T-BFL model based on two-dimensional trust and blockchain-federated learning for medical data sharing

The Journal of Supercomputing, Journal Year: 2025, Volume and Issue: 81(2)

Published: Jan. 8, 2025

Language: Английский

---

A comprehensive survey on impact of applying various technologies on the internet of medical things

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(3)

Published: Jan. 8, 2025

Abstract This paper explores the transformative impact of Internet Medical Things (IoMT) on healthcare. By integrating medical equipment and sensors with internet, IoMT enables real-time monitoring patient health, remote care, individualized treatment plans. significantly improves several healthcare domains, including managing chronic diseases, safety, drug adherence, resulting in better outcomes reduced expenses. Technologies like blockchain, Artificial Intelligence (AI), cloud computing further boost IoMT’s capabilities Blockchain enhances data security interoperability, AI analyzes massive volumes health to find patterns make predictions, offers scalable cost-effective processing storage. Therefore, this provides a comprehensive review (IoT) IoMT-based edge-intelligent smart healthcare, focusing publications published between 2018 2024. The addresses numerous studies IoT, IoMT, AI, edge computing, security, Deep Learning, blockchain. obstacles facing are also covered paper, interoperability issues, regulatory compliance, privacy concerns. Finally, recommendations for provided.

Language: Английский

---

Survey on Federated Learning enabling indoor navigation for industry 4.0 in B5G

Future Generation Computer Systems, Journal Year: 2023, Volume and Issue: 148, P. 250 - 265

Published: June 12, 2023

Language: Английский

---

Enhancing trust and privacy in distributed networks: a comprehensive survey on blockchain-based federated learning

Knowledge and Information Systems, Journal Year: 2024, Volume and Issue: 66(8), P. 4377 - 4403

Published: April 25, 2024

Language: Английский

---

Survey: federated learning data security and privacy-preserving in edge-Internet of Things

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(5)

Published: April 29, 2024

Abstract The amount of data generated owing to the rapid development Smart Internet Things is increasing exponentially. Traditional machine learning can no longer meet requirements for training complex models with large amounts data. Federated learning, as a new paradigm statistical in distributed edge networks, alleviates integration and problems context massive heterogeneous security protection private Edge computing processes at layers sources ensure low-data-delay processing; it provides high-bandwidth communication stable network environment, relieves pressure processing using single node cloud center. A combination federated further optimize computing, communication, edge-Internet Things. This review investigated status expounded on its basic principles. Then, view attacks privacy leakage things, relevant work was from cryptographic technologies (such secure multi-party computation, homomorphic encryption secret sharing), perturbation schemes differential privacy), adversarial other measures. Finally, challenges future research directions are discussed.

Language: Английский

---

Increasing the attractiveness of electric vehicles for consumers in cold climates

E3S Web of Conferences, Journal Year: 2024, Volume and Issue: 471, P. 06014 - 06014

Published: Jan. 1, 2024

This article examines the factors that constrain spread of electric vehicles in cold regions. An analysis main reasons restraining regions is carried out, including limited battery life, risks breakdown temperatures, and underdeveloped infrastructure. Promising research paths aimed at increasing attractiveness for users living have been identified. Results Factor Study Those restrain can be used to develop environmental programs residents regions, as well conduct adapting operation

Language: Английский

---

Development of service infrastructure for private motor boats in the northern regions

E3S Web of Conferences, Journal Year: 2024, Volume and Issue: 471, P. 01001 - 01001

Published: Jan. 1, 2024

This article examines the current trends in development of infrastructure for maintenance and repair private motor boats northern regions (on example Republic Sakha (Yakutia)). A survey boat owners three different groups was conducted. The data provide on most relevant areas region. Results study Repair can be used programs water transport infrastructure, by manufacturers boats, as well conducting new research this area.

Language: Английский

---

Towards sustainable industry 4.0: A survey on greening IoE in 6G networks

Ad Hoc Networks, Journal Year: 2024, Volume and Issue: 165, P. 103610 - 103610

Published: Aug. 30, 2024

Language: Английский

---

Explainable Federated Medical Image Analysis Through Causal Learning and Blockchain

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2024, Volume and Issue: 28(6), P. 3206 - 3218

Published: March 18, 2024

Federated learning (FL) enables collaborative training of machine models across distributed medical data sources without compromising privacy. However, applying FL to image analysis presents challenges like high communication overhead and heterogeneity. This paper proposes novel techniques using explainable artificial intelligence (XAI) for efficient, accurate, trustworthy analysis. A heterogeneity-aware causal approach selectively sparsifies model weights based on their contributions, significantly reducing requirements while retaining performance improving interpretability. Furthermore, blockchain provides decentralized quality assessment client datasets. The scores adjust aggregation so higher-quality has more influence during training, generalization. Comprehensive experiments show our XAI-integrated framework enhances efficiency, accuracy method decreases maintaining segmentation accuracy. blockchain-based valuation mitigates issues from low-quality local Our essential explanations trust mechanisms, making viable clinical adoption in

Language: Английский

---

A multifaceted survey on privacy preservation of federated learning: progress, challenges, and opportunities

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(7)

Published: June 21, 2024

Abstract Federated learning (FL) refers to a system of training and stabilizing local machine models at the global level by aggregating gradients models. It reduces concern sharing private data participating entities for statistical analysis be carried out server. allows called clients or users infer useful information from their raw data. As consequence, need share confidential with any other entity central server is eliminated. FL can clearly interpreted as privacy-preserving version traditional deep algorithms. However, despite this being an efficient distributed scheme, client’s sensitive still exposed various security threats shared parameters. Since has always been major priority user organization, article primarily concerned discussing significant problems issues relevant preservation privacy viability feasibility several proposed solutions in context. In work, we conduct detailed study on FL, categorization challenges attacks that executed disclose users’ used during learning. survey, review compare different prevent leakage discuss secret (SS)-based researchers concise form. We also briefly quantum federated (QFL) privacy-preservation techniques QFL. addition these, comparison contrast survey works included work. highlight applications based FL. certain future directions pertaining open field finally conclude our

Language: Английский

---