Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.1
2.8
Journals
Future Internet
Special Issues
Edge Intelligence: Edge Computing for 5G and the Internet of...
share announcement

Edge Intelligence: Edge Computing for 5G and the Internet of Things

A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: closed (20 November 2024) | Viewed by 11880

Special Issue Editors

Dr. Yuezhi Zhou

E-Mail Website
Guest Editor
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
Interests: mobile computing; data privacy; machine learning (artificial intelligence); Internet of Things
Prof. Dr. Xu Chen

E-Mail Website
Guest Editor
Department of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China
Interests: edge computing; edge intelligence; 5G/6G; IoT

Special Issue Information

Dear Colleagues,

To empower 5G and IoT networks with AI capabilities, large volumes of multi-modal sensing data (e.g., audios, and videos) are continuously generated by the mobile and IoT devices that reside at the network edge. Impelled by this trend, there is an urgent need to push the frontiers of AI to the network edge so as to fully unleash the potential utilization of 5G and IoT networks in various smart services and applications. Thus, edge intelligence, as an emerging paradigm that pushes AI tasks and services from the network core to the network edge, has been widely recognized as an indispensable component of next-generation intelligent networking systems. Existing research on edge intelligence is still in its preliminary stage, and thus a venue dedicated to the discussion, promotion, and dissemination of research in this domain is highly desired by the networking, computing and AI communities alike. To bridge this gap, this Special Issue aims to gather recent advances and novel contributions from academic researchers and industry practitioners in the areas of edge intelligence and edge computing for 5G and IoT networks. The scope of this Special Issue includes, but is not limited to, the following:

  • Intelligent edge computing resource management for 5G and IoT;
  • Edge computing system and AI model co-design for 5G and IoT;
  • Cloud–edge–device converged computing for AI for 5G and IoT;
  • Federated edge learning over for 5G and IoT;
  • Distributed edge intelligence model training and inference;
  • Privacy-preserving methods for edge intelligence;
  • Distributed edge data analytics for 5G and IoT;
  • Other emerging edge computing and edge intelligence techniques and applications for 5G and IoT.

Dr. Yuezhi Zhou
Prof. Dr. Xu Chen
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. Future Internet 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 1600 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

  • edge computing
  • edge intelligence
  • 5G networks
  • IoT networks
  • federated edge learning
  • cloud–edge–device converged computing
  • distributed edge intelligence model training and inference
  • privacy-preserving edge intelligence

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 polices can be found here.

Published Papers (7 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

14 pages, 464 KiB  
Article
Empowering Healthcare: TinyML for Precise Lung Disease Classification
by Youssef Abadade, Nabil Benamar, Miloud Bagaa and Habiba Chaoui
Future Internet 2024, 16(11), 391; https://doi.org/10.3390/fi16110391 - 25 Oct 2024
Viewed by 1775
Abstract
Respiratory diseases such as asthma pose significant global health challenges, necessitating efficient and accessible diagnostic methods. The traditional stethoscope is widely used as a non-invasive and patient-friendly tool for diagnosing respiratory conditions through lung auscultation. However, it has limitations, such as a lack [...] Read more.
Respiratory diseases such as asthma pose significant global health challenges, necessitating efficient and accessible diagnostic methods. The traditional stethoscope is widely used as a non-invasive and patient-friendly tool for diagnosing respiratory conditions through lung auscultation. However, it has limitations, such as a lack of recording functionality, dependence on the expertise and judgment of physicians, and the absence of noise-filtering capabilities. To overcome these limitations, digital stethoscopes have been developed to digitize and record lung sounds. Recently, there has been growing interest in the automated analysis of lung sounds using Deep Learning (DL). Nevertheless, the execution of large DL models in the cloud often leads to latency, dependency on internet connectivity, and potential privacy issues due to the transmission of sensitive health data. To address these challenges, we developed Tiny Machine Learning (TinyML) models for the real-time detection of respiratory conditions by using lung sound recordings, deployable on low-power, cost-effective devices like digital stethoscopes. We trained three machine learning models—a custom CNN, an Edge Impulse CNN, and a custom LSTM—on a publicly available lung sound dataset. Our data preprocessing included bandpass filtering and feature extraction through Mel-Frequency Cepstral Coefficients (MFCCs). We applied quantization techniques to ensure model efficiency. The custom CNN model achieved the highest performance, with 96% accuracy and 97% precision, recall, and F1-scores, while maintaining moderate resource usage. These findings highlight the potential of TinyML to provide accessible, reliable, and real-time diagnostic tools, particularly in remote and underserved areas, demonstrating the transformative impact of integrating advanced AI algorithms into portable medical devices. This advancement facilitates the prospect of automated respiratory health screening using lung sounds. Full article
(This article belongs to the Special Issue Edge Intelligence: Edge Computing for 5G and the Internet of Things)
►▼ Show Figures

Figure 1

13 pages, 4781 KiB  
Article
An Intelligent System for Determining Driver Anxiety Level: A Comparison Study of Two Fuzzy-Based Models
by Yi Liu and Leonard Barolli
Future Internet 2024, 16(10), 348; https://doi.org/10.3390/fi16100348 - 24 Sep 2024
Viewed by 548
Abstract
While driving, stress and frustration can affect safe driving and pose the risk of causing traffic accidents. Therefore, it is important to control the driver’s anxiety level in order to improve the driving experience. In this paper, we propose and implement an intelligent [...] Read more.
While driving, stress and frustration can affect safe driving and pose the risk of causing traffic accidents. Therefore, it is important to control the driver’s anxiety level in order to improve the driving experience. In this paper, we propose and implement an intelligent system based on fuzzy logic (FL) for deciding the driver’s anxiety level (DAL). In order to investigate the effects of the considered parameters and compare the evaluation results, we implement two models: DAL Model 1 (DALM1) and DAL Model 2 (DALM2). The input parameters of DALM1 include driving experience (DE), in-car environment conditions (IECs), and driver age (DA), while for DALM2, we add a new parameter called the accident anxiety state (AAS). For both models, the output parameter is DAL. We carried out many simulations and compared the results of DALM1 and DALM2. The evaluation results show that the DAL is very good for drivers’ ages between 30 to 50 years old. However, when the driver’s age is below 30 or above 50, DAL tends to decline. With an increase in DE and IECs, the DAL value is decreased. But when the AAS is increased, the DAL is increased. DALM2 is more complex because the rule base is larger than DALM1, but it makes a better decision of DAL value. Full article
(This article belongs to the Special Issue Edge Intelligence: Edge Computing for 5G and the Internet of Things)
►▼ Show Figures

Figure 1

22 pages, 1871 KiB  
Article
Wireless and Fiber-Based Post-Quantum-Cryptography-Secured IPsec Tunnel
by Daniel Christian Lawo, Rana Abu Bakar, Abraham Cano Aguilera, Filippo Cugini, José Luis Imaña, Idelfonso Tafur Monroy and Juan Jose Vegas Olmos
Future Internet 2024, 16(8), 300; https://doi.org/10.3390/fi16080300 - 21 Aug 2024
Cited by 1 | Viewed by 1730
Abstract
In the near future, commercially accessible quantum computers are anticipated to revolutionize the world as we know it. These advanced machines are predicted to render traditional cryptographic security measures, deeply ingrained in contemporary communication, obsolete. While symmetric cryptography methods like AES can withstand [...] Read more.
In the near future, commercially accessible quantum computers are anticipated to revolutionize the world as we know it. These advanced machines are predicted to render traditional cryptographic security measures, deeply ingrained in contemporary communication, obsolete. While symmetric cryptography methods like AES can withstand quantum assaults if key sizes are doubled compared to current standards, asymmetric cryptographic techniques, such as RSA, are vulnerable to compromise. Consequently, there is a pressing need to transition towards post-quantum cryptography (PQC) principles in order to safeguard our privacy effectively. A challenge is to include PQC into existing protocols and thus into the existing communication structure. In this work, we report on the first experimental IPsec tunnel secured by the PQC algorithms Falcon, Dilithium, and Kyber. We deploy our IPsec tunnel in two scenarios. The first scenario represents a high-performance data center environment where many machines are interconnected via high-speed networks. We achieve an IPsec tunnel with an AES-256 GCM encrypted east–west throughput of 100 Gbit/s line rate. The second scenario shows an IPsec tunnel between a wireless NVIDIA Jetson and the cloud that achieves a 0.486 Gbit/s AES-256 GCM encrypted north–south throughput. This case represents a mobile device that communicates securely with applications running in the cloud. Full article
(This article belongs to the Special Issue Edge Intelligence: Edge Computing for 5G and the Internet of Things)
►▼ Show Figures

Figure 1

29 pages, 8084 KiB  
Article
SRv6-Based Edge Service Continuity in 5G Mobile Networks
by Laura Lemmi, Carlo Puliafito, Antonio Virdis and Enzo Mingozzi
Future Internet 2024, 16(4), 138; https://doi.org/10.3390/fi16040138 - 19 Apr 2024
Viewed by 1607
Abstract
Ensuring compliance with the stringent latency requirements of edge services requires close cooperation between the network and computing components. Within mobile 5G networks, the nomadic behavior of users may impact the performance of edge services, prompting the need for workload migration techniques. These [...] Read more.
Ensuring compliance with the stringent latency requirements of edge services requires close cooperation between the network and computing components. Within mobile 5G networks, the nomadic behavior of users may impact the performance of edge services, prompting the need for workload migration techniques. These techniques allow services to follow users by moving between edge nodes. This paper introduces an innovative approach for edge service continuity by integrating Segment Routing over IPv6 (SRv6) into the 5G core data plane alongside the ETSI multi-access edge computing (MEC) architecture. Our approach maintains compatibility with non-SRv6 5G network components. We use SRv6 for packet steering and Software-Defined Networking (SDN) for dynamic network configuration. Leveraging the SRv6 Network Programming paradigm, we achieve lossless workload migration by implementing a packet buffer as a virtual network function. Our buffer may be dynamically allocated and configured within the network. We test our proposed solution on a small-scale testbed consisting of an Open Network Operating System (ONOS) SDN controller and a core network made of P4 BMv2 switches, emulated using Mininet. A comparison with a non-SRv6 alternative that uses IPv6 routing shows the higher scalability and flexibility of our approach in terms of the number of rules to be installed and time required for configuration. Full article
(This article belongs to the Special Issue Edge Intelligence: Edge Computing for 5G and the Internet of Things)
►▼ Show Figures

Figure 1

31 pages, 2605 KiB  
Article
Intelligent Resource Orchestration for 5G Edge Infrastructures
by Rafael Moreno-Vozmediano, Rubén S. Montero, Eduardo Huedo and Ignacio M. Llorente
Future Internet 2024, 16(3), 103; https://doi.org/10.3390/fi16030103 - 19 Mar 2024
Cited by 2 | Viewed by 1921
Abstract
The adoption of edge infrastructure in 5G environments stands out as a transformative technology aimed at meeting the increasing demands of latency-sensitive and data-intensive applications. This research paper presents a comprehensive study on the intelligent orchestration of 5G edge computing infrastructures. The proposed [...] Read more.
The adoption of edge infrastructure in 5G environments stands out as a transformative technology aimed at meeting the increasing demands of latency-sensitive and data-intensive applications. This research paper presents a comprehensive study on the intelligent orchestration of 5G edge computing infrastructures. The proposed Smart 5G Edge-Cloud Management Architecture, built upon an OpenNebula foundation, incorporates a ONEedge5G experimental component, which offers intelligent workload forecasting and infrastructure orchestration and automation capabilities, for optimal allocation of virtual resources across diverse edge locations. The research evaluated different forecasting models, based both on traditional statistical techniques and machine learning techniques, comparing their accuracy in CPU usage prediction for a dataset of virtual machines (VMs). Additionally, an integer linear programming formulation was proposed to solve the optimization problem of mapping VMs to physical servers in distributed edge infrastructure. Different optimization criteria such as minimizing server usage, load balancing, and reducing latency violations were considered, along with mapping constraints. Comprehensive tests and experiments were conducted to evaluate the efficacy of the proposed architecture. Full article
(This article belongs to the Special Issue Edge Intelligence: Edge Computing for 5G and the Internet of Things)
►▼ Show Figures

Figure 1

17 pages, 5387 KiB  
Article
Edge-Enhanced TempoFuseNet: A Two-Stream Framework for Intelligent Multiclass Video Anomaly Recognition in 5G and IoT Environments
by Gulshan Saleem, Usama Ijaz Bajwa, Rana Hammad Raza and Fan Zhang
Future Internet 2024, 16(3), 83; https://doi.org/10.3390/fi16030083 - 29 Feb 2024
Cited by 1 | Viewed by 1626
Abstract
Surveillance video analytics encounters unprecedented challenges in 5G and IoT environments, including complex intra-class variations, short-term and long-term temporal dynamics, and variable video quality. This study introduces Edge-Enhanced TempoFuseNet, a cutting-edge framework that strategically reduces spatial resolution to allow the processing of low-resolution [...] Read more.
Surveillance video analytics encounters unprecedented challenges in 5G and IoT environments, including complex intra-class variations, short-term and long-term temporal dynamics, and variable video quality. This study introduces Edge-Enhanced TempoFuseNet, a cutting-edge framework that strategically reduces spatial resolution to allow the processing of low-resolution images. A dual upscaling methodology based on bicubic interpolation and an encoder–bank–decoder configuration is used for anomaly classification. The two-stream architecture combines the power of a pre-trained Convolutional Neural Network (CNN) for spatial feature extraction from RGB imagery in the spatial stream, while the temporal stream focuses on learning short-term temporal characteristics, reducing the computational burden of optical flow. To analyze long-term temporal patterns, the extracted features from both streams are combined and routed through a Gated Recurrent Unit (GRU) layer. The proposed framework (TempoFuseNet) outperforms the encoder–bank–decoder model in terms of performance metrics, achieving a multiclass macro average accuracy of 92.28%, an F1-score of 69.29%, and a false positive rate of 4.41%. This study presents a significant advancement in the field of video anomaly recognition and provides a comprehensive solution to the complex challenges posed by real-world surveillance scenarios in the context of 5G and IoT. Full article
(This article belongs to the Special Issue Edge Intelligence: Edge Computing for 5G and the Internet of Things)
►▼ Show Figures

Figure 1

23 pages, 737 KiB  
Article
A Synergistic Elixir-EDA-MQTT Framework for Advanced Smart Transportation Systems
by Yushan Li and Satoshi Fujita
Future Internet 2024, 16(3), 81; https://doi.org/10.3390/fi16030081 - 28 Feb 2024
Cited by 1 | Viewed by 1671
Abstract
This paper proposes a novel event-driven architecture for enhancing edge-based vehicular systems within smart transportation. Leveraging the inherent real-time, scalable, and fault-tolerant nature of the Elixir language, we present an innovative architecture tailored for edge computing. This architecture employs MQTT for efficient event [...] Read more.
This paper proposes a novel event-driven architecture for enhancing edge-based vehicular systems within smart transportation. Leveraging the inherent real-time, scalable, and fault-tolerant nature of the Elixir language, we present an innovative architecture tailored for edge computing. This architecture employs MQTT for efficient event transport and utilizes Elixir’s lightweight concurrency model for distributed processing. Robustness and scalability are further ensured through the EMQX broker. We demonstrate the effectiveness of our approach through two smart transportation case studies: a traffic light system for dynamically adjusting signal timing, and a cab dispatch prototype designed for high concurrency and real-time data processing. Evaluations on an Apple M1 chip reveal consistently low latency responses below 5 ms and efficient multicore utilization under load. These findings showcase the system’s robust throughput and multicore programming capabilities, confirming its suitability for real-time, distributed edge computing applications in smart transportation. Therefore, our work suggests that integrating Elixir with an event-driven model represents a promising approach for developing scalable, responsive applications in edge computing. This opens avenues for further exploration and adoption of Elixir in addressing the evolving demands of edge-based smart transportation systems. Full article
(This article belongs to the Special Issue Edge Intelligence: Edge Computing for 5G and the Internet of Things)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-7
Back to TopTop