Volume 23, Issue 2 (JIAEEE Vol.23 No.2 2026)
Journal of Iranian Association of Electrical and Electronics Engineers 2026, 23(2): 31-37 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Mazroei Abkenar A, Maddah Ali M, Nasirian M. Implementation of Resent-101 neural network and particle swarm optimization algorithm in modeling frequency Selective surfaces with Complex Shapes of type Sierpiński-Gasket. Journal of Iranian Association of Electrical and Electronics Engineers 2026; 23 (2) :31-37
URL: http://jiaeee.com/article-1-1788-en.html
URL: http://jiaeee.com/article-1-1788-en.html
Department of Electrical and Electromagnetic Engineering, Malek Ashtar University of Technology
Abstract: (77 Views)
Modeling fractal frequency selective surfaces (FSS) is one of the primary challenges in designing absorbers and electromagnetic structures based on such surfaces, primarily due to their geometric complexity and the demand for precise simulations, which require significant time and resources. In this project, the main objective is to utilize the ResNet convolutional neural network to predict the reflection coefficient of fractal surfaces based on their images. A notable feature of this study is the incorporation of data extracted from the particle swarm optimization (PSO) algorithm alongside random data for training the network. This approach has not only enhanced the prediction accuracy of the neural network but also improved the quality of the generated dataset. Furthermore, the integration of the PSO algorithm with the ResNet network has resulted in improved model performance in terms of more accurate and faster reflection coefficient predictions. The proposed methodology has the potential to significantly reduce the time and costs associated with modeling fractal frequency selective surfaces, ultimately facilitating the optimization of their design process.
Keywords: Neural network, ResNet neural network, fractal frequency selective surfaces, convolutional neural network, particle swarm optimization algorithm
Type of Article: Research |
Subject:
Communication
Received: 2025/01/12 | Accepted: 2025/12/6 | Published: 2026/06/22
Received: 2025/01/12 | Accepted: 2025/12/6 | Published: 2026/06/22
Send email to the article author
| Rights and permissions | |
 |
This Journal is an open access Journal Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. (CC BY NC 4.0) |
