Asynchronous Federated Learning for Personalized Healthcare: Enhancing Privacy and Efficiency through Machine Learning and Computer Networking Integration

de Sousa Pacheco, Lucas; Braun, Torsten (5 May 2023). Asynchronous Federated Learning for Personalized Healthcare: Enhancing Privacy and Efficiency through Machine Learning and Computer Networking Integration. In: Bern Data Science Day. Data Science Lab: University of Bern

[img]
Preview
Text (Poster Presentation)
BDSD_2023_Lucas__1_.pdf - Presentation
Available under License BORIS Standard License.

Download (1MB) | Preview

This poster presents a novel privacy-preserving federated learning algorithm, called Privacy-Preserving Asynchronous Federated Learning (PPAFL), tailored for personalized healthcare applications. The algorithm integrates machine learning advancements and computer networking techniques to address data privacy and communication overhead challenges. Real-world health datasets are used for evaluating the algorithm's effectiveness and scalability. The results show that PPAFL has significant implications for personalized healthcare, bridging machine learning and computer networking to enable effective collaboration while preserving data privacy. This research has the potential to revolutionize data-driven decision-making in healthcare, leading to improved patient outcomes and quality of care. Future work includes the development of advanced privacy-preserving techniques, communication-efficient algorithms, and adaptive learning strategies to further enhance the algorithm's capabilities and generalizability.

Item Type:

Conference or Workshop Item (Poster)

Division/Institute:

08 Faculty of Science > Institute of Computer Science (INF)
08 Faculty of Science > Institute of Computer Science (INF) > Communication and Distributed Systems (CDS)

UniBE Contributor:

De Sousa Pacheco, Lucas, Braun, Torsten

Subjects:

000 Computer science, knowledge & systems
500 Science > 510 Mathematics

Publisher:

University of Bern

Language:

English

Submitter:

Dimitrios Xenakis

Date Deposited:

13 Jul 2023 14:27

Last Modified:

28 Aug 2023 15:56

Related URLs:

BORIS DOI:

10.48350/184751

URI:

https://boris.unibe.ch/id/eprint/184751

Actions (login required)

Edit item Edit item
Provide Feedback