Neural Computing and Applications

, Volume 27, Issue 5, pp 1191–1206 | Cite as

HISYCOL a hybrid computational intelligence system for combined machine learning: the case of air pollution modeling in Athens

  • Ilias Bougoudis
  • Konstantinos Demertzis
  • Lazaros IliadisEmail author


The analysis of air quality and the continuous monitoring of air pollution levels are important subjects of the environmental science and research. This problem actually has real impact in the human health and quality of life. The determination of the conditions which favor high concentration of pollutants and most of all the timely forecast of such cases is really crucial, as it facilitates the imposition of specific protection and prevention actions by civil protection. This research paper discusses an innovative threefold intelligent hybrid system of combined machine learning algorithms HISYCOL (henceforth). First, it deals with the correlation of the conditions under which high pollutants concentrations emerge. On the other hand, it proposes and presents an ensemble system using combination of machine learning algorithms capable of forecasting the values of air pollutants. What is really important and gives this modeling effort a hybrid nature is the fact that it uses clustered datasets. Moreover, this approach improves the accuracy of existing forecasting models by using unsupervised machine learning to cluster the data vectors and trace hidden knowledge. Finally, it employs a Mamdani fuzzy inference system for each air pollutant in order to forecast even more effectively its concentrations.


Ensembles learning Ensembles of classifiers Fuzzy inference systems Feedforward neural network Random forest Air pollution 


  1. 1.
    Bougoudis I, Iliadis L, Papaleonidas A (2014) Fuzzy inference ANN ensembles for air pollutants modeling in a major urban area: the Case of Athens. Eng Appl Neural Netw Commun Comput Inf Sci 459(2014):1–14Google Scholar
  2. 2.
    Breiman L (2001) Random Forests. Mach Learn 45(1):5–32. doi: 10.1023/A:1010933404324 MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Haykin S (2009) Neural networks and learning machines, 3rd edn. New York, Pearson EducationGoogle Scholar
  4. 4.
    Hooyberghs J, Mensink C, Dumont G, Fierens F, Brasseur O (2005) A neural network forecast for daily average PM10 concentrations in Belgium. Atmos Environ 39(18):3279–3289CrossRefGoogle Scholar
  5. 5.
    Iliadis L (2007) Intelligent information systems and applications in risk estimation. Stamoulis publication, Thessaloniki. ISBN: 978-960-6741-33-3 AGoogle Scholar
  6. 6.
    Inal F (2010) Artificial neural network prediction of tropospheric ozone concentrations in Istanbul, Turkey. CLEAN Soil Air Water 38(10):897–908MathSciNetCrossRefGoogle Scholar
  7. 7.
    Jollois FX, Poggi JM, Portier B (2009) Three non-linear statistical methods for analyzing PM10 pollution in Rouen area CS-BIGS 3(1):1–17 CS
  8. 8.
    Kadri C, Tian F, Zhang L, Dang L, Li G (2013) Neural network ensembles for online gas concentration estimation using an electronic nose. Int J Comput Sci 10(2):1Google Scholar
  9. 9.
    Lei KS, Wan F (2012) Applying ensemble learning techniques to ANFIS for air pollution index prediction in Macau. ISNN 2012, Part I, LNCS 7367. pp 509–516Google Scholar
  10. 10.
    Kohonen Τ (1989) Self-organization and associative memory, 3rd edn. Springer, BerlinCrossRefzbMATHGoogle Scholar
  11. 11.
    Singha KP, Guptaa S, Rai P (2013) Identifying pollution sources and predicting urban air quality using ensemble learning methods. Atmos Environ 80:426–437CrossRefGoogle Scholar
  12. 12.
    Lopez M, Melin P, Castillo O (2007) A method for creating ensemble neural networks using a sampling data approach. Theor Adv Appl Fuzzy Log ASC42 pp. 772–780, SpringerGoogle Scholar
  13. 13.
    Maclin R, Opitz D (1999) Popular ensemble methods: an empirical study. J Artif Intell Res 11:169–198zbMATHGoogle Scholar
  14. 14.
    Mamdani EH, Assilian S (1975) An experiment in linguistic synthesis with a fuzzy logic controller. Int J Man Mach Stud 7(1):1–13CrossRefzbMATHGoogle Scholar
  15. 15.
    Mamdani EH (1974) Application of fuzzy algorithms for the control of a simple dynamic plant. In: Proceedings of IEEE, pp 121–159Google Scholar
  16. 16.
    Ordieres Meré JB, Vergara González EP, Capuz RS, Salaza RE (2005) Neural network prediction model for fine particulate matter (PM). Environ Modell Softw 20:547–559CrossRefGoogle Scholar
  17. 17.
    Ozcan HK, Bilgili E, Sahin U, Bayat C (2007) Modeling of trophospheric ozone concentrations using genetically trained multi-level cellular neural networks. Adv Atmos Sci Springer 24(5):907–914CrossRefGoogle Scholar
  18. 18.
    Ozdemir H, Demir G, Altay G, Albayrak S, Bayat C (2008) Environ Eng Sci 25(9):1249–1254CrossRefGoogle Scholar
  19. 19.
    Paoli C (2011) A neural network model forecasting for prediction of hourly ozone concentration in Corsica. In: Proceedings IEEE of the 10th International Conference on Environment and Electrical Engineering (EEEIC)Google Scholar
  20. 20.
    Paschalidou A, Iliadis L, Kassomenos P, Bezirtzoglou C (2007) Neural modeling of the tropospheric ozone concentrations in an urban site. In: 10th ICEANN, pp 436–445Google Scholar
  21. 21.
    Robles LA, Ortega JC, Fu JS, Reed GD, Chow JC, Watson JG, Moncada-Herrera JA (2008) A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: the case of Temuco, Chile. Atmos Environ 42(35):8331–8340Google Scholar
  22. 22.
    Rokach L (2010) Ensemble-based classifiers. Artif Intell Rev 33(1–2):1–39. doi: 10.1007/s10462-009-9124-7 CrossRefGoogle Scholar
  23. 23.
    Roy S (2012) Prediction of particulate matter concentrations using artificial neural network. Resour Environ 2(2):30–36. doi: 10.5923/ CrossRefGoogle Scholar
  24. 24.
    Takagi Τ, Sugeno M (1985) Fuzzy identification of systems and its applications to modeling and control. IEEE Trans Syst Man Cybern SMC-15(1):116–133CrossRefzbMATHGoogle Scholar
  25. 25.
    Wahab A-SA, Al-Alawi SM (2002) Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks. EM & Softw 17:219–228Google Scholar
  26. 26.
  27. 27.
    Zhou ZH, Wu J, Wei T (2010) Corrigendum to “Ensembling neural networks: many could be better than all”. Artif Intell 174(18):1570CrossRefzbMATHGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2015

Authors and Affiliations

  • Ilias Bougoudis
    • 1
  • Konstantinos Demertzis
    • 1
  • Lazaros Iliadis
    • 1
    Email author
  1. 1.Democritus University of ThraceOrestiadaGreece

Personalised recommendations