Federated Learning for Smart Healthcare: A Survey

ACM Computing Surveys, Journal Year: 2022, Volume and Issue: 55(3), P. 1 - 37

Published: Feb. 3, 2022

Recent advances in communication technologies and the Internet-of-Medical-Things (IOMT) have transformed smart healthcare enabled by artificial intelligence (AI). Traditionally, AI techniques require centralized data collection processing that may be infeasible realistic scenarios due to high scalability of modern networks growing privacy concerns. Federated Learning (FL), as an emerging distributed collaborative paradigm, is particularly attractive for healthcare, coordinating multiple clients (e.g., hospitals) perform training without sharing raw data. Accordingly, we provide a comprehensive survey on use FL healthcare. First, present recent FL, motivations, requirements using The designs are then discussed, ranging from resource-aware secure privacy-aware incentive personalized FL. Subsequently, state-of-the-art review applications key domains, including health management, remote monitoring, medical imaging, COVID-19 detection. Several FL-based projects analyzed, lessons learned also highlighted. Finally, discuss interesting research challenges possible directions future

Language: Английский

---

Cellular, Wide-Area, and Non-Terrestrial IoT: A Survey on 5G Advances and the Road Toward 6G

IEEE Communications Surveys & Tutorials, Journal Year: 2022, Volume and Issue: 24(2), P. 1117 - 1174

Published: Jan. 1, 2022

The next wave of wireless technologies is proliferating in connecting things among themselves as well to humans. In the era Internet Things (IoT), billions sensors, machines, vehicles, drones, and robots will be connected, making world around us smarter. IoT encompass devices that must wirelessly communicate a diverse set data gathered from environment for myriad new applications. ultimate goal extract insights this develop solutions improve quality life generate revenue. Providing large-scale, long-lasting, reliable, near real-time connectivity major challenge enabling smart connected world. This paper provides comprehensive survey on existing emerging communication serving applications context cellular, wide-area, non-terrestrial networks. Specifically, technology enhancements providing access fifth-generation (5G) beyond cellular networks, networks over unlicensed spectrum are presented. Aligned with main key performance indicators 5G we investigate standards enable energy efficiency, reliability, low latency, scalability (connection density) current future include grant-free channel coding short-packet communications, non-orthogonal multiple access, on-device intelligence. Further, vision paradigm shifts 2030s provided, integration associated like artificial intelligence, spectra elaborated. particular, potential using deep learning federated techniques enhancing efficiency security discussed, their promises challenges introduced. Finally, research directions toward pointed out.

Language: Английский

---

Edge Learning for B5G Networks With Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing

IEEE Journal of Selected Topics in Signal Processing, Journal Year: 2023, Volume and Issue: 17(1), P. 9 - 39

Published: Jan. 1, 2023

To process and transfer large amounts of data in emerging wireless services, it has become increasingly appealing to exploit distributed communication learning. Specifically, edge learning (EL) enables local model training on geographically disperse nodes minimizes the need for frequent exchange. However, current design separating EL deployment optimization does not yet reap promised benefits signal processing, sometimes suffers from excessive signalling overhead, long processing delay, unstable convergence. In this paper, we provide an overview practical techniques their interplay with advanced designs. particular, typical performance metrics dual-functional networks are discussed. Also, recent achievements enabling surveyed exemplifications mutual perspectives "communications learning" "learning communications." The application within a variety future systems also envisioned beyond 5G (B5G) networks. For goal-oriented semantic communication, present first mathematical source entropy as problem. addition, viewpoint information theory, identify fundamental open problems characterizing rate regions supporting learning-and-computing tasks. We technical challenges well opportunities field, aim inspiring research promoting widespread developments B5G.

Language: Английский

---

A state-of-the-art survey on solving non-IID data in Federated Learning

Future Generation Computer Systems, Journal Year: 2022, Volume and Issue: 135, P. 244 - 258

Published: May 7, 2022

Language: Английский

---

Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 138509 - 138542

Published: Jan. 1, 2021

In this article, we present a comprehensive study with an experimental analysis of federated deep learning approaches for cyber security in the Internet Things (IoT) applications. Specifically, first provide review learning-based and privacy systems several types IoT applications, including, Industrial IoT, Edge Computing, Drones, Healthcare Things, Vehicles, etc. Second, use blockchain malware/intrusion detection applications is discussed. Then, vulnerabilities systems. Finally, three approaches, namely, Recurrent Neural Network (RNN), Convolutional (CNN), Deep (DNN). For each model, performance centralized under new real traffic datasets, Bot-IoT dataset, MQTTset TON_IoT dataset. The goal article to important information on emerging technologies security. addition, it demonstrates that outperform classic/centralized versions machine (non-federated learning) assuring device data higher accuracy detecting attacks.

Language: Английский

---

Federated Learning for Cybersecurity: Concepts, Challenges, and Future Directions

IEEE Transactions on Industrial Informatics, Journal Year: 2021, Volume and Issue: 18(5), P. 3501 - 3509

Published: Oct. 11, 2021

Federated learning (FL) is a recent development in artificial intelligence, which typically based on the concept of decentralized data. As cyberattacks are frequently happening various applications deployed real time, most industrialists hesitating to move forward adopting technology Internet Everything. This article aims provide an extensive study how FL could be utilized for providing better cybersecurity and prevent time. We present survey models currently developed by researchers authentication, privacy, trust management, attack detection. also discuss few real-time use cases that have been recently adopted them preserving privacy data improving performance system. Based study, we conclude this with some prominent challenges future directions can focus scenarios.

Language: Английский

---

Federated Learning in Edge Computing: A Systematic Survey

Sensors, Journal Year: 2022, Volume and Issue: 22(2), P. 450 - 450

Published: Jan. 7, 2022

Edge Computing (EC) is a new architecture that extends Cloud (CC) services closer to data sources. EC combined with Deep Learning (DL) promising technology and widely used in several applications. However, conventional DL architectures enabled, producers must frequently send share third parties, edge or cloud servers, train their models. This often impractical due the high bandwidth requirements, legalization, privacy vulnerabilities. The Federated (FL) concept has recently emerged as solution for mitigating problems of unwanted loss, privacy, legalization. FL can co-train models across distributed clients, such mobile phones, automobiles, hospitals, more, through centralized server, while maintaining localization. therefore be viewed stimulating factor paradigm it enables collaborative learning model optimization. Although existing surveys have taken into account applications environments, there not been any systematic survey discussing implementation challenges paradigm. paper aims provide literature on environments taxonomy identify advanced solutions other open problems. In this survey, we review fundamentals FL, then related works EC. Furthermore, describe protocols, architecture, framework, hardware requirements environment. Moreover, discuss applications, challenges, FL. Finally, detail two relevant case studies applying EC, issues potential directions future research. We believe will help researchers better understand connection between enabling technologies concepts.

Language: Английский

---

Blockchain-Based Federated Learning for Securing Internet of Things: A Comprehensive Survey

ACM Computing Surveys, Journal Year: 2022, Volume and Issue: 55(9), P. 1 - 43

Published: Sept. 6, 2022

The Internet of Things (IoT) ecosystem connects physical devices to the internet, offering significant advantages in agility, responsiveness, and potential environmental benefits. number variety IoT are sharply increasing, as they do, generate data sources. Deep learning (DL) algorithms increasingly integrated into applications learn infer patterns make intelligent decisions. However, current paradigms rely on centralized storage computing operate DL algorithms. This key central component can potentially cause issues scalability, security threats, privacy breaches. Federated (FL) has emerged a new paradigm for preserve privacy. Although FL helps reduce leakage by avoiding transferring client data, it still many challenges related models’ vulnerabilities attacks. With emergence blockchain smart contracts, utilization these technologies safeguard across ecosystems. study aims review blockchain-based methods securing systems holistically. It presents state research blockchain, how be applied approaches, issues, responses outline need use emerging approaches toward also focuses analytics from perspective open questions. provides thorough literature applications. Finally, risks associated with integrating discussed considered future works.

Language: Английский

---

Federated learning for smart cities: A comprehensive survey

Sustainable Energy Technologies and Assessments, Journal Year: 2022, Volume and Issue: 55, P. 102987 - 102987

Published: Dec. 31, 2022

Language: Английский

---

Blockchain and AI-Based Solutions to Combat Coronavirus (COVID-19)-Like Epidemics: A Survey

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 95730 - 95753

Published: Jan. 1, 2021

The beginning of 2020 has seen the emergence coronavirus outbreak caused by a novel virus called SARS-CoV-2. sudden explosion and uncontrolled worldwide spread COVID-19 show limitations existing healthcare systems in timely handling public health emergencies. In such contexts, innovative technologies as blockchain Artificial Intelligence (AI) have emerged promising solutions for fighting epidemic. particular, can combat pandemics enabling early detection outbreaks, ensuring ordering medical data, reliable supply chain during tracing. Moreover, AI provides intelligent identifying symptoms treatments supporting drug manufacturing. Therefore, we present an extensive survey on use combating epidemics. First, introduce new conceptual architecture which integrates COVID-19. Then, latest research efforts various applications. newly emerging projects cases enabled these to deal with pandemic are also presented. A case study is provided using federated detection. Finally, point out challenges future directions that motivate more coronavirus-like

Language: Английский

---