Combining the Global and Local Estimation Models for Predicting PM\(_{10}\) Concentrations

  • Han Bin Bae
  • Tae Hyun Kim
  • Rhee Man KilEmail author
  • Hee Yong Youn
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10638)


This paper presents a new way of predicting timely air pollution measure such as the PM\(_{10}\) concentration in Seoul based on a new method of combining the global and local estimation models. In the proposed method, the structure of nonlinear dynamics of generating air pollution data series is analyzed by investigating the attractors in the phase space and this structure is used to build the prediction model. Then, the global estimation model such as the network with Gaussian kernel functions is trained for the air pollution series data. Furthermore, the local estimation model which will recover the errors of the global estimation model using the on-line adaptation method, is also adopted. As a result, the proposed prediction model combining the global and local estimation models provides robust performances of predicting PM\(_{10}\) concentrations.


PM\(_{10}\) concentration Phase space analysis Time series prediction Gaussian kernel functions Global and local estimation models 



This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No. B0717-17-0070).


  1. 1.
    Gardner, M., Dorling, S.: Artificial neural networks (the multilayer perceptron) - a review of applications in the atmosphere sciences. Atmos. Environ. 32, 2627–2636 (1998)CrossRefGoogle Scholar
  2. 2.
    Patricio, P., Alex, T., Jorge, R.: Prediction of PM\(_{2.5}\) concentrations several hours in advance using neural networks in Santiago, Chile. Atmos. Environ. 34, 1189–1196 (2000)CrossRefGoogle Scholar
  3. 3.
    Jiang, D., Zhang, Y., Hu, X., Zeng, Y., Tan, J., Shao, D.: Progress in developing an ANN model for air pollution index forecast. Atmos. Environ. 38, 7055–7064 (2004)CrossRefGoogle Scholar
  4. 4.
    Hooyberghs, J., Mensink, C., Dumont, G., Fierens, F., Brasseur, O.: A neural network forecast for daily average PM\(_{10}\) concentrations in Belgium. Atmos. Environ. 39, 3279–3289 (2005)CrossRefGoogle Scholar
  5. 5.
    Grivas, G., Chaloulakou, A.: Artificial neural network models for prediction of PM\(_{10}\) hourly concentrations in the greater area of Athens, Greece. Atmos. Environ. 40, 1216–1229 (2006)CrossRefGoogle Scholar
  6. 6.
    Cao, Z., Yu, S., Xu G., Chen B., Principe J.: Multiple adaptive kernel size KLMS for Beijing PM2.5 prediction. In: International Joint Conference on Neural Networks, pp. 1403–1407 (2016)Google Scholar
  7. 7.
    Kil, R., Park, S., Kim, S.: Time series analysis based on the smoothness measure of mapping in the phase space of attractors. In: International Joint Conference on Neural Networks, vol. 4, pp. 2584–2589 (1999)Google Scholar
  8. 8.
    Kil, R.: Function approximation based on a network with kernel functions of bounds and locality: an approach of non-parametric estimation. ETRI J. 15, 35–51 (1993)CrossRefGoogle Scholar
  9. 9.
    Kim, D.K., Kil, R.M.: Stock price prediction based on a network with Gaussian kernel functions. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013. LNCS, vol. 8227, pp. 705–712. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-42042-9_87 CrossRefGoogle Scholar
  10. 10.
    Air Korea, PM\(_{10}\) and PM\(_{2.5}\) Concentrations Information on South Korea.
  11. 11.
    Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Han Bin Bae
    • 1
  • Tae Hyun Kim
    • 1
  • Rhee Man Kil
    • 1
    Email author
  • Hee Yong Youn
    • 1
  1. 1.College of SoftwareSungkyunkwan UnivesityJangan-gu, Suwon-siKorea

Personalised recommendations