[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.4
2.7
Journals
JMSE
Special Issues
Maritime Communication Networks and 6G Technologies
share announcement

Maritime Communication Networks and 6G Technologies

A special issue of Journal of Marine Science and Engineering (ISSN 2077-1312).

Deadline for manuscript submissions: 20 March 2025 | Viewed by 1820

Special Issue Editors

Dr. Anastasios E. Giannopoulos

E-Mail Website
Guest Editor
Department of Ports Management and Shipping, National and Kapodistrian University of Athens, Athens, Greece
Interests: resource management; wireless network optimization; machine learning; maritime communications; multi-dimensional analysis
Dr. Nikolaos Nomikos

E-Mail Website
Guest Editor
Department of Ports Management and Shipping, National and Kapodistrian University of Athens, Athens, Greece
Interests: cooperative communications; maritime communication networks; low-latency communications and machine learning for wireless network optimization
Special Issues, Collections and Topics in MDPI journals
Dr. Panagiotis Trakadas

E-Mail Website
Guest Editor
Department of Ports Management and Shipping, National and Kapodistrian University of Athens, Athens, Greece
Interests: 5G technologies; wireless sensor networks; maritime communications; signal processing and routing protocols
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

This Special Issue aims to explore the advancements and future directions in maritime communication networks and the integration of 6G technologies. Our focus is on innovative solutions that enhance connectivity, data transmission, and operational efficiency in maritime environments. Topics include but are not limited to 6G-enabled communication protocols, IoT applications, cybersecurity, predictive maintenance, machine learning, and satellite communications.

This issue can fill a gap in the existing literature by providing a comprehensive overview of the latest research and developments in this rapidly evolving field. By situating the discussion within the context of current technological trends and maritime needs, this Special Issue can serve as a valuable resource for researchers, practitioners, and policymakers interested in the future of maritime communications.

We invite contributions that offer new insights, propose novel methodologies, and present case studies demonstrating the practical applications of 6G technologies in maritime contexts.

Dr. Anastasios E. Giannopoulos
Dr. Nikolaos Nomikos
Dr. Panagiotis Trakadas
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. Journal of Marine Science and Engineering 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 2600 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

  • maritime communication networks (MCNs)
  • machine learning and MCNs
  • 6G technologies in MCNs
  • multi-hop relaying techniques for MCNs
  • measurements and channel modeling for MCNs
  • radio resource management algorithms for MCNs

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

16 pages, 3733 KiB  
Article
Research on Rapid Detection of Underwater Targets Based on Global Differential Model Compression
by Weishan Li, Yilin Li, Ruixue Li, Haozhe Shen, Wenjun Li and Keqiang Yue
J. Mar. Sci. Eng. 2024, 12(10), 1760; https://doi.org/10.3390/jmse12101760 - 4 Oct 2024
Viewed by 895
Abstract
Large-scale deep learning algorithms have emerged as the primary technology for underwater target detection, demonstrating exceptional inference effectiveness and accuracy. However, the real-time capabilities of these high-accuracy algorithms rely heavily on high-performance computing resources like CPUs and GPUs. It presents a challenge for [...] Read more.
Large-scale deep learning algorithms have emerged as the primary technology for underwater target detection, demonstrating exceptional inference effectiveness and accuracy. However, the real-time capabilities of these high-accuracy algorithms rely heavily on high-performance computing resources like CPUs and GPUs. It presents a challenge for deploying them on underwater embedded devices, where communication is limited and computational and energy resources are constrained. To overcome this, this paper focuses on constructing a lightweight yet highly accurate deep learning model suitable for real-time underwater target detection on edge devices. We develop a new lightweight model, named YOLO-TN, for real-time underwater object recognition on edge devices using a self-constructed image dataset captured by an underwater unmanned vehicle. This model is obtained by compressing the classical YOLO-V5, utilizing a globally differentiable deep neural architecture search method and a network pruning technique. Experimental results show that the YOLO-TN achieves a mean average precision (mAP) of 0.5425 and an inference speed of 28.6 FPS on embedded devices, while its parameter size is between 0.4 M and 0.6 M. This performance is a fifth of the parameter size and twelve times the FPS of the YOLO-V5 model, with almost no loss in inference accuracy. In conclusion, this framework significantly enhances the feasibility of deploying large-scale deep learning models on edge devices with high precision and compactness, ensuring real-time inference and offline deployment capabilities. This research is pivotal in addressing the computational challenges faced in underwater operations. Full article
(This article belongs to the Special Issue Maritime Communication Networks and 6G Technologies)
►▼ Show Figures

Figure 1

Figure 1
<p>This approach uses YOLO-V5 as a teacher network while building a student network whose architecture needs to be searched within the search space. Finally, the student network obtained by the search is pruned to obtain the lightweight YOLO-TN.</p> Full article ">Figure 2
<p>Schematic diagram of the search network structure. This network framework uses three normal convolutional layers and two basic computing units to achieve 32× downsampling while setting up Reduce computing units at a 1/3 and 2/3 depth of the network, stacked as the backbone network.</p> Full article ">Figure 3
<p>Each computational unit is primarily composed of five nodes, and the output is the cascaded output of all intermediate nodes within the computational unit. The first and second input nodes of the <span class="html-italic">i</span>-th computational unit are set as the outputs of the (<span class="html-italic">i</span> − 2)-th and (<span class="html-italic">i</span> − 1)-th computational units, respectively, and a 1 × 1 convolution may be inserted as needed. The first intermediate node is obtained by linearly transforming the two input nodes, adding their results, and then applying the tanh activation function. Other configurations are similar to ENAS’s cell, enabling batch normalization in each node to prevent gradient explosions during architecture search.</p> Full article ">Figure 4
<p>Structure of the lightweight YOLO-TN model. The new architecture employs depthwise separable convolution, which divides a standard convolution into depthwise convolution and pointwise convolution, leading to a reduction in the number of parameters and computational workload.</p> Full article ">Figure 5
<p>Model performance comparison with different pruning strategies and rates. (<b>a</b>) is the comparison of the performance in terms of mAP@0.5, (<b>b</b>) is the comparison of FLOPs performance, (<b>c</b>) is the comparison of the FPS performance on the CPU, and (<b>d</b>) is the comparison of the FPS performance on the GPU.</p> Full article ">Figure 6
<p>Training mAP and loss curves of YOLO-TN and YOLO-V5s using the fish–trash dataset. (<b>a</b>) is the mAP@0.5 iteration curve, (<b>b</b>) is the mAP@0.5:0.95 iteration curve, (<b>c</b>) is the box loss convergence curve, (<b>d</b>) is the object loss convergence curve. It is evident that the model converges at epoch 175.</p> Full article ">Figure 7
<p>Model performance comparison with different pruning strategies and rates. (<b>a</b>) is the device used for shooting. (<b>b</b>) is a field photo of Qiandao Lake. (<b>c</b>) is a field photo of a park. (<b>d</b>) is the sum of the collected data. (<b>e</b>,<b>f</b>) are the two simple images in the dataset.</p> Full article ">Figure 8
<p>Dark channel dehazing algorithm processing blurred image and automatic color equalization algorithm processing underwater deep color distortion image. (<b>a</b>,<b>b</b>) are the two simple images in the dataset. (<b>c</b>) is the image in (<b>a</b>) processed by the dark channel defogging algorithm. (<b>d</b>) is the image in (<b>b</b>) processed by the underwater color restoration algorithm and the automatic color balance algorithm.</p> Full article ">Figure 9
<p>Training mAP and loss curves of YOLO-TN and YOLO-V5s using real underwater dataset. (<b>a</b>) is the mAP@0.5 iteration curve, (<b>b</b>) is the mAP@0.5:0.95 iteration curve, (<b>c</b>) is the box loss convergence curve, (<b>d</b>) is the object loss convergence curve. It is evident that the model converges at epoch 175.</p> Full article ">Figure 10
<p>Results of YOLO-V5, unpruned YOLO-TN, and YOLO-TN with different input sizes in underwater target recognition. The new architecture employs depthwise separable convolution, which divides a standard convolution into depthwise convolution and pointwise convolution, leading to a reduction in the number of parameters and computational workload.</p> Full article ">

Review

Jump to: Research

21 pages, 1364 KiB  
Review
Towards Predictive Maintenance in the Maritime Industry: A Component-Based Overview
by Alexandros S. Kalafatelis, Nikolaos Nomikos, Anastasios Giannopoulos, Georgios Alexandridis, Aikaterini Karditsa and Panagiotis Trakadas
J. Mar. Sci. Eng. 2025, 13(3), 425; https://doi.org/10.3390/jmse13030425 - 25 Feb 2025
Viewed by 146
Abstract
The maritime industry has a significant influence on the global economy, underscoring the need for operational availability and safety through effective maintenance practices. Predictive maintenance emerges as a promising solution compared to conventional maintenance schemes currently employed by the industry, offering proactive failure [...] Read more.
The maritime industry has a significant influence on the global economy, underscoring the need for operational availability and safety through effective maintenance practices. Predictive maintenance emerges as a promising solution compared to conventional maintenance schemes currently employed by the industry, offering proactive failure predictions, reduced downtime events, and extended machinery lifespan. This paper addresses a critical gap in the existing literature by providing a comprehensive overview of the main data-driven PdM systems. Specifically, the review explores common issues found in vessel components (i.e., propulsion, auxiliary, electric, hull), examining how different state-of-the-art PdM architectures, ranging from basic machine learning models to advanced deep learning techniques aim to address them. Additionally, the concepts of centralized machine learning, federated, and transfer learning are also discussed, demonstrating their potential to enhance PdM systems as well as their limitations. Finally, the current challenges hindering adoption are discussed, together with the future directions to advance implementation in the field. Full article
(This article belongs to the Special Issue Maritime Communication Networks and 6G Technologies)
►▼ Show Figures

Figure 1

Figure 1
<p>Review structure.</p> Full article ">Figure 2
<p>Comparison of ML training schemes: (<b>A</b>) CML, (<b>B</b>) FL, and (<b>C</b>) TL.</p> Full article ">Figure 3
<p>Distinction between RUL, TTF, and TTR.</p> Full article ">Figure 4
<p>Key factors contributing to propulsion system failures.</p> Full article ">Figure 5
<p>Hybrid propulsion architectural configurations: (<b>A</b>) serial hybrid system, (<b>B</b>) serial–parallel hybrid system, and (<b>C</b>) parallel hybrid system [<a href="#B40-jmse-13-00425" class="html-bibr">40</a>].</p> Full article ">Figure 6
<p>Comparison of traditional and electric power system configurations. (<b>A</b>) Internal Combustion Engine (ICE), (<b>B</b>) Lithium–Nickel–Manganese–Cobalt–Oxide (NMC) batteries, (<b>C</b>) Lithium–Iron–Phosphate (LFP) batteries, (<b>D</b>) Lithium–Titanium–Oxide (LTO) batteries [<a href="#B88-jmse-13-00425" class="html-bibr">88</a>].</p> Full article ">Figure 7
<p>Illustration of marine vessel hull corrosion [<a href="#B105-jmse-13-00425" class="html-bibr">105</a>].</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Deep-Learning based Beam Selection in RIS-aided Maritime next-generation networks
Author: Avdikos
Highlights: Improved throughput Optimized beam selection Deep learning Reconfigurable Intelligent Surfaces (RIS)

Back to TopTop