Article Per Year (5 Year)
p-Index From 2021 - 2026
0
P-Index
This Author published in this journals
All Journal International Journal of Intelligent Systems and Applications in Engineering
Özkan-Bakbak, Pınar
Advanced Technology and Science (ATScience)
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Particle Swarm Optimization Design of Optical Directional Coupler Based on Power Loss Analysis Özkan-Bakbak, Pınar
International Journal of Intelligent Systems and Applications in Engineering Vol 1, No 2 (2013)
Publisher : Advanced Technology and Science (ATScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In this work, feasible design is presented as an optimization problem for an optical directional coupler and designed by using particle swarm optimization (PSO). Principally, identical, weakly guiding, slab and lossless optical waveguides are supposed to be weakly coupled to each other. The power loss and the propagation constant change of TE and TM modes in mutual coupling of two cladded and uncladded optical waveguides are analyzed by the modal analysis and PSO. PSO design of an optical directional coupler is an optimization problem consisting of input variables and design parameters within a fitness function (FF). FF is the power loss of TE and TM modes. PSO should minimize the FF and obtain design criteria. The analysis shows that the results, by using PSO are compatible with modal analysis results. The availability of the optical coupler design by PSO has been tested successfully.
Neural Boundary Conditions in Optic Guides Özkan-Bakbak, Pınar
International Journal of Intelligent Systems and Applications in Engineering Vol 3, No 3 (2015)
Publisher : Advanced Technology and Science (ATScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18201/ijisae.04354

Abstract

In this study, the boundary coefficients of Transverse Electric (TE) and Transverse Magnetic (TM) modes at a planar slab optic guides are modeled by Neural Networks (NN). After modal analysis, train and test files are prepared for NN. Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) neural networks are performed and compared with each other. NNs are expected to be capable of modeling optical fiber technology in industry based on the same approaches as a result of this study.
Co-Authors