Personalized Federated Learning for ECG Classification Based on Feature Alignment

Electrocardiogram (ECG) data classification is a hot research area for its application in medical information processing. However, insufficient data, privacy preserve, and local deployment are still challenging difficulties. To address these problems, a novel personalized federated learning method f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Renjie Tang, Junzhou Luo, Junbo Qian, Jiahui Jin
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi-Wiley 2021
Materias:	Technology (General) T1-995 Science (General) Q1-390
Acceso en línea:	https://doaj.org/article/8e69330c85db4047abc32dd91eb31e8c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8e69330c85db4047abc32dd91eb31e8c
record_format	dspace
spelling	oai:doaj.org-article:8e69330c85db4047abc32dd91eb31e8c2021-11-15T01:19:54ZPersonalized Federated Learning for ECG Classification Based on Feature Alignment1939-012210.1155/2021/6217601https://doaj.org/article/8e69330c85db4047abc32dd91eb31e8c2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/6217601https://doaj.org/toc/1939-0122Electrocardiogram (ECG) data classification is a hot research area for its application in medical information processing. However, insufficient data, privacy preserve, and local deployment are still challenging difficulties. To address these problems, a novel personalized federated learning method for ECG classification is proposed in this paper. First, a global model is trained with federated learning framework on multiple local data clients. Then, we use the global model and private data to train the local model. To reduce the feature inconsistency between global and private local data and for better fitting the private local data, a novel ”feature alignment” module is devised to guarantee the uniformity, which contains two parts, global alignment and local alignment, respectively. For global alignment, the graph metric of batch data is used to constrain the dissimilarity between features generated by the global model and local model. For local alignment, triplet loss is adopted to increase discriminative ability for local private data. Comprehensive experiments on our collected dataset are evaluated. The results show that the proposed method can be better adapted to local data and exhibit superior ability of generalization.Renjie TangJunzhou LuoJunbo QianJiahui JinHindawi-WileyarticleTechnology (General)T1-995Science (General)Q1-390ENSecurity and Communication Networks, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Technology (General) T1-995 Science (General) Q1-390
spellingShingle	Technology (General) T1-995 Science (General) Q1-390 Renjie Tang Junzhou Luo Junbo Qian Jiahui Jin Personalized Federated Learning for ECG Classification Based on Feature Alignment
description	Electrocardiogram (ECG) data classification is a hot research area for its application in medical information processing. However, insufficient data, privacy preserve, and local deployment are still challenging difficulties. To address these problems, a novel personalized federated learning method for ECG classification is proposed in this paper. First, a global model is trained with federated learning framework on multiple local data clients. Then, we use the global model and private data to train the local model. To reduce the feature inconsistency between global and private local data and for better fitting the private local data, a novel ”feature alignment” module is devised to guarantee the uniformity, which contains two parts, global alignment and local alignment, respectively. For global alignment, the graph metric of batch data is used to constrain the dissimilarity between features generated by the global model and local model. For local alignment, triplet loss is adopted to increase discriminative ability for local private data. Comprehensive experiments on our collected dataset are evaluated. The results show that the proposed method can be better adapted to local data and exhibit superior ability of generalization.
format	article
author	Renjie Tang Junzhou Luo Junbo Qian Jiahui Jin
author_facet	Renjie Tang Junzhou Luo Junbo Qian Jiahui Jin
author_sort	Renjie Tang
title	Personalized Federated Learning for ECG Classification Based on Feature Alignment
title_short	Personalized Federated Learning for ECG Classification Based on Feature Alignment
title_full	Personalized Federated Learning for ECG Classification Based on Feature Alignment
title_fullStr	Personalized Federated Learning for ECG Classification Based on Feature Alignment
title_full_unstemmed	Personalized Federated Learning for ECG Classification Based on Feature Alignment
title_sort	personalized federated learning for ecg classification based on feature alignment
publisher	Hindawi-Wiley
publishDate	2021
url	https://doaj.org/article/8e69330c85db4047abc32dd91eb31e8c
work_keys_str_mv	AT renjietang personalizedfederatedlearningforecgclassificationbasedonfeaturealignment AT junzhouluo personalizedfederatedlearningforecgclassificationbasedonfeaturealignment AT junboqian personalizedfederatedlearningforecgclassificationbasedonfeaturealignment AT jiahuijin personalizedfederatedlearningforecgclassificationbasedonfeaturealignment
_version_	1718428935649230848

Personalized Federated Learning for ECG Classification Based on Feature Alignment

Ejemplares similares