Privacy-preserving edge federated learning for intelligent mobile-health systems
Aminifar, Amin ; Shokri, Matin and Aminifar, Amir LU
(2024)
In Future Generation Computer Systems
161.
p.625-637
- Abstract
Machine Learning (ML) algorithms are generally designed for scenarios in which all data is stored in one data center, where the training is performed. However, in many applications, e.g., in the healthcare domain, the training data is distributed among several entities, e.g., different hospitals or patients’ mobile devices/sensors. At the same time, transferring the data to a central location for learning is certainly not an option, due to privacy concerns and legal issues, and in certain cases, because of the communication and computation overheads. Federated Learning (FL) is the state-of-the-art collaborative ML approach for training an ML model across multiple parties holding local data samples, without sharing them. However,... (More)
Machine Learning (ML) algorithms are generally designed for scenarios in which all data is stored in one data center, where the training is performed. However, in many applications, e.g., in the healthcare domain, the training data is distributed among several entities, e.g., different hospitals or patients’ mobile devices/sensors. At the same time, transferring the data to a central location for learning is certainly not an option, due to privacy concerns and legal issues, and in certain cases, because of the communication and computation overheads. Federated Learning (FL) is the state-of-the-art collaborative ML approach for training an ML model across multiple parties holding local data samples, without sharing them. However, enabling learning from distributed data over such edge Internet of Things (IoT) systems (e.g., mobile-health and wearable technologies, involving sensitive personal/medical data) in a privacy-preserving fashion presents a major challenge mainly due to their stringent resource constraints, i.e., limited computing capacity, communication bandwidth, memory storage, and battery lifetime. In this paper, we propose a privacy-preserving edge FL framework for resource-constrained mobile-health and wearable technologies over the IoT infrastructure. We evaluate our proposed framework extensively and provide the implementation of our technique on Amazon's AWS cloud platform based on the seizure detection application in epilepsy monitoring using wearable technologies.
(Less)
- author
- Aminifar, Amin
; Shokri, Matin
and Aminifar, Amir
LU
- organization
- publishing date
- 2024-12
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Edge federated learning, Mobile-health technologies, Privacy-preserving machine learning
- in
- Future Generation Computer Systems
- volume
- 161
- pages
- 13 pages
- publisher
- Elsevier
- external identifiers
-
- scopus:85200898761
- ISSN
- 0167-739X
- DOI
- 10.1016/j.future.2024.07.035
- language
- English
- LU publication?
- yes
- id
- 8363a505-369a-4300-8e4c-dd9042e74262
- date added to LUP
- 2024-08-30 14:53:32
- date last changed
- 2024-08-30 14:58:21
@article{8363a505-369a-4300-8e4c-dd9042e74262,
abstract = {{<p>Machine Learning (ML) algorithms are generally designed for scenarios in which all data is stored in one data center, where the training is performed. However, in many applications, e.g., in the healthcare domain, the training data is distributed among several entities, e.g., different hospitals or patients’ mobile devices/sensors. At the same time, transferring the data to a central location for learning is certainly not an option, due to privacy concerns and legal issues, and in certain cases, because of the communication and computation overheads. Federated Learning (FL) is the state-of-the-art collaborative ML approach for training an ML model across multiple parties holding local data samples, without sharing them. However, enabling learning from distributed data over such edge Internet of Things (IoT) systems (e.g., mobile-health and wearable technologies, involving sensitive personal/medical data) in a privacy-preserving fashion presents a major challenge mainly due to their stringent resource constraints, i.e., limited computing capacity, communication bandwidth, memory storage, and battery lifetime. In this paper, we propose a privacy-preserving edge FL framework for resource-constrained mobile-health and wearable technologies over the IoT infrastructure. We evaluate our proposed framework extensively and provide the implementation of our technique on Amazon's AWS cloud platform based on the seizure detection application in epilepsy monitoring using wearable technologies.</p>}},
author = {{Aminifar, Amin and Shokri, Matin and Aminifar, Amir}},
issn = {{0167-739X}},
keywords = {{Edge federated learning; Mobile-health technologies; Privacy-preserving machine learning}},
language = {{eng}},
pages = {{625--637}},
publisher = {{Elsevier}},
series = {{Future Generation Computer Systems}},
title = {{Privacy-preserving edge federated learning for intelligent mobile-health systems}},
url = {{http://dx.doi.org/10.1016/j.future.2024.07.035}},
doi = {{10.1016/j.future.2024.07.035}},
volume = {{161}},
year = {{2024}},
}