| Issue |
EPJ Web Conf.
Volume 309, 2024
EOS Annual Meeting (EOSAM 2024)
|
|
|---|---|---|
| Article Number | 01010 | |
| Number of page(s) | 2 | |
| Section | Topical Meeting (TOM) 1- Silicon Photonics and Integrated Optics | |
| DOI | https://doi.org/10.1051/epjconf/202430901010 | |
| Published online | 31 October 2024 | |
https://doi.org/10.1051/epjconf/202430901010
Single Mode rib waveguide design using Machine Learning techniques
1 Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio 21, 80125 Napoli, Italy
2 Mediterranea University of Reggio Calabria, DIIES Dept., 89124 Reggio Calabria, Italy
3 Institute of Applied Sciences and Intelligent Systems (ISASI-CNR), Via P. Castellino n. 111, 80131 Napoli, Italy
4 Open Fiber S.p.A., Via Laurentina 449, 00142 Roma, Italy
* Corresponding author: Mohamed.Mammri@unina.it
Published online: 31 October 2024
This work aim to determine a Single Mode (SM) Silicon-On-Insulator (SOI) rib waveguide using Machine learning (ML) techniques, which learn automatically by matching the input data with the target property. Random Forest (RF) is the ML algorithm used in this work. The accuracy of the model reaches 99% by using R2 score. The device is a rib waveguide based on Silicon (Si), with a cladding made of Silica (SiO2). The results obtained illustrate the conditions for SM, with the width and the rib etch-depth found to be relatively smaller compared to the total thickness. The ML approach have proven to be quick and effective regarding this problem.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.