@inproceedings{2f64c4c0fbc84253830f6f3042a710f7,
title = "Resonant Mode Recognition with Convolutional Neural Network",
abstract = "This research proposes a simple approach to recognize resonate modes in rectangular dielectric resonator antennas (DRAs) with machine learning (ML) techniques. The proposed method utilizes a convolutional neural network (CNN) with a focal loss function to classify various modes present in the antenna. DRAs with different dimensions are simulated with ANSYS HFSS to obtain their electric fields at various resonant frequencies. The resulting dataset comprises 700 fields, manually labeled according to their corresponding resonant modes. After training the CNN model using this dataset, it is capable of accurately classifying 12 low-order resonant modes in rectangular DRAs. The performance of the model is evaluated using a test set, where it achieves a recognition accuracy of 97.8\%. {\textcopyright} 2023 IEEE.",
keywords = "Artificial intelligence, convolutional neural network, dielectric resonator antenna, imbalanced dataset, machine learning, resonant mode",
author = "Yuqi Xiao and Kai Lu and Leung, \{Kwok Wa\} and Chi-Sing Leung",
year = "2023",
doi = "10.1109/ICMMT58241.2023.10276637",
language = "English",
isbn = "9798350338881",
series = "International Conference on Microwave and Millimeter Wave Technology, ICMMT - Proceedings",
publisher = "IEEE",
booktitle = "2023 International Conference on Microwave and Millimeter Wave Technology (ICMMT 2023) - Proceedings",
address = "United States",
note = "15th International Conference on Microwave and Millimeter Wave Technology (ICMMT 2023) ; Conference date: 14-05-2023 Through 17-05-2023",
}