Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems

Baghersalimi, Saleh ; Teijeiro, Tomas ; Aminifar, Amir LU orcid and Atienza, David (2023) In IEEE Transactions on Mobile Computing p.1-16
Abstract

In healthcare, data privacy of patients regulations prohibits data from being moved outside the hospital, preventing international medical datasets from being centralized for AI training. Federated learning (FL) is a data privacy-focused method that trains a global model by aggregating local models from hospitals. Existing FL techniques adopt a central server-based network topology, where the server assembles the local models trained in each hospital to create a global model. However, the server could be a point of failure, and models trained in FL usually have worse performance than those trained in the centralized learning manner when the patient's data are not independent and identically distributed (Non-IID) in the... (More)

In healthcare, data privacy of patients regulations prohibits data from being moved outside the hospital, preventing international medical datasets from being centralized for AI training. Federated learning (FL) is a data privacy-focused method that trains a global model by aggregating local models from hospitals. Existing FL techniques adopt a central server-based network topology, where the server assembles the local models trained in each hospital to create a global model. However, the server could be a point of failure, and models trained in FL usually have worse performance than those trained in the centralized learning manner when the patient's data are not independent and identically distributed (Non-IID) in the hospitals. This paper presents a decentralized FL framework, including training with adaptive ensemble learning and a deployment phase using knowledge distillation. The adaptive ensemble learning step in the training phase leads to the acquisition of a specific model for each hospital that is the optimal combination of local models and models from other available hospitals. This step solves the non-IID challenges in each hospital. The deployment phase adjusts the model's complexity to meet the resource constraints of wearable systems. We evaluated the performance of our approach on edge computing platforms using EPILEPSIAE and TUSZ databases, which are public epilepsy datasets.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Contribution to journal
publication status
in press
subject
keywords
Brain modeling, Data models, Deep learning, Electrocardiogram, Electrocardiography, Electroencephalography, Epilepsy, Federated Learning, Hospitals, Knowledge distillation, Multi-biosignal processing, Seizure detection, Servers, Training, Wearable systems
in
IEEE Transactions on Mobile Computing
pages
16 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • scopus:85173362049
ISSN
1536-1233
DOI
10.1109/TMC.2023.3320862
language
English
LU publication?
yes
id
dfa00e67-b9b4-475c-b673-0f7467c02374
date added to LUP
2023-12-19 15:46:55
date last changed
2023-12-19 15:49:03
@article{dfa00e67-b9b4-475c-b673-0f7467c02374,
  abstract     = {{<p>In healthcare, data privacy of patients regulations prohibits data from being moved outside the hospital, preventing international medical datasets from being centralized for AI training. Federated learning (FL) is a data privacy-focused method that trains a global model by aggregating local models from hospitals. Existing FL techniques adopt a central server-based network topology, where the server assembles the local models trained in each hospital to create a global model. However, the server could be a point of failure, and models trained in FL usually have worse performance than those trained in the centralized learning manner when the patient&amp;#x0027;s data are not independent and identically distributed (Non-IID) in the hospitals. This paper presents a decentralized FL framework, including training with adaptive ensemble learning and a deployment phase using knowledge distillation. The adaptive ensemble learning step in the training phase leads to the acquisition of a specific model for each hospital that is the optimal combination of local models and models from other available hospitals. This step solves the non-IID challenges in each hospital. The deployment phase adjusts the model&amp;#x0027;s complexity to meet the resource constraints of wearable systems. We evaluated the performance of our approach on edge computing platforms using EPILEPSIAE and TUSZ databases, which are public epilepsy datasets.</p>}},
  author       = {{Baghersalimi, Saleh and Teijeiro, Tomas and Aminifar, Amir and Atienza, David}},
  issn         = {{1536-1233}},
  keywords     = {{Brain modeling; Data models; Deep learning; Electrocardiogram; Electrocardiography; Electroencephalography; Epilepsy; Federated Learning; Hospitals; Knowledge distillation; Multi-biosignal processing; Seizure detection; Servers; Training; Wearable systems}},
  language     = {{eng}},
  pages        = {{1--16}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Transactions on Mobile Computing}},
  title        = {{Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems}},
  url          = {{http://dx.doi.org/10.1109/TMC.2023.3320862}},
  doi          = {{10.1109/TMC.2023.3320862}},
  year         = {{2023}},
}