Adaptive Federated Learning Based Crowd Sensing Algorithm for Environmental Monitoring

JIANG Wei-jin; DU Xi-chen; JIANG Yi-rong; YANG Xuan; NIE Cai-yan; LIU Qian

doi:10.12263/DZXB.20240946

您当前的位置：

首页 >

文章列表页 >

Adaptive Federated Learning Based Crowd Sensing Algorithm for Environmental Monitoring

PAPERS | 更新时间：2025-12-08

- Adaptive Federated Learning Based Crowd Sensing Algorithm for Environmental Monitoring
- ACTA ELECTRONICA SINICA Vol. 53, Issue 3, Pages: 821-835(2025)
- 作者机构：
  
  1.湖南工商大学计算机学院，湖南长沙 410205
  2.湘江实验室，湖南长沙 410205
  3.湖南工商大学前沿交叉学院，湖南长沙 410205
  4.湖南信息学院，湖南长沙 410151
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation Basic Science Center Project(61772196);Hunan Provincial Natural Science Foundation(2020JJ4249);Key Project of Hunan Provincial Social Science Achievement Review Committee Subjects(XSP19ZD1005);Key Project of Hunan Provincial Department of Education for Science and Technology Research(21A0374);Philosophy and Social Sciences Planning Project of Changsha City(2024CSSKKT31)
- DOI：10.12263/DZXB.20240946
  CLC： TP301;X328
- Received：17 October 2024，
  
  Revised：2025-01-27，
  
  Published：25 March 2025
- 稿件说明：
移动端阅览
蒋伟进, 杜熙晨, 蒋意容, 等. 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(03): 821-835.

JIANG Wei-jin, DU Xi-chen, JIANG Yi-rong, et al. Adaptive Federated Learning Based Crowd Sensing Algorithm for Environmental Monitoring[J]. Acta Electronica Sinica, 2025, 53(03): 821-835.
蒋伟进, 杜熙晨, 蒋意容, 等. 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(03): 821-835. DOI：10.12263/DZXB.20240946

JIANG Wei-jin, DU Xi-chen, JIANG Yi-rong, et al. Adaptive Federated Learning Based Crowd Sensing Algorithm for Environmental Monitoring[J]. Acta Electronica Sinica, 2025, 53(03): 821-835. DOI：10.12263/DZXB.20240946

摘要

随着工业化和城市化的快速发展，环境监测的重要性日益凸显，然而传统监测方法受限于高昂成本、布局困难和维护挑战，难以实现全面和实时的监测.群智感知作为一种新兴的环境监测方法，利用广泛使用的高度智能设备和集成传感器进行环境数据的大规模收集和实时传输.但现有研究很少同时考虑到数据隐私保护、工作平衡以及系统成本，导致在实际应用中难以达到预期效果.为解决这一问题，本文提出一种能适用于环境监测群智感知的低成本、高效率方法（Adaptive Federated Learning based Crowd Sensing algorithm for Environmental Monitoring，AFL-CSEM）.具体而言，考虑系统中的资源限制、设备异构性和数据非独立同分布等挑战，本文结合群智感知与联邦学习技术进行了系统建模，在用户设备上进行本地模型训练，仅共享模型参数，有效保护数据隐私；进行系统的收敛性分析，得到基于联邦学习的群智感知算法在非独立同分布数据分布下的收敛界限；为了减少设备异构性影响，依据收敛性分析的结果，设计一种自适应控制方法，动态调整局部更新频率和批大小，以适应异构与动态的监测环境.通过在真实数据集上的比较，所有实验结果一致证明了本文所提出算法的有效性，AFL-CSEM算法在减少计算和通信开销、降低经济成本的同时，提升了模型训练的效率与精度，为环境监测领域的群智感知提供了一种新颖且具有参考价值的解决方案.

Abstract

With the rapid development of industrialization and urbanization

the importance of environmental monitoring 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 privacy 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 combining 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 convergence bounds of the crowd sending algorithm based on federated learning are obtained for non-independently and identically distributed data distributions. Then

in order to reduce the impact of device heterogeneity

based on the results of the convergence 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 results 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

Keywords

references

MAMUN M A AL , YUCE M R . Sensors and systems for wearable environmental monitoring toward IoT-enabled applications: A review [J ] . IEEE Sensors Journal , 2019 , 19 ( 18 ): 7771 - 7788 .

SUHAG D , JHA V . A comprehensive survey on mobile crowdsensing systems [J ] . Journal of Systems Architecture , 2023 , 142 : 102952 .

ANTONIĆ A , BILAS V , MARJANOVIĆ M , et al . Urban crowd sensing demonstrator: Sense the Zagreb air [C ] // 2014 22nd International Conference on Software, Telecommunications and Computer Networks (SoftCOM) . Piscataway : IEEE , 2014 : 423 - 424 .

JIANG Z H , ZHU H , ZHOU B B , et al . CrowdPatrol: A mobile crowdsensing framework for traffic violation hotspot patrolling [J ] . IEEE Transactions on Mobile Computing , 2021 , 22 ( 3 ): 1401 - 1416 .

SIVAGNANASUNDARAM J , GINIGE A , GOONETILLAKE J . Farmers as sensors: A crowdsensing platform to generate agricultural pest incidence reports [C ] // 2019 International Conference on Internet of Things Research and Practice (iCIOTRP) . Piscataway : IEEE , 2019 : 13 - 18 .

RASHID M T , WANG D . CovidSens: A vision on reliable social sensing for COVID-19 [J ] . Artificial Intelligence Review , 2021 , 54 ( 1 ): 1 - 25 .

GUO B , WANG Z , YU Z W , et al . Mobile crowd sensing and computing: The review of an emerging human-powered sensing paradigm [J ] . ACM Computing Surveys , 2015 , 48 ( 1 ): 1 - 31 .

YAN X F , NG W W Y , ZENG B , et al . P2SIM: Privacy-preserving and source-reliable incentive mechanism for mobile crowdsensing [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 24 ): 25424 - 25437 .

LUO Z Y , XU J , ZHAO P C , et al . Towards high quality mobile crowdsensing: Incentive mechanism design based on fine-grained ability reputation [J ] . Computer Communications , 2021 , 180 : 197 - 209 .

MCMAHAN H B , MOORE E , RAMAGE D , et al . Communication-efficient learning of deep networks from decentralized data [EB/OL ] . ( 2016-02-17 )[ 2024-10-16 ] . https://arxiv.org/abs/1602.05629v4 https://arxiv.org/abs/1602.05629v4 .

MOTHUKURI V , PARIZI R M , POURIYEH S , et al . A survey on security and privacy of federated learning [J ] . Future Generation Computer Systems , 2021 , 115 : 619 - 640 .

ZHANG Z X , CHEN G , XU Y J , et al . FedDQA: A novel regularization-based deep learning method for data quality assessment in federated learning [J ] . Decision Support Systems , 2024 , 180 : 114183 .

ZHAN Y F , LI P , GUO S , et al . Incentive mechanism design for federated learning: Challenges and opportunities [J ] . IEEE Network , 2021 , 35 ( 4 ): 310 - 317 .

WANG K I , ZHOU X K , LIANG W , et al . Federated transfer learning based cross-domain prediction for smart manufacturing [J ] . IEEE Transactions on Industrial Informatics , 2022 , 18 ( 6 ): 4088 - 4096 .

JIANG W J , CHEN J P , LIU X L , et al . Participant recruitment method aiming at service quality in mobile crowd sensing [J ] . Wireless Communications and Mobile Computing , 2021 , 2021 ( 1 ): 6621659 .

FASCISTA A . Toward integrated large-scale environmental monitoring using WSN/UAV/crowdsensing: A review of applications, signal processing, and future perspectives [J ] . Sensors , 2022 , 22 ( 5 ): 1824 .

JIANG W J , ZHANG W Q , CHEN P P , et al . Quantity sensitive task allocation based on improved whale optimization algorithm in crowdsensing system [J ] . Concurrency and Computation: Practice and Experience , 2023 , 35 ( 20 ): e6637 .

BIAN J , XIONG H Y , WANG Z Y , et al . Aggregation-free spatial-temporal mobile community sensing [J ] . IEEE Transactions on Mobile Computing , 2023 , 22 ( 9 ): 5017 - 5034 .

MORSELLI F , ZABINI F , CONTI A . Environmental monitoring via vehicular crowdsensing [C ] // 2018 IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) . Piscataway : IEEE , 2018 : 1382 - 1387 .

ZHANG Q , WANG T C , TAO Y , et al . Trajectory privacy protection method based on differential privacy in crowdsensing [J ] . IEEE Transactions on Services Computing , 2024 , 17 ( 6 ): 4423 - 4435 .

TONG F , ZHOU Y H , WANG K M , et al . A privacy-preserving incentive mechanism for mobile crowdsensing based on blockchain [J ] . IEEE Transactions on Dependable and Secure Computing , 2024 , 21 ( 6 ): 5071 - 5085 .

LUO B , YU Y , JIANG Z L , et al . Crowd-BT: A bilateral trustworthy ensured scheme for blockchain assisted mobile crowdsensing [J ] . IEEE Internet of Things Journal , 2024 , 99 : 1 .

MONTASER N A RAMADAN A , MOHAMMED A H ALI A , SHIN YEE KHOO A B , et al . SecureIoT-FL: A federated learning framework for privacy-preserving real-time environmental monitoring in industrial IoT applications [J ] . Alexandria Engineering Journal , 2025 , 114 : 681 - 701 .

马华东 , 赵东 , 王新兵 , 等 . 一种新型群智感知系统架构模型和实现方法 [J ] . 中国科学: 信息科学 , 2023 , 53 ( 7 ): 1262 - 1280 .

MA H D , ZHAO D , WANG X B , et al . A novel crowdsensing system architecture model and its implementation methods [J ] . Scientia Sinica (Informationis) , 2023 , 53 ( 7 ): 1262 - 1280 . (in Chinese)

XIE X , BAI T , GUO W W , et al . Cooperative computing for mobile crowdsensing: Design and optimization [J ] . IEEE Transactions on Mobile Computing , 2023 , 23 ( 5 ): 6437 - 6454 .

PICAUT J , FORTIN N , BOCHER E , et al . An open-science crowdsourcing approach for producing community noise maps using smartphones [J ] . Building and Environment , 2019 , 148 : 20 - 33 .

HU Q , WANG Z L , XU M H , et al . Blockchain and federated edge learning for privacy-preserving mobile crowdsensing [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 14 ): 12000 - 12011 .

LI L , YU X , CAI X L , et al . Contract-theory-based incentive mechanism for federated learning in health crowd sensing [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 5 ): 4475 - 4489 .

ZHANG M W , CHEN S J , SHEN J , et al . PrivacyEAFL: Privacy-enhanced aggregation for federated learning in mobile crowdsensing [J ] . IEEE Transactions on Information Forensics and Security , 2023 , 18 : 5804 - 5816 .

公茂果 , 高原 , 王炯乾 , 等 . 基于进化策略的自适应联邦学习算法 [J ] . 中国科学: 信息科学 , 2023 , 53 ( 3 ): 437 - 453 .

GONG M G , GAO Y , WANG J Q , et al . Adaptive federated learning algorithm based on evolution strategies [J ] . Scientia Sinica (Informationis) , 2023 , 53 ( 3 ): 437 - 453 . (in Chinese)

蒋伟进 , 韩裕清 , 吴玉庭 , 等 . 基于边缘计算的环境监测自适应联邦学习算法 [J ] . 电子学报 , 2023 , 51 ( 11 ): 3061 - 3069 .

JIANG W J , HAN Y Q , WU Y T , et al . Federated learning scheme for environmental monitoring based on edge computing [J ] . Acta Electronica Sinica , 2023 , 51 ( 11 ): 3061 - 3069 . (in Chinese)

CHAKMA A , VIZENA B , CAO T T , et al . Image-based air quality analysis using deep convolutional neural network [C ] // 2017 IEEE International Conference on Image Processing (ICIP) . Piscataway : IEEE , 2017 : 3949 - 3952 .

Single S , Iranmanesh S , Raad R . RealWaste . UCI machine learning repository[EB/OL ] . ( 2023-10-17 )[ 2024-10-16 ] . https://doi.org/10.24432/C5SS4GSingle https://doi.org/10.24432/C5SS4GSingle .

XU C H , QU Y Y , XIANG Y , et al . Asynchronous federated learning on heterogeneous devices: A survey [J ] . Computer Science Review , 2023 , 50 : 100595 .

LI T , SAHU A K , ZAHEER M , et al . Federated optimization in heterogeneous networks [EB/OL ] . ( 2020-04-21 )[ 2024-10-16 ] . https://arxiv.org/abs/1812.06127v5 https://arxiv.org/abs/1812.06127v5 .

HUANG S , FU L L , LI Y C , et al . A cross-client coordinator in federated learning framework for conquering heterogeneity [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2024 , 1 : 1 - 15 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Blockchain-Based Hierarchical Federated Learning System

Research on Network Attack Detection Method Based on Federated Large Model

An Active Semi-Supervised Short Text Classification Method Based on Federated Learning

Related Author

HU Rong-lei

LIU Si-hui

DUAN Xiao-yi

ZUO Pei-liang

ZHANG Yan-shuo

KANG Hai-yan

ZHANG Yi-fan

WANG Nan-min

Related Institution

Department of Electronics and Information Engineering, Beijing Electronic Science and Technology Institute

Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing

Computer School, Beijing Information Science and Technology University

Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, School of Cyberspace Science and Techonology, Beijing Jiaotong University

School of Software Engineering, Beijing Jiaotong University

⁰