Location Selection for Air Quality Monitoring With Consideration of Limited Budget and Estimation Error

Accurate acquisition of air quality is important for improving human well-being. However, directly monitoring air quality at all locations is costly. The challenge is how we can select a small number of locations to monitor the air quality such that the estimation error of air quality at other locations can be minimized. In this paper, a general location selection strategy is proposed based on active learning, which involves iterations of a selector and an estimator. We implement four instances of this general strategy to embody it: KAL (Active Learning based on Kriging), TAL (Active Learning based on Regression Tree), KMAL (Active Learning based on Kriging and MPGR) and TMAL (Active Learning based on Regression Tree and MPGR). The estimator of KAL or TAL can estimate the air quality at remaining locations from air quality samples at monitoring locations, leveraging spatial or cross-domain correlation of air quality. The selecting indicators of their selectors are designed to measure the uncertainty of unlabeled samples according to their estimators. KMAL and TMAL are upgrades of the former two, respectively, by introducing MPGR (Manifold Preserving Graph Reduction) to also take the representativeness of unlabeled samples into account. The experimental results show that the proposed strategy can achieve a low estimation error with few monitoring locations. Particularly, given the same budget (i.e., the number of monitoring locations), the estimation error is reduced from about 20 percent of baselines to 15 percent by KAL and to 5 percent by KMAL; and TAML likewise.

[1]  En Wang,et al.  User Recruitment for Enhancing Data Inference Accuracy in Sparse Mobile Crowdsensing , 2020, IEEE Internet of Things Journal.

[2]  Diego Reforgiato Recupero,et al.  Toward Supporting Food Journaling Using Air Quality Data Mining and a Social Robot , 2019, AmI.

[3]  George Suciu,et al.  IoT System for Air Pollutants Assessment in Underground Infrastructures , 2019, ECBS.

[4]  Barak Fishbain,et al.  Optimal Deployment of a Heterogeneous Air Quality Sensor Network , 2019, Journal of Environmental Informatics.

[5]  Victor O. K. Li,et al.  Optimal Citizen-Centric Sensor Placement for Air Quality Monitoring: A Case Study of City of Cambridge, the United Kingdom , 2019, IEEE Access.

[6]  M. Shamim Hossain,et al.  Urban Healthcare Big Data System Based on Crowdsourced and Cloud-Based Air Quality Indicators , 2018, IEEE Communications Magazine.

[7]  Ye Tian,et al.  MCS-RF: mobile crowdsensing–based air quality estimation with random forest , 2018, Int. J. Distributed Sens. Networks.

[8]  Gonçalo Marques,et al.  Monitoring Indoor Air Quality for Enhanced Occupational Health , 2017, Journal of Medical Systems.

[9]  Tianrui Li,et al.  Urban sensing based on human mobility , 2016, UbiComp.

[10]  Daqing Zhang,et al.  iCrowd: Near-Optimal Task Allocation for Piggyback Crowdsensing , 2016, IEEE Transactions on Mobile Computing.

[11]  Su Yang,et al.  Spatiotemporal Context Awareness for Urban Traffic Modeling and Prediction: Sparse Representation Based Variable Selection , 2015, PloS one.

[12]  Daqing Zhang,et al.  CCS-TA: quality-guaranteed online task allocation in compressive crowdsensing , 2015, UbiComp.

[13]  Jie Hao,et al.  Adaptive compressive sensing based sample scheduling mechanism for wireless sensor networks , 2015, Pervasive Mob. Comput..

[14]  Shou-De Lin,et al.  Inferring Air Quality for Station Location Recommendation Based on Urban Big Data , 2015, KDD.

[15]  Shiliang Sun,et al.  Active learning of Gaussian processes with manifold-preserving graph reduction , 2014, Neural Computing and Applications.

[16]  Huadong Ma,et al.  Opportunities in mobile crowd sensing , 2014, IEEE Communications Magazine.

[17]  Daqing Zhang,et al.  4W1H in mobile crowd sensing , 2014, IEEE Communications Magazine.

[18]  Bin Guo,et al.  From participatory sensing to Mobile Crowd Sensing , 2014, 2014 IEEE International Conference on Pervasive Computing and Communication Workshops (PERCOM WORKSHOPS).

[19]  Jiayu Zhou,et al.  Active Matrix Completion , 2013, 2013 IEEE 13th International Conference on Data Mining.

[20]  Minglu Li,et al.  A Compressive Sensing Approach to Urban Traffic Estimation with Probe Vehicles , 2013, IEEE Transactions on Mobile Computing.

[21]  Andreas Krause,et al.  Incentives for Privacy Tradeoff in Community Sensing , 2013, HCOMP.

[22]  Barnabás Póczos,et al.  Active learning and search on low-rank matrices , 2013, KDD.

[23]  Yu Zheng,et al.  U-Air: when urban air quality inference meets big data , 2013, KDD.

[24]  Frank Dürr,et al.  DrOPS: Model-driven optimization for Public Sensing systems , 2013, 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[25]  Valérie Issarny,et al.  Probabilistic registration for large-scale mobile participatory sensing , 2013, 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[26]  Deng Cai,et al.  Manifold Adaptive Experimental Design for Text Categorization , 2012, IEEE Transactions on Knowledge and Data Engineering.

[27]  Jian Tang,et al.  Energy-efficient collaborative sensing with mobile phones , 2012, 2012 Proceedings IEEE INFOCOM.

[28]  Richard J. Gibbens,et al.  Evaluation of velocity fields via sparse bus probe data in urban areas , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[29]  Chun Chen,et al.  Active Learning Based on Locally Linear Reconstruction , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Alexandre M. Bayen,et al.  Estimating arterial traffic conditions using sparse probe data , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[31]  David Evans,et al.  Statistical modelling and analysis of sparse bus probe data in urban areas , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[32]  Deborah Estrin,et al.  Recruitment Framework for Participatory Sensing Data Collections , 2010, Pervasive.

[33]  Wen Hu,et al.  Ear-phone: an end-to-end participatory urban noise mapping system , 2010, IPSN '10.

[34]  Deborah Estrin,et al.  Using Context Annotated Mobility Profiles to Recruit Data Collectors in Participatory Sensing , 2009, LoCA.

[35]  Mark Craven,et al.  An Analysis of Active Learning Strategies for Sequence Labeling Tasks , 2008, EMNLP.

[36]  Zhi-Hua Zhou,et al.  Semisupervised Regression with Cotraining-Style Algorithms , 2007, IEEE Transactions on Knowledge and Data Engineering.

[37]  Rong Yan,et al.  Extreme video retrieval: joint maximization of human and computer performance , 2006, MM '06.

[38]  Rong Jin,et al.  Large-scale text categorization by batch mode active learning , 2006, WWW '06.

[39]  Ying Liu,et al.  Active Learning with Support Vector Machine Applied to Gene Expression Data for Cancer Classification , 2004, J. Chem. Inf. Model..

[40]  Rong Yan,et al.  Automatically labeling video data using multi-class active learning , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[41]  Tsuhan Chen,et al.  An active learning framework for content-based information retrieval , 2002, IEEE Trans. Multim..

[42]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[43]  Edward Y. Chang,et al.  Support vector machine active learning for image retrieval , 2001, MULTIMEDIA '01.

[44]  Nello Cristianini,et al.  Query Learning with Large Margin Classi ersColin , 2000 .

[45]  Greg Schohn,et al.  Less is More: Active Learning with Support Vector Machines , 2000, ICML.

[46]  H. Sebastian Seung,et al.  Selective Sampling Using the Query by Committee Algorithm , 1997, Machine Learning.

[47]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[48]  Bin Guo.  1 Mobile Crowd Sensing and Computing : The Review of an Emergin g Human-Powered Sensing Paradigm , 2015 .

[49]  Shiliang Sun,et al.  Manifold-preserving graph reduction for sparse semi-supervised learning , 2014, Neurocomputing.

[50]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[51]  Ronald Rosenfeld,et al.  Semi-supervised learning with graphs , 2005 .

[52]  Kamal Nigamyknigam,et al.  Employing Em in Pool-based Active Learning for Text Classiication , 1998 .