FedDSHAR: A dual-strategy federated learning approach for human activity recognition amid noise label user

doi:10.1016/j.future.2025.107724

	FedDSHAR: A dual-strategy federated learning approach for human activity recognition amid noise label user
	Lin, Ziqian 1; Jiang, Xuefeng 2; Zhang, Kun 3; Fan, Chongjun 1; Liu, Yaya 1
	2025-05-01
发表期刊	FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
ISSN	0167-739X
卷号	166 页码:11
摘要	Federated learning (FL) has recently achieved successes in privacy-sensitive health-care applications like medical analysis. Most previous studies suppose that collected user data are well-annotated, however, it a strong assumption in practice. For instance, human activity recognition (HAR) task aims to train a model which predicts a certain person's activity based on sensor data series collected from a given period of time. Due to diverse and incomplete annotation approaches, user-side data inevitably contain significant label noise, which greatly degrade model convergence and performance. In this work, we propose a novel FL framework FedDSHAR, which partitions the user-side data into the clean data subset and noisy data subset. Two strategies are utilized on two subsets to further exploit extra effective information from data, where strategic time-series augmentation is adopted on the clean subset and the semi-supervised learning scheme is used for the noisy subset. Extensive experiments conducted on three public real-world HAR datasets demonstrate that FedDSHAR outperforms six state-of-the-art methods, particularly in addressing extreme label noise in real-world distributed noisy HAR scenarios. Our code is available at https://github.com/coke2020ice/FedDSHAR.
关键词	Human activity recognition Federated learning Label noise Data augmentation
DOI	10.1016/j.future.2025.107724
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62006154]
WOS研究方向	Computer Science
WOS类目	Computer Science, Theory & Methods
WOS记录号	WOS:001422274200001
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40729
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Fan, Chongjun
作者单位	1.Univ Shanghai Sci & Technol, Business Sch, Shanghai 200093, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 101408, Peoples R China 3.Shanghai Univ Finance & Econ, Sch Informat Management & Engn, Shanghai 210023, Peoples R China
推荐引用方式 GB/T 7714	Lin, Ziqian,Jiang, Xuefeng,Zhang, Kun,et al. FedDSHAR: A dual-strategy federated learning approach for human activity recognition amid noise label user[J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE,2025,166:11.
APA	Lin, Ziqian,Jiang, Xuefeng,Zhang, Kun,Fan, Chongjun,&Liu, Yaya.(2025).FedDSHAR: A dual-strategy federated learning approach for human activity recognition amid noise label user.FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE,166,11.
MLA	Lin, Ziqian,et al."FedDSHAR: A dual-strategy federated learning approach for human activity recognition amid noise label user".FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 166(2025):11.