Abstract
Urban air quality information, e.g., PM2.5 concentration, is of great importance to both the government and society. Recently, there is a growing interest in developing low-cost sensors, installed on moving vehicles, for fine-grained air quality measurement. However, low-cost mobile sensors typically suffer from low accuracy and thus need careful calibration to preserve a high measurement quality. In this paper, we propose a two-phase data calibration method consisting of a linear part and a nonlinear part. We use MLS (multiple least square) to train the linear part, and use RF (random forest) to train the nonlinear part. We propose an automatic feature selection algorithm based on AIC (Akaike information criterion) for the linear model, which helps avoid overfitting due to the inclusion of inappropriate features. We evaluate our method extensively. Results show that our method outperforms existing approaches, achieving an overall accuracy improvement of 16.4% in terms of PM2.5 levels compared with state-of-the-art approach.
- C.M. Bishop. 2007. Pattern Recognition and Machine Learning. Springer (2007).Google Scholar
- H. Bozdogan. 1987. Model selection and Akaike's Information Criterion (AIC): The general theory and its analytical extensions. Psychometrika 52, 3 (1987), 345--370.Google ScholarCross Ref
- Central Moving Average. 2017. https://en.wikipedia.org/wiki/Moving_average. (2017).Google Scholar
- L. Chen, Y.Y. Cai, Y.F. Ding, M.Q. Lv, C.L. Yuan, and G.C. Chen. 2016. Spatially Fine-grained Urban Air Quality Estimation Using Ensemble Semi-supervised Learning and Pruning. In Proc. of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Google ScholarDigital Library
- W.H. Chen, S.H. Hsu, and H.P. Shen. 2005. Application of SVM and ANN for intrusion detection. Computers 8 Operations Research 32, 10 (2005), 2617--2634. Google ScholarDigital Library
- Y. Cheng, X.C. Li, Z.J. Li, S.X. Jiang, Y.L. Li, J. Jia, and X.F. Jiang. 2014. AirCloud: A Cloud-based Air-quality Monitoring System for Everyone. In Proc. of the 12th ACM Conference on Embedded Networked Sensor Systems. Google ScholarDigital Library
- W. Dong, G.Y. Guan, Y. Chen, K. Guo, and Y. Gao. 2015. Mosaic: Towards City Scale Sensing with Mobile Sensor Networks. In Proc. of the 21st IEEE International Conference on Parallel and Distributed Systems. Google ScholarDigital Library
- X.W. Fang and I. Bate. 2017. Using Multi-parameters for Calibration of Low-cost Sensors in Urban Environment. In Proc. of the International Conference on Embedded Wireless Systems and Networks.Google Scholar
- C. Frost and Thompson S.G. 2000. Correcting for regression dilution bias: comparison of methods for a single predictor variable. Journal of the Royal Statistical Society Series A 163, 2 (2000), 173--189.Google ScholarCross Ref
- K.B. Fu, W. Ren, and W. Dong. 2017. Multihop Calibration for Mobile Sensing: k-hop Calibratability and Reference Sensor Deployment. In Proc. of IEEE International Conference on Computer Communications.Google Scholar
- Y. Gao, W. Dong, K. Guo, X. Liu, Y. Chen, X.J. Liu, J.J. Bu, and C. Chen. 2016. Mosaic: A Low-Cost Mobile Sensing System for Urban Air Quality Monitoring. In Proc. of IEEE International Conference on Computer Communications.Google Scholar
- Machine Learning in Python tools. 2017. Scikit-learn. http://scikit-learn.org. (2017).Google Scholar
- The Mathworks Inc. 2014. Neural Network Toolbox Sample Data Sets for Shallow Networks. (2014).Google Scholar
- Journal of Toxicology and Environmental Health. 2017. http://www.tandfonline.com/toc/uteh20/current. (2017).Google Scholar
- B. Maag, O. Saukh, D. Hasenfratz, and L. Thiele. 2016. Pre-Deployment Testing, Augmentation and Calibration of Cross-Sensitive Sensors. In Proc. of the International Conference on Embedded Wireless Systems and Networks. Google ScholarDigital Library
- B. Maag, Z.M. Zhou, O. Saukh, and L. Thiele. 2017. SCAN: Multi-Hop Calibration for Mobile Sensor Arrays. Proc. of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 1, 2 (2017), Article 19. Google ScholarDigital Library
- M. Martin, J. Santos, H. Vasquez, and J. Agapito. 1999. Study of the interferences of NO2 and CO in solid state commercial sensors. Sensors and Actuators B: Chemical 58, 1 (1999), 469--473.Google ScholarCross Ref
- M. Mead, O. Popoola, G. Stewart, P. Landshoff, M. Calleja, M. Hayes, J. Baldovi, M. McLeod, T. Hodgson, and Dicks J. 2013. The use of electrochemical sensors for monitoring urban air quality in low-cost, highdensity networks. Atmospheric Environment 70 (2013), 186--203.Google ScholarCross Ref
- M. I. Mead, O. A. M. Popoola, G. B. Stewart, P. Landshoff, M. Calleja, M. Hayes, J. J. Baldovi, M. W. Mcleod, T. F. Hodgson, and J. Dicks. 2013. The use of electrochemical sensors for monitoring urban air quality in low-cost, high-density networks. Atmospheric Environment 70, 2 (2013), 186--203.Google ScholarCross Ref
- Dylos Air Quality Monitor. 2017. Dylos DC1700. http://www.dylosproducts.com/dc1700.html. (2017).Google Scholar
- R. Piedrahita, Y. Xiang, N. Masson, J. Ortega, A. Collier, Y. Jiang, K. Li, R. Dick, Q. Lv, and M. Hannigan. 2014. The next generation of low-cost personal air quality sensors for quantitative exposure monitoring. Atmospheric Measurement Techniques 7, 10 (2014), 3325--3336.Google ScholarCross Ref
- PM2.5 Level. 2017. http://www.dwz.cn/cnnRO. (2017).Google Scholar
- D. Posada and T.R. Buckley. 2004. Model selection and model averaging in phylogenetics: advantages of akaike information criterion and bayesian approaches over likelihood ratio tests. Systematic Biology 53, 5 (2004), 793--808.Google ScholarCross Ref
- O. Saukh, D. Hasenfratz, and L. Thiele. 2015. Reducing Multi-hop Calibration Errors in Large-scale Mobile Sensor Networks. In Proc. of the 14th International Conference on Information Processing in Sensor Networks. Google ScholarDigital Library
- SDS011 Particle Sensor. 2017. NOVA SDS011. http://www.inovafitness.com/a/minyongchanpin/chuanganqilei/2015/0522/32.html. (2017).Google Scholar
- J. Shang, Y. Zheng, and W. Tong. 2014. Inferring gas consumption and pollution emission of vehicles throughout a city. In Proc. of the 20th International Conference on Knowledge Discovery and Data Mining. Google ScholarDigital Library
- L. Spinelle, M. Gerboles, M.G. Villani, M. Aleixandre, and F. Bonavitacola. 2015. Field calibration of a cluster of low-cost available sensors for air quality monitoring. part a: Ozone and nitrogen dioxide. Sensors and Actuators B: Chemical 215 (2015), 249--257.Google ScholarCross Ref
- Y. Xiang, L.S. Bai, R. Piedrahita, R.P. Dick, Q. Lv, M. Hannigan, and L. Shang. 2012. Collaborative Calibration and Sensor Placement for Mobile Sensor Networks. In Proc. of the 11th International Conference on Information Processing in Sensor Networks. Google ScholarDigital Library
- Y. Zheng, F. Liu, and H.P. Hsieh. 2013. U-Air: when urban air quality inference meets big data. In Proc. of the 19th International Conference on Knowledge Discovery and Data Mining. Google ScholarDigital Library
Index Terms
- Calibrating Low-Cost Sensors by a Two-Phase Learning Approach for Urban Air Quality Measurement
Recommendations
Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration: A Survey and Critical Analysis
The significance of air pollution and the problems associated with it are fueling deployments of air quality monitoring stations worldwide. The most common approach for air quality monitoring is to rely on environmental monitoring stations, which ...
Pre-Deployment Testing, Augmentation and Calibration of Cross-Sensitive Sensors
EWSN '16: Proceedings of the 2016 International Conference on Embedded Wireless Systems and NetworksOver the past few years, many low-cost pollution sensors have been integrated into measurement platforms for air quality monitoring. However, using these sensors is challenging: concentrations of toxic substances in ambient air often lie at sensors' ...
Quality Aware Graph Learning Regularization For Heterogeneous Air Quality Sensor Networks
EWSN '23: Proceedings of the 2023 International Conference on embedded Wireless Systems and NetworksIn recent years, the graph signal processing (GSP) field has brought signal processing techniques to numerous areas. Among them, graphs have been used for various applications in sensor networks for air quality monitoring. One of the main tasks consists ...
Comments