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

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...

Full description

Bibliographic Details
Authors: Baghersalimi, S., Teijeiro, T., Aminifar, A., Atienza, D.
Format: article
Status:Versión aceptada para publicación
Publication Date:2023
Country:España
Institution:Basque Center for Applied Mathematics (BCAM)
Repository:BIRD. BCAM's Institutional Repository Data
OAI Identifier:oai:bird.bcamath.org:20.500.11824/1712
Online Access:http://hdl.handle.net/20.500.11824/1712
Access Level:Open access
Keyword:Brain modeling
Data models
Deep learning
Electrocardiogram
Electrocardiography
Electroencephalography
Epilepsy
Federated Learning
Hospitals
Knowledge distillation
Multi-biosignal processing
Seizure detection
Servers
Training
Wearable systems
id ES_04ccee88719b0f527269d2e5e66ad33c
oai_identifier_str oai:bird.bcamath.org:20.500.11824/1712
network_acronym_str ES
network_name_str España
repository_id_str
spelling Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable SystemsBaghersalimi, S.Teijeiro, T.Aminifar, A.Atienza, D.Brain modelingData modelsDeep learningElectrocardiogramElectrocardiographyElectroencephalographyEpilepsyFederated LearningHospitalsKnowledge distillationMulti-biosignal processingSeizure detectionServersTrainingWearable systemsIn 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.RYC2021-032853-I202320232023info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfhttp://hdl.handle.net/20.500.11824/1712reponame:BIRD. BCAM's Institutional Repository Datainstname:Basque Center for Applied Mathematics (BCAM)InglésReconocimiento-NoComercial-CompartirIgual 3.0 Españahttp://creativecommons.org/licenses/by-nc-sa/3.0/es/info:eu-repo/semantics/openAccessoai:bird.bcamath.org:20.500.11824/17122026-06-19T12:47:47Z
dc.title.none.fl_str_mv Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems
title Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems
spellingShingle Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems
Baghersalimi, S.
Brain modeling
Data models
Deep learning
Electrocardiogram
Electrocardiography
Electroencephalography
Epilepsy
Federated Learning
Hospitals
Knowledge distillation
Multi-biosignal processing
Seizure detection
Servers
Training
Wearable systems
title_short Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems
title_full Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems
title_fullStr Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems
title_full_unstemmed Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems
title_sort Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems
dc.creator.none.fl_str_mv Baghersalimi, S.
Teijeiro, T.
Aminifar, A.
Atienza, D.
author Baghersalimi, S.
author_facet Baghersalimi, S.
Teijeiro, T.
Aminifar, A.
Atienza, D.
author_role author
author2 Teijeiro, T.
Aminifar, A.
Atienza, D.
author2_role author
author
author
dc.subject.none.fl_str_mv Brain modeling
Data models
Deep learning
Electrocardiogram
Electrocardiography
Electroencephalography
Epilepsy
Federated Learning
Hospitals
Knowledge distillation
Multi-biosignal processing
Seizure detection
Servers
Training
Wearable systems
topic Brain modeling
Data models
Deep learning
Electrocardiogram
Electrocardiography
Electroencephalography
Epilepsy
Federated Learning
Hospitals
Knowledge distillation
Multi-biosignal processing
Seizure detection
Servers
Training
Wearable systems
description 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.
publishDate 2023
dc.date.none.fl_str_mv 2023
2023
2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/20.500.11824/1712
url http://hdl.handle.net/20.500.11824/1712
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv Reconocimiento-NoComercial-CompartirIgual 3.0 España
http://creativecommons.org/licenses/by-nc-sa/3.0/es/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Reconocimiento-NoComercial-CompartirIgual 3.0 España
http://creativecommons.org/licenses/by-nc-sa/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:BIRD. BCAM's Institutional Repository Data
instname:Basque Center for Applied Mathematics (BCAM)
instname_str Basque Center for Applied Mathematics (BCAM)
reponame_str BIRD. BCAM's Institutional Repository Data
collection BIRD. BCAM's Institutional Repository Data
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869402815820988416
score 15,198674

Similar Items