电子学报2025，Vol.53Issue(3)：821-835,15.DOI:10.12263/DZXB.20240946
基于自适应联邦学习的环境监测群智感知算法
Adaptive Federated Learning Based Crowd Sensing Algorithm for Environmental Monitoring
摘要
Abstract
With the rapid development of industrialization and urbanization,the importance of environmental moni-toring is becoming more and more prominent.However,traditional monitoring methods are limited by high costs,difficult layout and maintenance challenges,making it difficult to achieve comprehensive and real-time monitoring.Crowd Sensing,an emerging environmental monitoring method,utilizes widely used highly intelligent devices and integrated sensors for large-scale collection and real-time transmission of environmental data.However,existing studies seldom consider data pri-vacy protection,work balance,and system cost at the same time,which makes it difficult to achieve the expected results in practical applications.To solve this practical problem,this paper proposes a low-cost and high-efficiency method that can be applied to crowd sensing for environmental monitoring(Adaptive Federated Learning based Crowd Sensing algorithm for Environmental Monitoring,AFL-CSEM).Specifically,we first consider the challenges of resource constraints,device heterogeneity,and non-independent and homogeneous distribution of data in the system,and model the system by combin-ing crowd sensing and federated learning techniques,and train the model locally on user's devices,sharing only the model parameters to effectively protect data privacy.Then,the convergence analysis of the system is carried out,and the conver-gence bounds of the crowd sending algorithm based on federated learning are obtained for non-independently and identical-ly distributed data distributions.Then,in order to reduce the impact of device heterogeneity,based on the results of the con-vergence analysis,an adaptive control method is designed to dynamically adjust the local update frequency and batch size to adapt to the heterogeneous and dynamic monitoring environment.By comparing on real datasets,all the experimental re-sults consistently prove the effectiveness of the proposed algorithm in this paper,and the AFL-CSEM algorithm improves the efficiency and accuracy of model training while reducing the computation and communication overhead and lowering the economic cost.It provides a novel and informative solution for environmental monitoring in resource-constrained edge computing environments.关键词
环境监测/群智感知/联邦学习/自适应算法/收敛性分析Key words
environmental monitoring/crowdsensing/federated learning/adaptive algorithm/convergence analysis分类
信息技术与安全科学引用本文复制引用
蒋伟进,杜熙晨,蒋意容,杨璇,聂彩燕,刘茜..基于自适应联邦学习的环境监测群智感知算法[J].电子学报,2025,53(3):821-835,15.基金项目
国家自然科学基金(No.61772196) （No.61772196）
湖南省自然科学基金(No.2020JJ4249) （No.2020JJ4249）
湖南省社会科学成果评审委员会课题重点项目(No.XSP19ZD1005) （No.XSP19ZD1005）
湖南省教育厅科学研究重点项目(No.21A0374) （No.21A0374）
长沙市哲学社会科学规划课题(No.2024CSSKKT31) National Natural Science Foundation Basic Science Center Project(No.61772196) （No.2024CSSKKT31）
Hunan Pro-vincial Natural Science Foundation(No.2020JJ4249) （No.2020JJ4249）
Key Project of Hunan Provincial Social Science Achievement Review Committee Subjects(No.XSP19ZD1005) （No.XSP19ZD1005）
Key Project of Hunan Provincial Department of Education for Science and Tech-nology Research(No.21A0374) （No.21A0374）
Philosophy and Social Sciences Planning Project of Changsha City(No.2024CSSKKT31) （No.2024CSSKKT31）
