计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 241000116-9.doi: 10.11896/jsjkx.241000116

• 数据库&大数据&数据科学 • 上一篇    下一篇

城市空气质量数据的时空主动采样与联合推测

稂奥奇1,2, 黄伟杰1,2, 於志勇1,2,3, 黄昉菀1,2,3   

  1. 1 福州大学计算机与大数据学院 福州 350108
    2 福建省网络计算与智能信息处理重点实验室(福州大学) 福州 305108
    3 大数据智能教育部工程研究中心 福州 350108
  • 出版日期:2025-11-15 发布日期:2025-11-10
  • 通讯作者: 黄昉菀(hfw@fzu.edu.cn)
  • 作者简介:1977881391@qq.com
  • 基金资助:
    国家自然科学基金(62332014);福建省促进海洋与渔业产业高质量发展专项资金(FJHYF-ZH-2023-02);福厦泉国家自主创新示范区协同创新平台项目(2022FX5)

Spatiotemporal Active-sampling and Joint Inference of Urban Air Quality Data

LANG Aoqi1,2, HUANG Weijie1,2, YU Zhiyong1,2,3, HUANG Fangwan1,2,3   

  1. 1 College of Computer and Data Science,Fuzhou University,Fuzhou 350108,China
    2 Fujian Key Laboratory of Network Computing and Intelligent Information Processing(Fuzhou University),Fuzhou 350108,China
    3 Engineering Research Center of Big Data Intelligence,Ministry of Education,Fuzhou 350108,China
  • Online:2025-11-15 Published:2025-11-10
  • Supported by:
    National Natural Science Foundation of China(62332014),Fujian Provincial Special Fund for Promoting High-Quality Development of Marine and Fishery Industry(FJHYF-ZH-2023-02) and Fuzhou-Xiamen-Quanzhou National Independent Innovation Demonstration Zone Collaborative Innovation Platform(2022FX5).

PDF (PC)

10

摘要： 当前,城市中的环境数据仍以固定站点作为主流采样方式,但高昂的全采样成本使其难以大规模扩展。在此背景下,通过局部采样并结合推测算法来推断其余未采样数据的方法成为了当前研究的热点。现有的研究通常使用两种不同的模型分别进行主动采样和缺失推测,存在计算成本高和误差易累积等不足。基于此,提出了一种时空主动采样与联合推测一体化模型(Spatiotemporal Active-sampling and Joint Inference,SAJI)。该模型不仅能选择带来高推测精度的采样站点,还可以确定其主动采样时刻,最后利用多测量向量(Multiple Measurement Vector,MMV)恢复算法联合推测出所有站点的缺失值。实验结果表明,相比于基线算法,SAJI可以充分利用时空相关性使得未采样站点获得有价值的预补值,并利用后续的联合推测算法在低采样率下获得最高的推测精度。

关键词: 时空主动采样, 时空相关性, 遗传算法, 压缩感知, 联合推测

Abstract: Currently,environmental data in cities are still sampled by fixed stations as the mainstream sampling method,but the high cost of full sampling makes it difficult to be scaled up on a large scale.In this context,the method of extrapolating the remaining unsampled data through local sampling and inference algorithm has become a hot topic in current research.Existing studies usually use two different models for active sampling and missing inference,respectively,which suffer from the shortcomings of high computational cost and easy accumulation of errors.Based on this,this paper proposes a spatiotemporal active-sampling and joint inference(SAJI) integration model.The model can not only select the sampling sites with high prediction accuracy,but also determine their own active sampling time.Finally,the missing values of all sites can be inferred jointly by using Multiple Mea-surement Vector(MMV) recovery algorithm.The experimental results show that compared with the baseline algorithms,SAJI can make full use of spatiotemporal correlation to obtain valuable prefilled values for the unsampled sites and achieve the highest inference accuracy using the subsequent joint inference algorithm at low sampling rates.

Key words: Spatiotemporal active sampling, Spatiotemporal correlation, Genetic algorithm, Compressed sensing, Joint inference

中图分类号: 

  • TP391
[1]FENG T,SUN Y,SHI Y,et al.Air pollution control policies and impacts:A review[J].Renewable and Sustainable Energy Reviews,2024,191:114071.
[2]SOKHI R S,MOUSSIOPOULOS N,BAKLANOV A,et al.Advances in air quality research-current and emerging challenges[J].Atmospheric Chemistry and Physics Discussions,2021,2021:1-89.
[3]HU J,LIANG Y,FAN Z,et al.Graph Neural Processes for Spa-tio-Temporal Extrapolation[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2023:752-763.
[4]WU Y,ZHUANG D,LABBE A,et al.Inductive graph neural networks for spatiotemporal kriging[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:4478-4485.
[5]WU Z,PAN S,LONG G,et al.Graph wavenet for deep spatial-temporal graph modeling[J].arXiv:1906.00121,2019.
[6]ROTH A,LIEBIG T.Forecasting unobserved node states with spatio-temporal graph neural networks[C]//2022 IEEE International Conference on Data Mining Workshops(ICDMW).IEEE,2022:740-747.
[7]TIAN Y,JIANG Y,LIU Q,et al.Temporal and spatial trends inair quality in Beijing[J].Landscape and urban planning,2019,185:35-43.
[8]LIU T,ZHU Y,YANG Y,et al.Incentive design for air pollution monitoring based on compressive crowdsensing[C]//2016 IEEE Global Communications Conference(GLOBECOM).IEEE,2016:1-6.
[9]PAN Z,YU H,MIAO C,et al.Crowdsensing air quality withcamera-enabled mobile devices[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2017:4728-4733.
[10]XU Y,ZHU Y,QIN Z.Urban noise mapping with a crowd sen-sing system[J].Wireless networks,2019,25:2351-2364.
[11]LIU T,ZHU Y,YANG Y,et al.ALC2:When active learning meets compressive crowdsensing for urban air pollution monitoring[J].IEEE Internet of Things Journal,2019,6(6):9427-9438.
[12]ZHU K,ZHANG A,NIYATO D.Cost-effective active sparseurban sensing:Adversarial autoencoder approach[J].IEEE Internet of Things Journal,2021,8(15):12064-12078.
[13]HUANG W J,GUO X W,YU Z Y,et al.Active Sampling of Air Quality Based on Compressed Sensing Adaptive Measurement Matrix [J].Computer science,2024,51(7):116-123.
[14]ZHENG Y,LIU F,HSIEHH P.U-air:When urban air quality inference meets big data[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2013:1436-1444.
[15]YI X,ZHENG Y,ZHANG J,et al.ST-MVL:Filling missingvalues in geo-sensory time series data[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence.2016.
[16]XIE K,LI X,WANG X,et al.Active sparse mobile crowd sensing based on matrix completion[C]//Proceedings of the 2019 Inernational Conference on Management of Data.2019:195-210.
[17]WANG L,ZHANG D,YANG D,et al.SPACE-TA:Cost-effective task allocation exploiting intradata and interdata correlations in sparse crowdsensing[J].ACM Transactions on Intelligent Systems and Technology(TIST),2017,9(2):1-28.
[18]WANG L,ZHANG D,PATHAK A,et al.CCS-TA:Quality-guaranteed online task allocation in compressive crowdsensing[C]//Proceedings of the 2015 ACM International Joint Confe-rence on Pervasive and Ubiquitous Computing.2015:683-694.
[19]WANG L,ZHANG D,YANG D,et al.Differential location privacy for sparse mobile crowdsensing[C]//2016 IEEE 16th International Conference on Data Mining(ICDM).IEEE,2016:1257-1262.
[20]LIU W,WANG L,WANG E,et al.Reinforcement learning-based cell selection in sparse mobile crowdsensing[J].Computer Networks,2019,161:102-114.
[21]LIU W,YANG Y,WANG E,et al.Multi-dimensional urbansensing in sparse mobile crowdsensing[J].IEEE Access,2019,7:82066-82079.
[22]WANG L,LIU W,ZHANG D,et al.Cell selection with deep reinforcement learning in sparse mobile crowdsensing[C]//2018 IEEE 38th International Conference on Distributed Computing Systems(ICDCS).IEEE,2018:1543-1546.
[23]LIU W,YANG Y,WANG E,et al.User recruitment for enhancing data inference accuracy in sparse mobile crowdsensing[J].IEEE Internet of Things Journal,2019,7(3):1802-1814.
[24]DING Y,RAO B D.Joint dictionary learning and recovery algorithms in a jointly sparse framework[C]//2015 49th Asilomar Conference on Signals,Systems and Computers.IEEE,2015:1482-1486.
[26]BENESTY J,BENESTY J.Speech Enhancement Via Correlation Coefficients[J].Fundamentals of Speech Enhancement,2018:45-64.
[27]SCHOBER P,BOER C,SCHWARTEL A.Correlation coeffi-cients:appropriate use and interpretation[J].Anesthesia & Analgesia,2018,126(5):1763-1768.
[28]ZHENG Y,YI X,LI M,et al.Forecasting fine-grained air quality based on big data[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2015:2267-2276.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发