Accurate radial basis function based neural network approach for analysis of photonic crystal fibers

Abstract

In this paper, a new and an accurate artificial neural network approach (ANN) is presented for the analysis and design of photonic crystal fibers (PCFs). The new ANN approach is based on the radial basis functions which offer a very quick convergence and high efficiency during the ANN learning. The accuracy of the suggested approach is demonstrated via the excellent agreement between the results obtained using the presented approach and the results of the full vectorial finite difference method (FVFDM). In addition, a new design of highly birefringence PCF with low losses for the two polarized modes is presented using the proposed approach.

Machine learning methods for estimating bent photonic crystal fiber based SPR sensor properties

“…In the recent years, optimizing and refinement of microstructured optical devices with considerable low computational time is becoming crucial. For this purpose, genetic algorithms, artificial neural networks (ANN), and various other machine learning (ML) algorithms [1] , [2] , [3] , [4] , [5] , [6] , [7] , [8] were employed in the past. In this study, ML approaches are proposed to estimate the bending loss characteristics of a PCF based SPR structure.…”

“…In this study, ML approaches are proposed to estimate the bending loss characteristics of a PCF based SPR structure. The comparisons are performed between two conventional techniques, namely, Linear Least Squares Regression (LLSR) [9] , k-Nearest Neighbor Regression (KNNR); and a commonly used Artificial Neural Networks (ANN) technique that has been used in multiple similar studies [2] , [3] , [4] , [5] . A feature space expansion method is also employed to improve the scores of LLSR and ANN systems.…”

“…KNNR is a non-linear regression system that can estimate the result of a system effectively. In the past, conventional ANN [2] , [3] , [4] , [8] and generative adversarial network (GAN) [5] models have been employed for PCF based structures. These methods need substantial training time.…”

Artificial Neural Networks for the Chromatic Dispersion Prediction of Photonic Crystal Fibers

“…On the other hand, ANNs have been used in photonics for the modeling of planar waveguides based couplers and optical fiber based couplers and also for the analysis of PCFs and patch antennas . The main advantages of an ANN based models are their simplicity, the reduced time, and computational effort and also its application for synthesis problems.…”

Efficient Neural Network Modeling of Photonic Crystal Fiber Chromatic Dispersion

“…On the other hand, neural networks have been used in photonics for the modeling of planar couplers [6] and optical fiber couplers [6,7] and photonic crystal fibers [8]. The main advantages of a neural network based models are their simplicity, the reduced time and computational effort and also their application for synthesis problems.…”