用于人体活动识别的基于对比学习与自适应变量控制的联邦模型

Ignatius IWAN; Bernardo Nugroho YAHYA; Seok-Lyong LEE

doi:10.1631/FITEE.2400797

Your Location：

Home >

Browse articles >

用于人体活动识别的基于对比学习与自适应变量控制的联邦模型

常规文章 | Updated：2025-07-02

- 用于人体活动识别的基于对比学习与自适应变量控制的联邦模型
  Enhanced Publication
- Federated model with contrastive learning and adaptive control variates for human activity recognition
- “在人类活动识别领域，研究人员引入了FedCoad，这是一种新型的联邦学习模型，它利用具有自适应控制变量的对比学习来解决客户端之间的数据偏斜问题，增强了模型收敛性，并在HAR基准数据集上优于最先进的FL算法。”
- 信息与电子工程前沿(英文版) 2025年26卷第6期页码：896-911
- Affiliations：
  
  Department of Industrial and Management Engineering, Hankuk University of Foreign Studies, Yongin 17035, Republic of Korea
- Author bio：
  
  E-mail: ignatiusiwan@hufs.ac.kr
  ‡ Corresponding author
  sllee@hufs.ac.kr
- Funds：
  
  the Hankuk University of Foreign Studies Research Fund(2025-01);the International Cooperative R&D Program of Ministry of Trade, Industry and Energy (MOTIE) and Korea Institute for Advancement of Technology (KIAT)(P0022316)
- DOI：10.1631/FITEE.2400797
  中图分类号： TP391
- 收稿日期：2024-09-13，
  
  修回日期：2025-01-08，
  
  纸质出版日期：2025-06
- Accepted：
Scan QR Code
Ignatius IWAN, Bernardo Nugroho YAHYA, Seok-Lyong LEE. 用于人体活动识别的基于对比学习与自适应变量控制的联邦模型[J]. 信息与电子工程前沿(英文版), 2025,26(6):896-911.

Ignatius IWAN, Bernardo Nugroho YAHYA, Seok-Lyong LEE. Federated model with contrastive learning and adaptive control variates for human activity recognition[J]. Frontiers of information technology & electronic engineering, 2025, 26(6): 896-911.
Ignatius IWAN, Bernardo Nugroho YAHYA, Seok-Lyong LEE. 用于人体活动识别的基于对比学习与自适应变量控制的联邦模型[J]. 信息与电子工程前沿(英文版), 2025,26(6):896-911. DOI： 10.1631/FITEE.2400797.

Ignatius IWAN, Bernardo Nugroho YAHYA, Seok-Lyong LEE. Federated model with contrastive learning and adaptive control variates for human activity recognition[J]. Frontiers of information technology & electronic engineering, 2025, 26(6): 896-911. DOI： 10.1631/FITEE.2400797.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

A comprehensive survey of physical adversarial vulnerabilities in autonomous driving systems

Automatic parallelism strategy generation with minimal memory redundancy

Visual knowledge in the big model era: retrospect and prospect

Quant 4.0: engineering quantitative investment with automated, explainable, and knowledge-driven artificial intelligence

Toward an accurate mobility trajectory recovery using contrastive learning

用于人体活动识别的基于对比学习与自适应变量控制的联邦模型

Federated model with contrastive learning and adaptive control variates for human activity recognition

DOI：10.1631/FITEE.2400797