In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 3

Method for dynamic node selection and resource allocation in federated learning for smart healthcare

Liu Yufeng1
Li Han1
Wu Qiuxin1
Wang Can1
Qin Yu2
Yang Pengfei1
1. School of Applied Science, Beijing Information Science and Technology University, Beijing 102206, China
2. Trusted Computing and Information Assurance Laboratory, Institute of Software, Chinese Academy of Science, Beijing 100190, China
DOI: 10.19734/j.issn.1001-3695.2025.06.0266

Abstract

Applying federated learning to Wireless Body Area Network (WBAN) can address privacy protection issues, but still faces challenges such as decreased global model accuracy and high energy consumption. This paper proposed a federated learning system model for smart healthcare, construct energy consumption model for each WBAN node participating in federated learning, and analyze its data and resource characteristics. To protect data privacy and avoid accessing raw data, the Kullback-Leibler (KL) divergence was introduced to represent the statistical heterogeneity of each node, and channel gain, bandwidth and other indicators were used to represent the system heterogeneity of each node. This paper proposed a federated learning dynamic node selection and resource allocation method combining SAC (Soft Actor Critic) algorithm. Before each round of federated learning training begins, the SAC algorithm dynamically selects participating nodes, allocates local computing and communication resources based on the data and resource characteristics uploaded by WBAN nodes, and solves the problems of global model accuracy decline and high energy consumption caused by statistical heterogeneity and system heterogeneity of WBAN nodes. Experiments were conducted on CIFAR10, FashionMNIST, and PathMNIST datasets. The experimental results show that compared with FedAvg, FAVOR, and FLASH-RL algorithms, the proposed method can improve global model accuracy by up to 20%, reduce energy consumption by 50%, and accelerate global model convergence speed while reducing accuracy fluctuations, demonstrating the effectiveness of the proposed approach.

Foundation Support

国家自然科学基金资助项目(61604014)
北京信息科技大学"勤信人才"培育计划(QXTCPB202409)
北京信息科技大学"青年骨干教师"支持计划(YBT202450)
未来区块链与隐私计算高精尖创新中心建设资助项目

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.06.0266
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 3

Publish History

[2025-11-18] Accepted Paper

Cite This Article

刘玉峰, 李涵, 吴秋新, 等. 面向智慧医疗的联邦学习动态节点选择和资源分配方法 [J]. 计算机应用研究, 2026, 43 (3). (2025-11-18). https://doi.org/10.19734/j.issn.1001-3695.2025.06.0266. (Liu Yufeng, Li Han, Wu Qiuxin, et al. Method for dynamic node selection and resource allocation in federated learning for smart healthcare [J]. Application Research of Computers, 2026, 43 (3). (2025-11-18). https://doi.org/10.19734/j.issn.1001-3695.2025.06.0266. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)