Improving air pollution detection accuracy and status monitoring based ‎on supervised learning systems and Internet of Things

Document Type : Research Paper


1 Department of CSE, IFET College of Engineering, Villupuram, India.

2 Department of IT, Annamalai University, Chidambaram, India.


In recent decades air pollution and its associated health risks are in growing numbers. Detecting ‎air pollution in the environment and alarming the people may accomplish various advantages ‎among health monitoring, telemedicine, and industrial sectors. A novel method of detecting air ‎pollution using supervised learning models and an alert system using IoT is proposed. The main ‎aim of the research is manifold: a) Air pollution data is preprocessed using the feature scaling ‎method, b) The feature selection and feature extraction process done followed by performing a ‎Recurrent Neural Network and c) The predicted data is stored in the cloud server, and it provides ‎the end-users with an alert when the threshold pollution index exceeds. The proposed RNN ‎reports enhanced performance when tested against traditional machine learning models such as ‎Convolutional Neural Networks (CNN), Deep Neural Networks(DNN), and Artificial Neural ‎Networks(ANN) for parameters such as accuracy, specificity, and sensitivity.‎


[1] J. Amoh, K. Odame,Deep Neural Networks for Identifying Cough Sounds, IEEE transactions on biomedical circuits
and systems, 2017.
[2] A. Baklanov, P. Mestayer, A. Clappier, S. Zilitinkevich, S. Joffre, A. Mahura and N. Nielsen, Towards improving the
simulation of environmental fields in urban areas through updated/advanced surface fluxes description, Atmospheric
Chemistry and Physics, 8 (2008)523-543.
[3] G. E. Box, G. M. Jenkins, G. C. Reinsel and G. M. Ljung, Time series analysis, forecasting and control. John
Wiley and Sons, 2015.
[4] L. Cagliero, T. Cerquitelli, S. Chiusano, P. Garza, G. Ricupero and X. Xiao, Designing correlations among air
pollution-related data through generalized association rules, in Proceedings of the 2016 IEEE International Conference on Smart Computing, SMARTCOMP 2016, St. Louis, MO, USA, May 2016.
[5] F. Caiazzo, A. Ashok, I. A. Waitz, S. H. L. Yim and S. R. H. Barrett, Air pollution and early deaths in the United
States. Part I: quantifying the impact of major sectors in 2005, Atmospheric Environment, 79, 2013, pp. 198-208.
[6] CERN, Air Status Forecasting, CERN, Geneva, Switzerland, 2001.
[7] M. Demuzere, R. M. Trigo, J. Vila-Guerau de Arellano and N. P. M. Van Lipzig, &e impact of weather and
atmospheric circulation on O3 and PM10 levels at a rural mid-latitude site, Atmospheric Chemistry and Physics,
9(8), 2009, pp. 2695-2714.
[8] L. Diaz-Robles, J. Ortega, J. Fu, G. Reed, J. Chow, J. Watson and J. Moncada-Herrera,A hybrid ARIMA and artificial neural networks design to forecast particulate matter in urban areas, The case of Temuco, Chile, Atmospheric
Environment, 42 (2008) 8331-8340.[9] D. Dominick, M. T. Latif, H. Juahir, A. Z. Aris and S. M. Zain, An assessment of influence of environmental
factors on PM10 and NO2 at selected stations in Malaysia, Sustainable Environment Research, 22(5), 2012, pp.
[10] Y. Gonzalez, C. Carranza and M. Iniguez et al., Inhaled air pollution particulate matter in alveolar macrophages
alters local pro-inflammatory cytokine and peripheral IFN production in response to mycobacterium tuberculosis,
American Journal of Respiratory and Critical Care Medicine, 195, 2017, p. S29.
[11] P. Goyal, A. Chan and N. Jaiswal, Statistical systems for the prediction of respirable suspended particulate matter
in urban cities , Atmospheric Environment, 40 (2006) 2068-2077.
[12] P. S. Gromski, E. Correa, A. A. Vaughan, D. C. Wedge, M. L. Turner and R. Goodacre, A comparison of
different chemometrics approaches for the robust classification of electronic nose data, Analytical and Bioanalytical
Chemistry, 406(29), 2014, pp. 7581-7590.
[13] B. Holmes-gen and W. Barrett,Clean Air Future, Health and Climate Benefits of Zero Emission Vehicles, American Lung Association, Chicago, IL, USA, 2016.
[14] U. A. Hvidtfeldt, M. Ketzel and M. Sørensen et al., Evaluation of the Danish AirGIS air pollution designing
system against measured concentrations of PM2.5, PM10, and black carbon, Environmental Epidemiology, 2(2),
[15] P. Kakabutr, K. S. Chen, V. Wangvisavawit, P.Padungweang and O. Rojanapornpun, Dog cough sound
classification using artificial neural network and the selected relevant features from discrete wavelet transform,
2017 9thnternational Conference on Knowledge and Smart Technology(KST), Chonburi, 2017, pp. 121-125,
[16] A. Kurt and A. Oktay, Forecasting air pollutant indicator levels with geographic systems 3days in advance using
neural networks. Expert Systems with Applications, 37 (2010)7986-7992 .
[17] Y. LeCun, Y. Bengio and G. Hinton, Deep learning nature, 521, 436, 2015.
[18] X. Liang, T. Zou, B. Guo, S. Li, H. Zhang, S. Zhang, H. Huang and S. Chen. Assessing Beijing’s PM2.5pollution,
severity, weather impact, APEC and winter heating. Proceedings of the Royal Society A, Mathematical, Physical
and Engineering Science, 471 (2015) 20150257.
[19] X. Liang, S. Li, S. Zhang, H. Huang and S. Chen, PM2.5data reliability, consistency, and air status assessment
in five Chinese cities, Journal of Geophysical Research, Atmospheres 121, 10, (2016) 220-10,236.
[20] C. Li, N. Hsu and S. Tsay, A study on the potential applications of satellite data in air status monitoring and
forecasting, Atmospheric Environment, 45 (2011) 3663-3675.
[21] X. Li et al., Long short-term memory neural network for air pollutant concentration predictions, Method development and evaluation [J], Elsevier Ltd., Environmental Pollution, September, 231 (2017) 997-1004.
[22] S. A. Mahmoudi, P. D. Cunha Possa, T. Ravet, Th. Drugman, R. Chessini, T. Dutoit and C. Valderrama,Sensorbased System for Automatic Cough Detection and Classification, ICT Innovations 2015 Web Proceedings ISSN ,
(2015) 1857-7288.
[23] B. Ong, K. Sugiura and K. Zettsu, Dynamically pre-trained deep recurrent neural networks using environmental
monitoring data for forecasting PM2.5, Neural Computing and Applications, 27(2015) 1553-1566.
[24] L. Pimpin, L. Retat and D. Fecht et al.,Estimating the costs of air pollution to the National Health Service and
social care, an assessment and forecast up to 2035, PLoS Medicine, Article ID e1002602, 15(7), 2018, pp. 1-16.
[25] K. Polat,A novel data preprocessing method to estimate the air pollution (SO2): neighbor-based feature scaling
(NBFS), Neural Comput and Applic, doi: 10.1007/s00521-011-0602-x.
[26] V. Prybutok, J. Yi and D. Mitchell, Comparison of neural network systems with ARIMA and regression systems
for prediction of Houston’s daily maximum ozone concentrations, European Journal of Operational Research 122,
(2000) 31-40.
[27] Al-R. Rami et al. and Theano, A Python framework for fast computation of mathematical expressions [R], arXiv
preprint arXiv, 1605.02688, 2016.
[28] P. Saide, G. Carmichael, S. Spak, L. Gallardo, A. Osses, M. Mena-Carrasco and M. Pagowski, Forecasting urban
PM10 and PM2.5 pollution episodes in very stable nocturnal conditions and complex terrain using WRF-Chem CO
tracer design, Atmospheric Environment, 45 (2011) 2769- 2780.
[29] D. Saravanan, K. P. Hemalatha, B. Jinitha, Dr. K. Santhosh Kumar and P.Hemalatha, Predict and Measure Air Quality Monitoring System Using Machine Learning, 12(2) (2021) 2554-2561,
[30] D. Saravanan, K. Santhosh Kumar, R. Sathya and U.Palani, An Iot Based Air Quality Monitoring And Air
Pollutant Level Prediction System Using Machine Learning Approach - Dlmnn, International Journal of FutureGeneration Communication and Networking, 13(4), 2020, pp. 925-945.
[31] X. Shi, Z. Chen, H. Wang, D. Y. Yeung, W. K. Wong and W. C. Woo, Convolutional LSTM network, A machine
learning approach for precipitation nowcasting, In Advances in neural information processing systems, (2015) 802-
[33] US Environmental Protection Agency (US EPA),Criteria air pollutants, America’s Children and the Environment,
US EPA, Washington, DC, USA, 2015.
[34] K. Veljanovska and A. Dimoski,Air Status Index Prediction Using Simple Machine Learning Algorithms [J], International Journal of Emerging Trends and Technology in Computer Science (IJETTCS), 7(1), January - February
[35] H. X. Zhao and F. Magoules, Feature selection for support vector regression in the application of building energy prediction, In Proceedings of the 9th IEEE International Symposium on Applied Machine Intelligence and
Informatics,Smolenice, Slovakia, January 2011, pp. 219-223.
[36] S. Zhao, X. Yuan, D. Xiao, J. Zhang and Z. Li, AirNet:a machine learning dataset for air status forecasting, 2018.
Volume 12, Issue 2
November 2021
Pages 1497-1511
  • Receive Date: 14 April 2021
  • Revise Date: 08 June 2021
  • Accept Date: 01 July 2021