up the antenna design process.

show abstract

Machine-Learning-Assisted Antenna Optimization With Data Augmentation

Cited by 7 publications

References 19 publications

Design and optimization of a Quasi‐Yagi antenna for 5G communications

Design and optimization of a Quasi‐Yagi antenna for 5G communications

Design and optimization of dielectric resonator based MIMO antenna with beam tilting at mm-wave for enhanced 5G communication using machine learning

Applications of Machine Learning and Deep Learning in Antenna Design, Optimization, and Selection: A Review

Contact Info

Product

Resources

About