Skip to main content

Advertisement

Log in

Usage of output-dependent data scaling in modeling and prediction of air pollution daily concentration values (PM10) in the city of Konya

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

This paper presents the combination of a data preprocessing called output-dependent data scaling (ODDS) and adaptive network-based fuzzy inference system (ANFIS) to predict the air pollution daily levels including particulate matter (PM10) concentration values belonging to the city of Konya in Turkey. Also, we have used the regression models including least square regression, partial least square regression, and multivariate linear regression as prediction models in addition to ANFIS model. Data transformation or normalization methods should be used to increase the performance of used prediction models and are used prior to prediction algorithms. In this study, we have used the output-dependent data scaling method as data transformation method and combined it with ANFIS and regression models. PM10 concentration dataset has been taken from Air Quality Statistics database of Turkish Statistical Institute. In PM10 concentration dataset, the mean values belonging to seasons of winter period have been used with the aim of watching the air pollution changes between dates of December, 1, 2003 and December, 30, 2005 in the city of Konya. In the forecasting of PM10 concentration in Konya province, temperature (°C), humidity (%), pressure (kPa), and wind velocity (km/h) attributes have been used. The experimental results demonstrated that the ODDS method has obtained very promising results in the prediction of PM10 concentration values.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

Abbreviations

MAE:

Mean absolute error

MSE:

Mean square error

IA:

Index of agreement

RMSE:

Root mean square error

P :

Pressure, kPa

R 2 :

Determination coefficient

T :

Temperature (°C)

y m :

Average of observed points

References

  1. http://www.airinfonow.com/pdf/particulate_matter.pdf. Accessed 2011

  2. Aydın ME, Durduran SS, Özcan S, Bedük F (2007) Konya’da Hava Kalitesi Değişiminin Coğrafi Bilgi Sistemi (CBS) İle Değerlendirilmesi, 7. Ulusal Çevre Mühendisliği Kongresi, Yaşam Çevre Teknoloji, 831–838, 24–27 Ekim 2007, İzmir

  3. http://www.cevreonline.com/emisyon/hava_etkiler.htm. Accessed 2011

  4. Durduran SS, Gökce V, Öztürk B (2008) Kent Bilgi Sisteminde Hava Kirliliği ve Sağlığımıza Etkileri, Ulusal Hava Kalitesi Sempozyumu UHAKS, Konya

  5. Özkan O, Azgın ŞT, Solmaz A, Özdemir Ö (2008) Kayseri İlindeki PM Konsantrasyonunun Yapay Sinir Ağları İle Tahmini, Black sea International environmental symposium, Giresun, Turkey, pp 468–472, 25–29 Aug 2008

  6. Dong M, Yang D, Kuang Y, He D, Erdal S, Kenski S (2009) PM2.5 concentration prediction using hidden semi-Markov model-based times series data mining. Expert Syst Appl 36(5):9046–9055

    Article  Google Scholar 

  7. Grivas G, Chaloulakou A (2006) Artificial neural network models for prediction of PM10 hourly concentrations, in the Greater Area of Athens, Greece. Atmos Environ 40(7):1216–1229

    Article  Google Scholar 

  8. http://www.wunderground.com/history/airport/LTAN/2006/5/23/DailyHistory.html?req_city=NA&req_state=NA&req_statename=NA. Accessed 2011

  9. Jang J-SR (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685

    Article  Google Scholar 

  10. Jang J-SR (1992) Self-learning fuzzy controllers based on temporal backpropagation. IEEE Trans Neural Netw 3(5):714–723

    Article  Google Scholar 

  11. Polat K, Güneş S (2006) A hybrid medical decision making system based on principles component analysis, k-NN based weighted pre-processing and adaptive neuro-fuzzy inference system. Digit Signal Process 16(6):913–921

    Article  Google Scholar 

  12. Akdemir B, Kara S, Polat K, Güven A, Güneş A (2008) Ensemble adaptive network-based fuzzy inference system with weighted arithmetical mean and application to diagnosis of optic nerve disease from visual-evoked potential signals. Artif Intell Med 43(2):141–149

    Article  Google Scholar 

  13. http://www.ipredict.it/ErrorStatistics.aspx. Accessed 2011

  14. Everitt BS (2002) Cambridge dictionary of statistics (2nd edn). CUP. ISBN 0-521-81099-x

  15. http://www.cevreonline.com/emisyon/hava_etkiler.htm. Accessed 2011

  16. Polat K (2010) Çıkısa Bağlı Veri Ölçekleme (ÇBVÖ) Yöntemi ve Parkinson Hastalığının Kümelenmesine Uygulanması. TIPTEKNO 2010, Antalya 14–16 Ekim

  17. http://www.itl.nist.gov/div898/handbook/pmd/section1/pmd141.htm. Accessed 2011

  18. Björck Å (1996) Numerical methods for least squares problems. SIAM. ISBN 978-0-898713-60-2

  19. http://en.wikipedia.org/wiki/Partial_least_squares_regression. Accessed 2011

  20. Frank I, Friedman J (1993) A statistical view of some chemometrics regression tools. Technometrics 35(2):109–148

    Article  MATH  Google Scholar 

  21. Haenlein M, Kaplan AM (2004) A beginner’s guide to partial least squares analysis. Understanding Statistics 3(4):283–297

    Article  Google Scholar 

  22. http://www.mathworks.com/help/toolbox/stats/mvregress.html. Accessed 2011

  23. Menlik T, Kırmacı V, Usta H (2009) Modeling of freeze drying behaviors of strawberries by using artificial neural network. J Therm Sci Technol 29:11–21

    Google Scholar 

  24. Yildirim Y, Bayramoğlu M (2006) Adaptive neuro-fuzzy based modelling for prediction of air pollution daily levels in city of Zonguldak. Chemosphere 63:1575–1582

    Article  Google Scholar 

  25. Polat K (2001) A novel data preprocessing method to estimate the air pollution (SO2): neighbor-based feature scaling (NBFS), Neural Comput Appl (in Press), doi:10.1007/s00521-011-0602-x

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Kemal Polat.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Polat, K., Durduran, S.S. Usage of output-dependent data scaling in modeling and prediction of air pollution daily concentration values (PM10) in the city of Konya. Neural Comput & Applic 21, 2153–2162 (2012). https://doi.org/10.1007/s00521-011-0661-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-011-0661-z

Keywords

Navigation