"

Cookies ussage consent

Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.

I agree, do not show this message again.

Machine learning based algorithm for multi-FBG peak detection using generative adversarial network

SUNIL KUMAR1,* , SOMNATH SENGUPTA1,*

Affiliation

  1. Department of Electronics and Communication Engineering, Birla Institute of Technology, Mesra, Ranchi, Jharkhand, India

Abstract

It is suggested to use a machine learning approach based on generative adversarial networks to detect the peak wavelengths of several Fiber Bragg Gratings (FBGs). A generative model and a discriminative model make up the algorithm. The discriminative model predicts the real FBG signal by the computation of the loss functions, whereas the generative model creates a synthetic signal and is sampled for training using a deep neural network. Separate calculations are made for the loss functions of the generating and discriminative signals after training. The discriminative signal's loss function maximum and generative signal's loss function minimum are matched, and the resulting peak wavelength which is the required peak wavelength of FBG is found. Simulink in MATLAB is used to experimentally validate the suggested approach..

Keywords

Fiber bragg grating, Generative model, Discriminative model and loss function.

Submitted at: Sept. 7, 2022
Accepted at: June 9, 2023

Citation

SUNIL KUMAR, SOMNATH SENGUPTA, Machine learning based algorithm for multi-FBG peak detection using generative adversarial network, Journal of Optoelectronics and Advanced Materials Vol. 25, Iss. 5-6, pp. 273-281 (2023)