Deep learning-based image transmission through a multi-modefiber

Kürekçi, Şahin
Odabaş, Ekrem
Temur, Tarık
Afshari, Gilda
Yüce, Emre
Image transmission through a multi-mode fiber is a difficult task given the complex interference of light through the fiber that leads to random speckle patterns at the distal end of the fiber. With traditional methods and techniques, it is impractical to reconstruct a high-resolution input image by using the information obtained from the intensity of the corresponding output speckle alone. In this work, we train three Convolutional Neural Networks (CNNs) with input-output couples of a multi-mode fiber and test the learning with images outside the learning set. The three implemented deep learning models have modern UNet, ResNet and VGGNet architectures and are trained with 31,200 grey-scale handwritten letters of the Latin alphabet. After the training, 5,200 images outside the learning set are used for testing and it was shown that the models successfully reconstruct the input images from the output random speckle patterns with average fidelities ranging from 81% to 90%. Our results show the superiority of the ResNet based architecture over UNet and VGGNet in reconstruction accuracy, achieving up to 97% fidelity in a short amount of time. This can be attributed to the success of the ResNet architecture in learning non-linear systems compared to its counterparts. We believe that the implementation of machine learning techniques to imaging, along with its contributions to biophysics, can reshape the telecommunication industry and thus will be a cornerstone in future optics and photonics studies.
Proceedings of the SPIE : Unconventional Optical Imaging II (2020)


User association and routing in UAV-supported HetNets
Tezergil, Berke; Onur, Ertan; Department of Computer Engineering (2022-1-24)
With the introduction of millimeter waves in 5G, using wireless backhaul has become feasible with higher performance comparable to that of fiber cables. Using unmanned aerial vehicles as small cells enabled many use-cases by reducing the average link length and increasing the line-of-sight probability. In this work, a heterogeneous network with users, flying small cells on unmanned aerial vehicles, and macro base stations are considered. We introduce two main problems: establishing backhaul routes for small...
Deep Learning-Based Hybrid Approach for Phase Retrieval
IŞIL, ÇAĞATAY; Öktem, Sevinç Figen; KOÇ, AYKUT (2019-06-24)
We develop a phase retrieval algorithm that utilizes the hybrid-input-output (HIO) algorithm with a deep neural network (DNN). The DNN architecture, which is trained to remove the artifacts of HIO, is used iteratively with HIO to improve the reconstructions. The results demonstrate the effectiveness of the approach with little additional cost.
Asymptotic solution of the radial wave equation for optical fiber wavequides
Cildlr, Sema; Çakır, Serhat (2006-08-26)
In this study, analytic solutions were studied for propagation of electromagnetic waves in cylindrical fiber optic cable. An asymptotic approach was used to solve radial wave equation The solution was derived for zero order eigenvalue equation. It was found that this solution is more general than other methods. By using a computer program was obtained some diagrams for core and cladding region for different eigenvalue equations and modes.
Online Antenna Tuning in Heterogeneous Cellular Networks With Deep Reinforcement Learning
Balevi, Eren; Andrews, Jeffrey G. (2019-12-01)
We aim to jointly optimize antenna tilt angle, and vertical and horizontal half-power beamwidths of the macrocells in a heterogeneous cellular network (HetNet). The interactions between the cells, most notably due to their coupled interference render this optimization prohibitively complex. Utilizing a single agent reinforcement learning (RL) algorithm for this optimization becomes quite suboptimum despite its scalability, whereas multi-agent RL algorithms yield better solutions at the expense of scalabilit...
Fiber loop ring down spectrometer optical based sensor for trace chemical detection
Yolalmaz, Alim; Esentürk, Okan; Danışman, Mehmet Fatih; Hanifehpour, Farhad (2016-04-11)
Fiber loop ring down (FLRD) is a time domain multi-functional sensing, characterization, detection technique. FLRD technique is used to sense temperature, pressure, strain, biological cells, refractive index, and chemical species. FLRD has high accuracy, high selectivity, ability of remote control and rapid response. In this project, two FLRD spectrometers working at 800 nm (figure 1) and 1535 nm (figure 2) were set up for sensing different chemical analytes like C2H2, CO2, Ar, N2, DMSO, DMF, H2O, C2H6O, C3...
Citation Formats
Ş. Kürekçi, E. Odabaş, T. Temur, G. Afshari, and E. Yüce, “Deep learning-based image transmission through a multi-modefiber,” Online Only, 2020, vol. 1135126, Accessed: 00, 2021. [Online]. Available: