Optical Machine Learning for Communication and Networking

A special issue of Photonics (ISSN 2304-6732). This special issue belongs to the section "Optical Communication and Network".

Deadline for manuscript submissions: closed (30 November 2022) | Viewed by 8176

Special Issue Editors


E-Mail Website
Guest Editor
Shandong Key Laboratory of Optical Communication Science and Technology, School of Physics Science and Information Technology, Liaocheng University, Liaocheng, China
Interests: optical fiber sensors; terahertz sensing and spectroscopy; optical networks and systems; bio-photonics; terahertz and infrared spectroscopy; biophysics; nanotechnolgy & nanoscience; integrated photonics; nonlinear optics; distributed optical sensing
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Computing and Mathematics, Manchester Metropolitan University, Manchester M15 6BH, UK
Interests: Internet of Things; network security; cloud computing; network function virtualization; wireless networks; 5G
Special Issues, Collections and Topics in MDPI journals
Adani Institute of Infrastructure Engineering, Ahmedabad, India
Interests: radio over fiber; power over fiber; photonic crystal fiber; multicore fiber; free-space optical communication; nonlinear distortion; THz; optical sensor; optical devices; OCT; optical imaging; machine learning based photonics system

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) has disrupted a comprehensive range of engineering and technologies segments. machine learning-based optical systems are also gaining more research attention, particularly in optoelectronics devices, communications, networking, nonlinear transmission systems, optical performance monitoring, and cross-layer network optimizations for photonics networks.

Optical machine learning (OML) can be employed to explore the challenges in the domain of optical fiber communications, namely: optical devices, optical waveguides, photonic crystal fiber, multicore fiber, radio over fiber, power over fiber, WDM, DWDM, and OFDM networks, such as nonlinear mitigation, characterization, performance optimization, testing, planning, fault prevention, network maintenance, quality of transmission (QoT), equipment realization performance prediction, network resources allocation and management. OML can also facilitate optimization in future photonics networks used for big data analytics. It can integrally acquire and reveal hidden patterns and correlations in big data, which can be extremely valuable for unraveling complex optical network optimization issues. OML-driven, next-generation optical networks can offer set-ups for monitoring themselves, analyzing and resolving their problems, and can provide intelligent and efficient services with minimal failure. The greatest challenge of optical communication is nonlinear distortions, which can be predicted and optimized using different, optical, machine learning-based algorithms. OML provides nonlinear mitigation, phase noise mitigation, signal recovery, pattern quantization, channel monitoring, channel estimation, performance enhancements for FSO (free-space optical communication), and guided systems. In the case of free-space optical communication, the greatest hurdle is atmospheric turbulence, which predicated and optimized using the deep learning algorithm. Machine learning techniques can conduct impairments monitoring in optical links without adaptive optics and other signal processing algorithms. Convolution neural networks (CNN) recognize orbital angular momentum (OAM) modes in turbulent FSO links, and support vector machines (SVM); ?-nearest neighbor (KNN)-based methods are also helpful for predicting noise in the channel. Optical machine learning (OML) techniques are implemented to compute PCF optical properties, nanophotonics structures, laser beam alignment, adaptive linear optic devices, ultrafast photonics, and medical application-based photonics devices.

This Special Issue will summarize the state-of-the-art methods so that researchers can validate ML practices for use as a distinctive and effective set of signal processing tools in optic communication systems. It aims to resolve critical issues that cannot be easily explored using conventional approaches. Furthermore, 5G networks will require a more dynamic and optimized network through increasing the implementation of AI and big data in future networks. Thus, such compressive material will become necessary and beneficial for optical communications and networking researchers.

Potential points incorporate yet are not restricted to the accompanying:

  • Intelligence optical systems;
  • Characterization of optical networks using AI/ML;
  • Transmission estimation in an optical networks using ML;
  • AI and on-board AI in optical networks;
  • OML-based failure management in optical networks;
  • Future intelligent elastic optical networks;
  • OML for routing and resource allocation in optical networks;
  • Mitigating nonlinearity issues in optical networks using AI;
  • Traffic prediction using OML;
  • Optimized photonics-based system;
  • OML for free-space optical communication;
  • Characterization of optoelectronic materials using ML;
  • Nanophotonic devices using machine learning;
  • Advancing optical communication systems using OML;
  • Optical sensor characterization using OML;
  • Multi dimension photonic crystal fiber using AI;
  • Machine learning-based optical systems for medical applications;
  • OML-based photonics devices.

Dr. Santosh Kumar
Dr. Ali Kashif Bashir
Dr. Ajay Kumar Vyas
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Photonics is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • optical machine learning
  • networking
  • intelligence network
  • AI
  • ML
  • optical communication
  • elastic optical networks
  • photonics devices
  • nonlinearity

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

11 pages, 586 KiB  
Communication
Photonic Crystal-Based Water Concentration Estimation in Blood Using Machine Learning for Identification of the Haematological Disorder
by Ankit Agarwal, Nitesh Mudgal, Kamal Kishor Choure, Rahul Pandey, Ghanshyam Singh and Satish Kumar Bhatnagar
Photonics 2023, 10(1), 71; https://doi.org/10.3390/photonics10010071 - 9 Jan 2023
Cited by 3 | Viewed by 1876
Abstract
Human blood is made up primarily of water. Water is significantly involved in balancing the human body. It affects the component of blood like mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin concentration (MCHC), and mean platelets volume (MPV). The water concentration varies from [...] Read more.
Human blood is made up primarily of water. Water is significantly involved in balancing the human body. It affects the component of blood like mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin concentration (MCHC), and mean platelets volume (MPV). The water concentration varies from 80 to 90% in blood. The change in water concentration changes the refractive index of plasma, and the change in the refractive index of plasma also changes the refractive index of blood. The proposed structure is designed to analyze the water concentration in human blood by analyzing the shifting in resonant peak and this shifting is processed by machine learning algorithm to estimate the concentration of water in human blood. Nanocavity ring structures in the waveguide region are designed as sensing nodes in this proposed structure. The air hole radius of these Nanocavity ring structures is 80 and 50 nm, whereas the proposed structure’s dimension is 12.15 by 8.45 μm2. The sensitivity of the design structure is 570 nm/RIU, and the quality factor is 650. The structure is simulated through the Finite Difference Time Domain (FDTD) method. Full article
(This article belongs to the Special Issue Optical Machine Learning for Communication and Networking)
Show Figures

Figure 1

17 pages, 5829 KiB  
Article
LSTM-Based DWBA Prediction for Tactile Applications in Optical Access Network
by Elaiyasuriyan Ganesan, Andrew Tanny Liem, I-Shyan Hwang, Mohammad Syuhaimi Ab-Rahman, Semmy Wellem Taju and Mohammad Nowsin Amin Sheikh
Photonics 2023, 10(1), 37; https://doi.org/10.3390/photonics10010037 - 29 Dec 2022
Cited by 2 | Viewed by 1654
Abstract
Historically, the optical access network (OAN) plays a crucial role of supporting emerging new services such as 4 k, 8 k multimedia streaming, telesurgery, augmented reality (AR), and virtual reality (VR) applications in the context of Tactile Internet (TI). In order to prevent [...] Read more.
Historically, the optical access network (OAN) plays a crucial role of supporting emerging new services such as 4 k, 8 k multimedia streaming, telesurgery, augmented reality (AR), and virtual reality (VR) applications in the context of Tactile Internet (TI). In order to prevent losing connectivity to the current mobile network and Tactile Internet, the OAN must expand capacity and improve the quality of Services (QoS) mainly for the low latency of 1 ms. The optical network has adopted artificial intelligence (AI) technology, such as deep learning (DL), in order to classify and predict complex data. This trend mainly focuses on bandwidth prediction. The software-defined network (SDN) and cloud technologies provide all the essential capabilities for deploying deep learning to enhance the performance of next-generation ethernet passive optical networks (NG-EPONs). Therefore, in this paper, we propose a deep learning long-short-term-memory model-based predictive dynamic wavelength bandwidth allocation (DWBA) mechanism, termed LSTM-DWBA in NG-EPON. Future bandwidth for the end-user is predicted based on NG-EPON MPCP control messages exchanged between the OLT and ONUs and cycle times. This proposed LSTM-DWBA addresses the uplink control message overhead and QoS bottleneck of such networks. Finally, the extensive simulation results show the packet delay, jitter, packet drop, and utilization. Full article
(This article belongs to the Special Issue Optical Machine Learning for Communication and Networking)
Show Figures

Figure 1

18 pages, 6578 KiB  
Article
Investigation of Machine Learning Methods for Prediction of Measured Values of Atmospheric Channel for Hybrid FSO/RF System
by Maroš Lapčák, Ľuboš Ovseník, Jakub Oravec and Norbert Zdravecký
Photonics 2022, 9(8), 524; https://doi.org/10.3390/photonics9080524 - 28 Jul 2022
Viewed by 1497
Abstract
This research paper addresses the problems of fiberless optical communication, known as free space optics, in predicting RSSI (Received Signal Strength Indicator) parameters necessary for hard switching in a hybrid FSO/RF (Free Space Optics/Radio Frequency) system. This parameter is used to determine the [...] Read more.
This research paper addresses the problems of fiberless optical communication, known as free space optics, in predicting RSSI (Received Signal Strength Indicator) parameters necessary for hard switching in a hybrid FSO/RF (Free Space Optics/Radio Frequency) system. This parameter is used to determine the intensity of the transmitted signal (in our case, a light beam) from one FSO head to another. Since we want to achieve almost 100% reliability, it is important to know the parameters of the transmission environment for the FSO and RF lines. Each of them has its limitations and, as a result, a weather monitoring station is required. The FSO is mostly affected by fog and the concentration of particles in the air, while the RF line is affected by rain and snow. It is precisely due to these influences that it is necessary (based on the mentioned RSSI parameter) to switch using the hard switching method from the primary FSO line to the backup RF line by correctly predicting this value. If the value of the RSSI parameter falls below the critical level—42 dBm—the system automatically switches to the backup RF line. There are several ways we can predict this parameter. One of them is machine learning methods such as decision trees. Our research focused on the prediction of the RSSI parameter, the methods of decision trees and decision trees using the AdaBoost regressor. Since we want to correctly predict the RSSI parameter, it is also necessary to choose the right way to predict it based on the recorded weather conditions. If we want to correctly use the hard switching method in hybrid FSO/RF systems, it is necessary to choose the correct method of predicting the RSSI parameter, which serves as an indicator for switching from the primary FSO line to the secondary RF line. Therefore, we decided to investigate methods of machine learning—the decision tree and the decision tree with the use of an AdaBoost Regressor. The main benefit of this paper is the improvement of existing machine learning methods (decision trees and decision trees using the AdaBoost regressor) for the correct prediction of the RSSI parameter for the needs of hard switching in a hybrid FSO/RF system. The method chosen in this manuscript has very good results. As can be seen in the attached graphs, over a longer period and using correctly selected training data, it is possible to achieve ideal results for the prediction of the RSSI parameter. The tables also show the effectiveness of the prediction, and the fact that it is best to train on either the first- or third-minute data. In the future, it would be appropriate to implement weather prediction or to consider other methods, such as random forests or neural networks. Full article
(This article belongs to the Special Issue Optical Machine Learning for Communication and Networking)
Show Figures

Figure 1

13 pages, 5062 KiB  
Article
Inverse Design for Coating Parameters in Nano-Film Growth Based on Deep Learning Neural Network and Particle Swarm Optimization Algorithm
by Xiaohan Guo, Jinsu Lu, Yu Li, Jianhong Li and Weiping Huang
Photonics 2022, 9(8), 513; https://doi.org/10.3390/photonics9080513 - 23 Jul 2022
Cited by 1 | Viewed by 1551
Abstract
The NN (neural network)-PSO (particle swarm optimization) method is demonstrated to be able to inversely extract the coating parameters for the multilayer nano-films through a simulation case and two experimental cases to verify its accuracy and robustness. In the simulation case, the relative [...] Read more.
The NN (neural network)-PSO (particle swarm optimization) method is demonstrated to be able to inversely extract the coating parameters for the multilayer nano-films through a simulation case and two experimental cases to verify its accuracy and robustness. In the simulation case, the relative error (RE) between the average layer values and the original one was less than 3.45% for 50 inverse designs. In the experimental anti-reflection (AR) coating case, the mean thickness values of the inverse design results had a RE of around 5.05%, and in the Bragg reflector case, the RE was less than 1.03% for the repeated inverse simulations. The method can also be used to solve the single-solution problem of a tandem neural network in the inverse process. Full article
(This article belongs to the Special Issue Optical Machine Learning for Communication and Networking)
Show Figures

Figure 1

Back to TopTop