Software-Driven Federated Learning for/in Smart Environment

A special issue of Future Internet (ISSN 1999-5903).

Deadline for manuscript submissions: 28 February 2025 | Viewed by 2039

Special Issue Editors


E-Mail Website
Guest Editor
School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, 16 Malone Rd, Belfast BT9 6SB, UK
Interests: empirical software engineering; edge/cloud computing; performance engineering; privacy preserving data analytics

E-Mail Website
Guest Editor
Department of Software Engineering and Artificial Intelligence (DISIA), Faculty of Computer Science and Engineering, Office 431, Universidad Complutense de Madrid (UCM), 28040 Madrid, Spain
Interests: computer security; cyber security; privacy; information security; cryptography; intrusion detection; malware; trust; anonymity
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Since the term “smart environment” was coined in the late 1980s, there has been an increase in the amount of interest and effort in various smart environmental scenarios. For example, the early definition of smart homes derived from home automation terminology in 1992, while the term smart city emerged in the literature in 1998 and derived from urban simulations and different knowledge bases. Nowadays, along with the evolution of technology, the Internet of Things (IoT) and machine learning (ML) increasingly play a crucial and combined role in achieving all kinds of data-centric smart environments. However, such enabling technologies also bring challenges to smart environments involved in large-scale data collection, analysis, and decision-making processes. Three typical challenges are as follows:

  • Individual IoT devices generally have limited computation, storage, and network capabilities (e.g., the embedded RAM has only 4 KB in the current taxi-mounted GPS devices). Consequently, the heavy computation overhead makes conventional ML techniques impractical due to the resource constraints of IoT devices.
  • An IoT system may involve the non-scalable integration of heterogeneous technologies produced by different manufacturers; thus, there is not a one-size-fits-all solution for ML implementations in smart environments.
  • The distributed, diverse, and uncertain end-user situations of an IoT system would face more data privacy, security, and ethical risks from nefarious attacks within smart environments.

To address these challenges, following the software-driven trend in making computing environments programmable and software defined, smart environments should also pay more attention to software with significant heterogeneity and diversity in IoT technologies. In fact, despite the widely recognised and possibly overemphasised aspects of hardware, it is software that eventually makes an environment smart. Inspired by the well-known “mind/brain” metaphor, users essentially rely on software applications to communicate and work with smart devices and objects around them.

By considering the privacy-friendly paradigm of federated learning, we propose this Special Issue on Software-driven Federated Learning for/in Smart Environments. This Special Issue aims to bring together professionals from academia and industry to explore the latest experiences, advancements, challenges, methods, techniques, and solutions related to the engineering of federated learning systems for/in smart environments. Thus, we invite researchers, practitioners, and industry experts to submit their original contributions that cover the conjoint area of software engineering, federated learning, and smart environments, including, but not limited to, the following:

  • Software architectures and design patterns for constructing smart environments;
  • Evidential assessments on the rigor, effectiveness, and relevance of a variety of software technologies in any specific smart environment (e.g., smart city, office, home, etc.);
  • Empirical case studies on federated learning implementation in/for smart environments;
  • Experiences in building federated learning systems to enable smart environments;
  • Challenges and lessons learned from adopting federated learning in/for software-driven smart environments;
  • Negative results highlighting the areas where future studies are needed for building smart environments.

Dr. Zheng Li
Prof. Dr. Luis Javier García Villalba
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

  • federated learning
  • Internet of Things
  • machine learning
  • smart environment
  • software-driven world

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 (1 paper)

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

Research

23 pages, 5496 KiB  
Article
Edge Federated Optimization for Heterogeneous Data
by Hsin-Tung Lin and Chih-Yu Wen
Future Internet 2024, 16(4), 142; https://doi.org/10.3390/fi16040142 - 22 Apr 2024
Cited by 1 | Viewed by 1629
Abstract
This study focuses on optimizing federated learning in heterogeneous data environments. We implement the FedProx and a baseline algorithm (i.e., the FedAvg) with advanced optimization strategies to tackle non-IID data issues in distributed learning. Model freezing and pruning techniques are explored to showcase [...] Read more.
This study focuses on optimizing federated learning in heterogeneous data environments. We implement the FedProx and a baseline algorithm (i.e., the FedAvg) with advanced optimization strategies to tackle non-IID data issues in distributed learning. Model freezing and pruning techniques are explored to showcase the effective operations of deep learning models on resource-constrained edge devices. Experimental results show that at a pruning rate of 10%, the FedProx with structured pruning in the MIT-BIH and ST databases achieved the best F1 scores, reaching 96.01% and 77.81%, respectively, which achieves a good balance between system efficiency and model accuracy compared to those of the FedProx with the original configuration, reaching F1 scores of 66.12% and 89.90%, respectively. Similarly, with layer freezing technique, unstructured pruning method, and a pruning rate of 20%, the FedAvg algorithm effectively balances classification performance and degradation of pruned model accuracy, achieving F1 scores of 88.75% and 72.75%, respectively, compared to those of the FedAvg with the original configuration, reaching 56.82% and 85.80%, respectively. By adopting model optimization strategies, a practical solution is developed for deploying complex models in edge federated learning, vital for its efficient implementation. Full article
(This article belongs to the Special Issue Software-Driven Federated Learning for/in Smart Environment)
Show Figures

Figure 1

Back to TopTop