基于压缩感知自适应测量矩阵的空气质量主动采样

doi:10.11896/jsjkx.230400111

计算机科学 ›› 2024, Vol. 51 ›› Issue (7): 116-123.doi: 10.11896/jsjkx.230400111

• 数据库&大数据&数据科学 • 上一篇下一篇

基于压缩感知自适应测量矩阵的空气质量主动采样

黄伟杰¹, 郭贤伟¹, 於志勇^1,2, 黄昉菀^1,2

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 350108

收稿日期:2023-04-16 修回日期:2023-09-08 出版日期:2024-07-15 发布日期:2024-07-10
通讯作者: 黄昉菀(hfw@fzu.edu.cn)
作者简介:(211027099@fzu.edu.cn)
基金资助:
国家自然科学基金(61772136);福建省引导性项目(2020H0008);福建省中青年教师教育科研项目(JAT210007)

Active Sampling of Air Quality Based on Compressed Sensing Adaptive Measurement Matrix

HUANG Weijie¹, GUO Xianwei¹, YU Zhiyong^1,2, HUANG Fangwan^1,2

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

Received:2023-04-16 Revised:2023-09-08 Online:2024-07-15 Published:2024-07-10
About author:HUANG Weijie,born in 1999,postgra-duate.His main research interests include machine learning and so on.
HUANG Fangwan,born in 1980,Ph.D,senior lecturer,is a member of CCF(No.D3015M).Her main research interests include computational intelligence,machine learning and big data analysis.
Supported by:
National Natural Science Foundation of China(61772136),Fujian Provincial Guiding Project(2020H0008) and Educational Research Project for Young and Middle-aged Teachers in Fujian Province(JAT210007).

摘要/Abstract

摘要： 随着城市化进程的不断加快,工业发展、人口聚集使得空气质量问题日益严峻。出于对采集成本的考虑,对空气质量的主动采样正受到越来越多的关注。但现有模型要么只能迭代选择采样位置,要么难以实时更新采样算法。基于此,提出了一种基于压缩感知自适应测量矩阵的空气质量主动采样方法,将采样位置的选择问题转化为矩阵的列子集选择问题。该方法首先利用历史完整数据进行字典学习,然后将学习后的字典经过列子集选择后得到能够指导批量采样的自适应测量矩阵,最后结合利用空气质量数据特性构建的稀疏基矩阵恢复出未采样的数据。该方法使用压缩感知模型一体化实现采样和推断,避免了使用多个模型的不足。此外,考虑到空气质量的时序变动问题,在每一次的主动采样后,字典还会利用最新数据进行在线更新以指导下一次的采样。两个真实数据集上的实验结果表明,经过字典学习后得到的自适应测量矩阵在低于20%的多个采样率下,恢复性能优于所有基线。

关键词: 群智感知, 压缩感知, 自适应测量矩阵, 字典学习, 主动采样

Abstract: With the continuous acceleration of urbanization,industrial development and population agglomeration make the pro-blem of air quality increasingly serious.Due to the cost of sampling,more and more attention is paid to active sampling of air qua-lity.However,the existing models can either only select the sampling location iteratively or hardly update the sampling algorithm in real time.Motivated by this,an active sampling method of air quality based on compressed sensing adaptive measurement matrix is proposed in this paper.The problem of sampling location selection is transformed into the column subset selection problem of the matrix.Firstly,the historical complete data is used for dictionary learning.After column subset selection of the learned dictionary,an adaptive measurement matrix that can guide batch sampling is obtained.Finally,the unsampled data is recovered by using the sparse basis matrix constructed by the data characteristics of air quality.This method uses a compressed sensing model to realize sampling and inference integrally,which avoids the shortcoming of using multiple models.In addition,considering the ti-ming variation of air quality,after each active sampling,the dictionary is updated online with the latest data to guide the next sampling.Experimental results on two real datasets show that the adaptive measurement matrix obtained after dictionary learning has better recovery performance than all baselines at multiple sampling rates less than 20%.

Key words: Crowd sensing, Compressed sensing, Adaptive measurement matrix, Dictionary learning, Active sampling

中图分类号:

TP391

黄伟杰, 郭贤伟, 於志勇, 黄昉菀. 基于压缩感知自适应测量矩阵的空气质量主动采样[J]. 计算机科学, 2024, 51(7): 116-123. https://doi.org/10.11896/jsjkx.230400111

HUANG Weijie, GUO Xianwei, YU Zhiyong, HUANG Fangwan. Active Sampling of Air Quality Based on Compressed Sensing Adaptive Measurement Matrix[J]. Computer Science, 2024, 51(7): 116-123. https://doi.org/10.11896/jsjkx.230400111

参考文献

[1]SHADDICK G,THOMAS M L,MUDU P,et al.Half theworld's population are exposed to increasing air pollution[J].NPJ Climate and Atmospheric Science,2020,3(1):1-5.
[2]SOKHI R S,MOUSSIOPOULOS N,BAKLANOV A,et al.Advances in air quality research-current and emerging challenges[J].Atmospheric Chemistry and Physics,2022,22(7):4615-4703.
[3]YANG X,ZHANG Z.An attention-based domain spatial-temporal meta-learning(ADST-ML) approach for PM2.5 concentration dynamics prediction[J].Urban Climate,2023,47:101363.
[4]GUO B,WANG Z,YU Z,et al.Mobile crowd sensing and computing:The review of an emerging human-powered sensing para-digm[J].ACM Computing Surveys(CSUR),2015,48(1):1-31.
[5]JEZDOVIĆ I,POPOVIĆ S,RADENKOVIĆ M,et al.A crowd-sensing platform forreal-time monitoring and analysis of noise pollution in smart cities[J].Sustainable Computing:Informatics and Systems,2021,31:100588.
[6]BALLATORE A,VERHAGEN T J,LI Z,et al.This city is not a bin:crowd mapping the distribution of urban litter[J].Journal of Industrial Ecology,2022,26(1):197-212.
[7]SHENG X,TANG J,ZHANG W.Energy-efficient collaborative sensing with mobile phones[C]//Proceedings of IEEE Confe-rence on Computer Communications(INFOCOM).IEEE,2012:1916-1924.
[8]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.
[9]SONG X,GUO Y,LI N,et al.A novel approach for missing data prediction in coevolving time series[J].Computing,2019,101(11):1565-1584.
[10]BUDD S,ROBINSON E C,KAINZ B.A survey on active lear-ning and human-in-the-loop deep learning for medical image ana-lysis[J].Medical Image Analysis,2021,71:102062.
[11]DONOHO D L.Compressed sensing[J].IEEE Transactions on Information Theory,2006,52(4):1289-1306.
[12]TSAIG Y,DONOHO D L.Extensions of compressed sensing[J].Signal Processing,2006,86(3):549-571.
[13]CAI C,BAI E,JIANG X Q,et al.Simultaneous Audio Encryption and Compression Using Parallel Compressive Sensing and Modified Toeplitz Measurement Matrix[J].Electronics,2021,10(23):2902.
[14]MENDELSON S,PAJOR A,TOMCZAK-JAEGERMANN N.Uniform uncertainty principle for Bernoulli and subgaussian ensembles[J].Constructive Approximation,2008,28(3):277-289.
[15]HEGDE C,SANKARANARAYANAN A C,YIN W,et al.Numax:A convex approach for learning near-isometric linear embeddings[J].IEEE Transactions on Signal Processing,2015,63(22):6109-6121.
[16]TROPP J A.A mathematical introduction to compressive sen-sing [J].Bulletin of the American Mathematical Society,2017,54(1):151-165.
[17]XU K,LI Y,REN F.A data-driven compressive sensing framework tailored for energy-efficient wearable sensing[C]//Proceedings of 2017 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2017:861-865.
[18]LI S,ZHANG W,CUI Y,et al.Joint design of measurement matrix and sparse support recovery method via deep auto-encoder[J].IEEE Signal Processing Letters,2019,26(12):1778-1782.
[19]HUIJBEN I A M,VEELING B S,VAN SLOUN R J G.Deep probabilistic subsampling for task-adaptive compressed sensing[C]//Proceedings of 8th International Conference on Learning Representations.ICLR,2020.
[20]SHAHRASBI B,RAHNAVARD N.Model-based nonuniformcompressive sampling and recovery of natural images utilizing a wavelet-domain universal hidden Markov model[J].IEEE Transactions on Signal Processing,2016,65(1):95-104.
[21]MALLOY M L,NOWAK R D.Near-optimal adaptive com-pressed sensing[J].IEEE Transactions on Information Theory,2014,60(7):4001-4012.
[22]XIE K,LI X,WANG X,et al.Active sparse mobile crowd sen-sing based on matrix completion[C]//Proceedings of the 2019 International Conference on Management of Data.2019:195-210.
[23]TANG G.Seismic data reconstruction and denoising based oncompressive sensing and sparse representation[D].Beijing:Tsinghua University,2010.
[24]CAO J J,XIAO J M,ZHU Y F,et al.Efficient shallow seismicacquisition method based on compressed sensing theory[J].Progress in Geophysics,2022,37(5):1920-1932.
[25]LIU W,WANG L,WANG E,et al.Reinforcement learning-based cell selection in sparse mobile crowdsensing[J].Computer Networks,2019,161:102-114.
[26]WANG L,LIU W,ZHANG D,et al.Cell selection with deep reinforcement learning in sparse mobile crowdsensing[C]//Proceedings of 2018 IEEE 38th International Conference on Distri-buted Computing Systems(ICDCS).IEEE,2018:1543-1546.
[27]ZHANG Z,XU Y,YANG J,et al.A survey of sparse representation:algorithms and applications[J].IEEE Access,2015,3:490-530..
[28]PATI Y C,REZAIIFAR R,KRISHNAPRASAD P S.Orthogonal matching pursuit:Recursive function approximation with applications to wavelet decomposition[C]//Proceedings of 27th Asilomar Conference on Signals,Systems and Computers.IEEE,1993:40-44.
[29]CHEN S S,DONOHO D L,SAUNDERS M A.Atomic decomposition by basis pursuit[J].SIAM Review,2001,43(1):129-159.
[30]BLUMENSATH T,DAVIES M E.Iterative hard thresholding for compressed sensing[J].Applied and Computational Harmonic Analysis,2009,27(3):265-274.
[31]AHARON M,ELAD M,BRUCKSTEIN A.K-SVD:An algo-rithm for designing overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[32]BOUTSIDIS C,MAHONEY M W,DRINEAS P.An improved approximation algorithm for the column subset selection pro-blem[C]//Proceedings of the Twentieth Annual ACM-SIAM Symposium on Discrete algorithms.Society for Industrial and Applied Mathematics,2009:968-977.
[33]PAN C T.On the existence and computation of rank-revealing LU factorizations[J].Linear Algebra and Its Applications,2000,316(1/2/3):199-222.
[34]BOUTSIDIS C,DRINEAS P,MAGDON-ISMAIL M.Near-optimal column-based matrix reconstruction[J].SIAM Journal on Computing,2014,43(2):687-717.
[35]LIANG X,LI S,ZHANG S,et al.PM2.5 data reliability,consis-tency,and air quality assessment in five Chinesecities[J].Journal of Geophysical Research:Atmospheres,2016,121(17):10220-10236.
[36]BURBIDGE R,ROWLAND J J,KING R D.Active learning for regression based on query by committee[J].Lecture Notes in Computer Science,2007,4881:209-218.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于压缩感知自适应测量矩阵的空气质量主动采样

Active Sampling of Air Quality Based on Compressed Sensing Adaptive Measurement Matrix

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0