The design and analysis of microstrip patch antennas are crucial for microwave applications, such as communication systems, radar, and imaging devices. However, the complex interactions between the antenna's geometrical parameters, material properties, and performance characteristics make the design process computationally expensive and time-consuming. This paper presents a comprehensive study on data-driven surrogate modeling techniques for efficient design and optimization of microstrip patch antennas. We discuss various surrogate modeling techniques, such as support vector regression machine, Gaussian process models, artificial neural networks, and deep learning-based approaches, and evaluate their performance in predicting the antenna's performance metrics. Additionally, we demonstrate the application of surrogate modeling in the optimization of microstrip patch antennas and address the challenges and future research directions in this field.
Primary Language | English |
---|---|
Subjects | Artificial Intelligence |
Journal Section | Research Articles |
Authors | |
Publication Date | June 30, 2023 |
Submission Date | April 30, 2023 |
Published in Issue | Year 2023 Volume: 3 Issue: 1 |
All articles published by JAIDA are licensed under a Creative Commons Attribution 4.0 International License.