Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.9
Journals
Electronics
Special Issues
The Applications of Deep Neural Network in Edge Computing
share announcement

The Applications of Deep Neural Network in Edge Computing

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: 15 July 2024 | Viewed by 735

Special Issue Editors

Dr. Samiya Khan

E-Mail Website
Guest Editor
School of Computing and Mathematical Sciences, University of Greenwich, London SE10 9LS, UK
Interests: data science; edge computing; digital health
Dr. Korhan Cengiz

E-Mail Website
Guest Editor
Department of Information Technologies, Faculty of Informatics and Management, University of Hradec Kralove, 500 03 Hradec Králové 3, Czech Republic
Interests: Internet of Things; artificial intelligence; wireless sensor networks

Special Issue Information

Dear Colleagues,

The evolution of Deep Neural Networks (DNNs) has revolutionized various domains of artificial intelligence, from image recognition to natural language processing. When coupled with the expanding field of Edge Computing, where data processing occurs closer to the data source rather than in distant data centers, DNNs present a transformative potential. Edge Computing aims to reduce latency, preserve bandwidth, and upgrade privacy and security by processing data locally. The integration of DNNs into Edge Computing environments enables real-time, efficient, and intelligent decision-making in numerous applications, ranging from autonomous vehicles to smart city infrastructure. This convergence is particularly crucial as the Internet of Things (IoT) era matures, demanding more sophisticated, decentralized computing paradigms.

This Special Issue aims to explore the cutting-edge developments, existing challenges, and future directions regarding the deployment of Deep Neural Networks in Edge Computing scenarios. It will highlight innovative research that showcases how DNNs can enhance the capabilities of Edge Computing devices, making them smarter, more efficient, and capable of autonomous decision-making. This Special Issue aligns with the journal's scope, addressing novel technological advancements in computer science, and focusing on real-world applications, theoretical challenges, and the synergy between emerging computing paradigms and artificial intelligence.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

  • Deep Neural Networks (DNNs) in IoT: Applications and challenges of implementing DNNs in various IoT scenarios.
  • Optimization of DNNs for Edge Devices: Techniques and strategies for optimizing DNN architectures for resource-constrained Edge devices.
  • Edge-based AI Services: Development of AI-driven services and applications powered by DNNs at the Edge.
  • Real-time Analytics: Implementing DNNs for real-time data processing and decision-making in Edge environments.
  • DNNs for Autonomous Systems: Use of DNNs in Edge Computing for autonomous vehicles and robotics.
  • Energy-efficient Deep Learning: Approaches for reducing the power consumption of DNNs in Edge Computing.
  • Privacy-preserving Techniques for DNN: Utilizing DNNs at the Edge for enhancing data privacy and security.
  • Integration Challenges: Addressing the challenges in integrating DNNs with existing Edge Computing infrastructures.

Dr. Samiya Khan
Dr. Korhan Cengiz
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. Electronics is an international peer-reviewed open access semimonthly 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

  • deep neural networks
  • edge computing
  • Internet of Things (IoT)
  • real-time data processing
  • AI optimization for edge
  • autonomous decision-making
  • privacy and security in AI
  • energy-efficient machine learning
  • AI services at the edge

Published Papers (1 paper)

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

Research

25 pages, 10010 KiB  
Article
Task-Offloading Strategy of Mobile Edge Computing for WBANs
by Yuhong Li and Wenzhu Zhang
Electronics 2024, 13(8), 1422; https://doi.org/10.3390/electronics13081422 - 09 Apr 2024
Viewed by 383
Abstract
In recent years, mobile edge computing has become one of the popular methods to provide computing resources for the body area network, but existing research only considers the problem of minimizing the cost of offloading when solving the optimization problem of task-offloading, ignoring [...] Read more.
In recent years, mobile edge computing has become one of the popular methods to provide computing resources for the body area network, but existing research only considers the problem of minimizing the cost of offloading when solving the optimization problem of task-offloading, ignoring the trust problem of edge computing nodes, and offloading tasks on edge nodes may cause user information disclosure and reduce the quality of user experience. In response to this situation, this study aims to minimize the average user cost and designs a task-offloading strategy based on the D3QN (dueling double deep Q-network) algorithm in conjunction with the blockchain information security storage model. This strategy uses deep reinforcement learning algorithms to obtain the minimum average offloading cost of the system while considering user latency, energy consumption, and data protection conditions. The experimental simulation results show that compared to traditional schemes and other reinforcement learning-based schemes, this scheme can more effectively reduce the average cost of the system, and the average cost is reduced by 31.25% when reaching convergence. In addition, as the complexity of the model increases, this scheme can provide users with better experience quality, with 53.7% of the 1000 users having a very good experience quality. Full article
(This article belongs to the Special Issue The Applications of Deep Neural Network in Edge Computing)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop