Application Domains of Federated Learning in Healthcare 5.0 DOI
T. Ananth Kumar,

A. Gokulalakshmi,

P. Kanimozhi

et al.

Advances in healthcare information systems and administration book series, Journal Year: 2023, Volume and Issue: unknown, P. 321 - 338

Published: Dec. 18, 2023

Federated learning has emerged as a game-changing approach in machine learning, allowing high-quality centralised models to be trained across network of decentralised clients. Learning is defined by the collaborative process that involves large number customers, each whom contributes insights from their localised datasets. This critical cases where data privacy and constraints are critical. research focuses on unique algorithms built for this situation. Individual clients autonomously compute model changes based local at iteration, then communicate these modifications central server. These client-side updates subsequently aggregated server, resulting construction an updated global model. The challenge situation train efficiently while dealing with who have inconsistent slow connections.

Language: Английский

Enhancing Cybersecurity Through Federated Learning: A Critical Evaluation of Strategies and Implications DOI

M. Ashok Kumar,

Aliyu Mohammed,

S Sumanth

et al.

Published: Nov. 22, 2024

Language: Английский

Citations

0
Federated Learning: Introduction, Evolution, Working, Advantages, and Its Application in Various Domains DOI
Manoj Kumar Pandey,

Naresh Kumar Kar,

Priyanka Gupta

et al.

Published: Nov. 22, 2024

Language: Английский

Citations

0
Privacy-Preserving Federated Learning for Healthcare Data DOI

S. Sangeetha

Advances in information security, privacy, and ethics book series, Journal Year: 2023, Volume and Issue: unknown, P. 178 - 196

Published: Oct. 25, 2023

The evolution of technology has a significant impact on health data collection, transforming the way information is gathered, stored, and utilized in healthcare industry. big record contains sensitive user like contact details, status, demographics, vaccination exposure history. It's worth noting that while collection records been crucial for monitoring patients' history, it also raises important privacy security considerations. Safeguarding individuals' ensuring compliance with relevant regulations essential to maintain public trust protect information. Therefore, must adhere ethical This chapter elaborates key challenges solutions preservation within federated learning. include heterogeneity, leakage, attacks, regulatory compliances.

Language: Английский

Citations

0
Application Domains of Federated Learning in Healthcare 5.0 DOI
T. Ananth Kumar,

A. Gokulalakshmi,

P. Kanimozhi

et al.

Advances in healthcare information systems and administration book series, Journal Year: 2023, Volume and Issue: unknown, P. 321 - 338

Published: Dec. 18, 2023

Federated learning has emerged as a game-changing approach in machine learning, allowing high-quality centralised models to be trained across network of decentralised clients. Learning is defined by the collaborative process that involves large number customers, each whom contributes insights from their localised datasets. This critical cases where data privacy and constraints are critical. research focuses on unique algorithms built for this situation. Individual clients autonomously compute model changes based local at iteration, then communicate these modifications central server. These client-side updates subsequently aggregated server, resulting construction an updated global model. The challenge situation train efficiently while dealing with who have inconsistent slow connections.

Language: Английский

Citations

0