Machine Learning for Dependable Edge Computing Systems and Services

A special issue of Big Data and Cognitive Computing (ISSN 2504-2289).

Deadline for manuscript submissions: 30 April 2024 | Viewed by 21268

Special Issue Editors

School of Computing, Faculty of Engineering and Physical Sciences, University of Leeds, Leeds LS2 9JT, UK
Interests: large-scale distributed systems; resource management; fault tolerance and software reliability; big data processing and analytic; applied machine learning (graph representation learning); reinforcement learning
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310014, China
Interests: big data processing; distributed system; computer networks; machine learning systems
Special Issues, Collections and Topics in MDPI journals
College of Software, Beihang University, Beijing 100191, China
Interests: intelligent software engineering; distributed system; software reliability and scalability
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK
Interests: cyber security; smart grid security; wireless sensor networks and IoT security
Special Issues, Collections and Topics in MDPI journals
School of Computer Science and Technology, Xi'an Jiaotong University, Xi’an 710049, China
Interests: virtualization; resource management; distributed computing; graph data mining

Special Issue Information

Dear Colleagues, 

Recent advances in machine learning (ML) techniques, particularly deep learning (DL), reinforcement learning, and federated learning, have successfully caused a huge number of breakthroughs in various application domains. Internet of Things (IoT) systems and applications consist of ubiquitously interconnecting devices (e.g., wireless sensors, wearable/mobile devices, cameras, smart tags, robots/UAVs, etc.). The urgent requirement of responsiveness and privacy led to Edge computing, a new paradigm that pushes the power of data analytics and computing capability to the edge of a network, closer to where the data are generated.  Huge challenges exist in the design, implementation, deployment and maintenance of trustworthy and reliable Edge systems’ infrastructures, algorithms, and applications.  ML and DL technologies are well-suited and insightful for use in the provision automated data and resource management and offer advanced secure and robust malicious behaviour detection, thereby significantly improving the trusted intelligence and operational efficiency. 

This Special Issue will cover, but not be limited to, the following topics:

  • ML for dependable middleware and infrastructure design;
  • ML for end-to-end performance tracing, debugging, and prediction;
  • ML for security and privacy in Edge computing, including anomaly detection, anomaly diagnosis, intrusion/malware/fraud detection, cyber-attack detection, lightweight access control framework, etc.;
  • ML-assisted interoperability and collaboration between edge devices and clouds;
  • Interpretability and robustness of ML for edge computing systems;
  • ML for autonomous systems and applications;
  • ML-assisted fault tolerance in Edge computing infrastructures and applications;
  • Privacy preserving federated learning for Edge computing infrastructures and applications;
  • Reinforcement learning for edge computing systems, particularly in resource management and Quality of Service;
  • Risk and threat detection and analysis for edge applications;
  • Open datasets of edge computing systems for system and ML research;
  • Big data analytics frameworks for edge computing;
  • Distributed training and neural architecture search for/on the edge.

Dr. Renyu Yang 
Prof. Dr. Zhenyu Wen 
Dr. Xu Wang 
Dr. Prosanta Gope
Dr. Bin Shi 
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. Big Data and Cognitive Computing 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 1800 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

  • machine learning
  • deep learning
  • edge computing
  • dependability
  • security and privacy
  • fault-tolerance
  • anomaly detection
  • anomaly diagnosis
  • access control
  • federated learning
  • reinforcement learning

Published Papers (3 papers)

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

Research

20 pages, 3064 KiB  
Article
Explaining Intrusion Detection-Based Convolutional Neural Networks Using Shapley Additive Explanations (SHAP)
by Remah Younisse, Ashraf Ahmad and Qasem Abu Al-Haija
Big Data Cogn. Comput. 2022, 6(4), 126; https://doi.org/10.3390/bdcc6040126 - 25 Oct 2022
Cited by 12 | Viewed by 2739
Abstract
Artificial intelligence (AI) and machine learning (ML) models have become essential tools used in many critical systems to make significant decisions; the decisions taken by these models need to be trusted and explained on many occasions. On the other hand, the performance of [...] Read more.
Artificial intelligence (AI) and machine learning (ML) models have become essential tools used in many critical systems to make significant decisions; the decisions taken by these models need to be trusted and explained on many occasions. On the other hand, the performance of different ML and AI models varies with the same used dataset. Sometimes, developers have tried to use multiple models before deciding which model should be used without understanding the reasons behind this variance in performance. Explainable artificial intelligence (XAI) models have presented an explanation for the models’ performance based on highlighting the features that the model considered necessary while making the decision. This work presents an analytical approach to studying the density functions for intrusion detection dataset features. The study explains how and why these features are essential during the XAI process. We aim, in this study, to explain XAI behavior to add an extra layer of explainability. The density function analysis presented in this paper adds a deeper understanding of the importance of features in different AI models. Specifically, we present a method to explain the results of SHAP (Shapley additive explanations) for different machine learning models based on the feature data’s KDE (kernel density estimation) plots. We also survey the specifications of dataset features that can perform better for convolutional neural networks (CNN) based models. Full article
(This article belongs to the Special Issue Machine Learning for Dependable Edge Computing Systems and Services)
Show Figures

Figure 1

18 pages, 1612 KiB  
Article
Social Networks Marketing and Consumer Purchase Behavior: The Combination of SEM and Unsupervised Machine Learning Approaches
by Pejman Ebrahimi, Marjan Basirat, Ali Yousefi, Md. Nekmahmud, Abbas Gholampour and Maria Fekete-Farkas
Big Data Cogn. Comput. 2022, 6(2), 35; https://doi.org/10.3390/bdcc6020035 - 25 Mar 2022
Cited by 30 | Viewed by 13609
Abstract
The purpose of this paper is to reveal how social network marketing (SNM) can affect consumers’ purchase behavior (CPB). We used the combination of structural equation modeling (SEM) and unsupervised machine learning approaches as an innovative method. The statistical population of the study [...] Read more.
The purpose of this paper is to reveal how social network marketing (SNM) can affect consumers’ purchase behavior (CPB). We used the combination of structural equation modeling (SEM) and unsupervised machine learning approaches as an innovative method. The statistical population of the study concluded users who live in Hungary and use Facebook Marketplace. This research uses the convenience sampling approach to overcome bias. Out of 475 surveys distributed, a total of 466 respondents successfully filled out the entire survey with a response rate of 98.1%. The results showed that all dimensions of social network marketing, such as entertainment, customization, interaction, WoM and trend, had positively and significantly influenced consumer purchase behavior (CPB) in Facebook Marketplace. Furthermore, we used hierarchical clustering and K-means unsupervised algorithms to cluster consumers. The results show that respondents of this research can be clustered in nine different groups based on behavior regarding demographic attributes. It means that distinctive strategies can be used for different clusters. Meanwhile, marketing managers can provide different options, products and services for each group. This study is of high importance in that it has adopted and used plspm and Matrixpls packages in R to show the model predictive power. Meanwhile, we used unsupervised machine learning algorithms to cluster consumer behaviors. Full article
(This article belongs to the Special Issue Machine Learning for Dependable Edge Computing Systems and Services)
Show Figures

Figure 1

17 pages, 659 KiB  
Article
Vec2Dynamics: A Temporal Word Embedding Approach to Exploring the Dynamics of Scientific Keywords—Machine Learning as a Case Study
by Amna Dridi, Mohamed Medhat Gaber, Raja Muhammad Atif Azad and Jagdev Bhogal
Big Data Cogn. Comput. 2022, 6(1), 21; https://doi.org/10.3390/bdcc6010021 - 21 Feb 2022
Cited by 1 | Viewed by 3884
Abstract
The study of the dynamics or the progress of science has been widely explored with descriptive and statistical analyses. Also this study has attracted several computational approaches that are labelled together as the Computational History of Science, especially with the rise of data [...] Read more.
The study of the dynamics or the progress of science has been widely explored with descriptive and statistical analyses. Also this study has attracted several computational approaches that are labelled together as the Computational History of Science, especially with the rise of data science and the development of increasingly powerful computers. Among these approaches, some works have studied dynamism in scientific literature by employing text analysis techniques that rely on topic models to study the dynamics of research topics. Unlike topic models that do not delve deeper into the content of scientific publications, for the first time, this paper uses temporal word embeddings to automatically track the dynamics of scientific keywords over time. To this end, we propose Vec2Dynamics, a neural-based computational history approach that reports stability of k-nearest neighbors of scientific keywords over time; the stability indicates whether the keywords are taking new neighborhood due to evolution of scientific literature. To evaluate how Vec2Dynamics models such relationships in the domain of Machine Learning (ML), we constructed scientific corpora from the papers published in the Neural Information Processing Systems (NIPS; actually abbreviated NeurIPS) conference between 1987 and 2016. The descriptive analysis that we performed in this paper verify the efficacy of our proposed approach. In fact, we found a generally strong consistency between the obtained results and the Machine Learning timeline. Full article
(This article belongs to the Special Issue Machine Learning for Dependable Edge Computing Systems and Services)
Show Figures

Figure 1

Back to TopTop